MICCAI banner
MICCAI 2023 - Accepted Papers, Reviews, Author Feedback
List of topics: Clinical applications - Abdomen Clinical applications - Breast Clinical applications - Cardiac Clinical applications - Dermatology Clinical applications - Fetal Imaging Clinical applications - Lung Clinical applications - Musculoskeletal Clinical applications - Neuroimaging - Brain Development Clinical applications - Neuroimaging - DWI and Tractography Clinical applications - Neuroimaging - Functional Brain Networks Clinical applications - Neuroimaging - Others Clinical applications - Oncology Clinical applications - Ophthalmology Clinical applications - Vascular Computational (Integrative) Pathology Computational Anatomy and Physiology Computer Aided Diagnosis Image Reconstruction Image Registration Image Segmentation Image-Guided Interventions and Surgery Integration of Imaging with Non-Imaging Biomarkers Interventional Imaging Systems Interventional Simulation Systems Machine Learning - Active Learning Machine Learning - Attention models Machine Learning - Continual Learning Machine Learning - Data Efficient Learning Machine Learning - Interpretability / Explainability Machine Learning - Meta-learning Machine Learning - Model Generalizability / Federated Learning Machine Learning - Other Machine Learning - Reinforcement Learning Machine Learning - Semi-/Weakly-/Un-/Self-supervised Representation Learning Machine Learning - Transfer learning Machine Learning - Uncertainty Medical Robotics and Haptics Modalities - Biophotonics Modalities - CT Modalities - EEG/ECG Modalities - Histopathology Modalities - MRI Modalities - Microscopy Modalities - PET/SPECT Modalities - Text (clinical/radiology reports) Modalities - Ultrasound Modalities - Video Modalities - other Population Imaging and Imaging Genetics Rigorous Evaluations of Methodology in Clinical Workflows Surgical Data Science Surgical Planning and Simulation Surgical Scene Understanding Surgical Skill and Work Flow Analysis Surgical Visualization and Mixed/Augmented/Virtual Reality Treatment Response and Outcome/Disease Prediction Visualization in Biomedical Imaging Back to top

List of papers by topics


Clinical applications - Abdomen

  • A Style Transfer-based Augmentation Framework for Improving Segmentation and Classification Performance across Different Sources in Ultrasound Images
  • Anatomical-aware Point-Voxel Network for Couinaud Segmentation in Liver CT
  • Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
  • Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • DAST: Differentiable Architecture Search with Transformer for 3D Medical Image Segmentation
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Eye-Guided Dual-Path Network for Multi-organ Segmentation of Abdomen
  • FedContrast-GPA: Heterogeneous Federated Optimization via Local Contrastive Learning and Global Process-aware Aggregation
  • Few Shot Medical Image Segmentation with Cross Attention Transformer
  • Geometry-adaptive Network for Robust Detection of Placenta Accreta Spectrum Disorders
  • Infusing physically inspired known operators in deep models of ultrasound elastography
  • Intraoperative CT augmentation for needle-based liver interventions
  • Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network
  • LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
  • LOTUS: Learning to Optimize Task-based US representations
  • MDA-SR: Multi-level Domain Adaptation Super-Resolution for Wireless Capsule Endoscopy Images
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Partially Supervised Multi-Organ Segmentation via Affinity-aware Consistency Learning and Cross Site Feature Alignment
  • PET-diffusion: Unsupervised PET Enhancement based on the Latent Diffusion Model
  • Physics-Informed Neural Networks for Tissue Elasticity Reconstruction in Magnetic Resonance Elastography
  • Realistic endoscopic illumination modeling for NeRF-based data generation
  • SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  • Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
  • Segmentation of Kidney Tumors on Non-Contrast CT Images using Protuberance Detection Network
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • SwinUNETR-V2: Stronger Swin Transformers with Stagewise Convolutions for 3D Medical Image Segmentation
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • Trackerless Volume Reconstruction from Intraoperative Ultrasound Images
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification

    • Clinical applications - Breast

  • A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Combating Medical Label Noise via Robust Semi-supervised Contrastive Learning
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Developing Large Pre-trained Model for Breast Tumor Segmentation from Ultrasound Images
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Enhancing Breast Cancer Risk Prediction by Incorporating Prior Images
  • Infusing physically inspired known operators in deep models of ultrasound elastography
  • M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
  • SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
  • SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI
  • Synthesis of Contrast-Enhanced Breast MRI Using T1- and Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanism

    • Clinical applications - Cardiac

  • A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
  • A Spatial-Temporally Adaptive PINN Framework for 3D Bi-Ventricular Electrophysiological Simulations and Parameter Inference
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • CenterlinePointNet++: A new point cloud based architecture for coronary artery pressure drop and vFFR estimation
  • Conditional Physics-Informed Graph Neural Network For Fractional Flow Reserve Assessment
  • ConTrack: Contextual Transformer for Device Tracking in X-ray
  • ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  • DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
  • Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis
  • Forward-solution aided deep-learning framework for patient-specific noninvasive cardiac ectopic pacing localization
  • From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation
  • FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images
  • Gadolinium-Free Cardiac MRI Myocardial Scar Detection by 4D Convolution Factorization
  • Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling
  • GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
  • Maximum Entropy on Erroneous Predictions: Improving model calibration for medical image segmentation
  • Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • NISF: Neural Implicit Segmentation Functions
  • Nonuniformly Spaced Control Points based on Variational Cardiac Image Registration
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • PCMC-T1: Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Semantic difference guidance for the uncertain boundary segmentation of CT left atrial appendage
  • Semi-supervised Class Imbalanced Deep Learning for Cardiac MRI Segmentation
  • STAR-Echo: A Novel Biomarker for Prognosis of MACE in Chronic Kidney Disease Patients using Spatiotemporal Analysis and Transformer-Based Radiomics Models
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets
  • Tensor-based Multimodal Learning for Prediction of Pulmonary Arterial Wedge Pressure from Cardiac MRI
  • Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier
  • Towards Expert-Amateur Collaboration: Prototypical Label Isolation Learning for Left Atrium Segmentation with Mixed-Quality Labels
  • Transformer-based Dual-domain Network for Few-view Dedicated Cardiac SPECT Image Reconstructions
  • Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks
  • Ultrasonic tracking of a rapid-exchange microcatheter with simultaneous pressure sensing for cardiovascular interventions
  • Virtual Heart models help elucidate the role of border zone in sustained monomorphic Ventricular Tachycardia
  • Wall thickness estimation from short axis ultrasound images via temporal compatible deformation learning
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures
  • Weakly Supervised Medical Image Segmentation via Superpixel-guided Scribble Walking and Class-wise Contrastive Regularization

    • Clinical applications - Dermatology

  • A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images
  • An Unsupervised Multispectral Image Registration Network for Skin Diseases
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • Combating Medical Label Noise via Robust Semi-supervised Contrastive Learning
  • ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  • DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
  • Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification
  • ECL: Class-Enhancement Contrastive Learning for Long-tailed Skin Lesion Classification
  • EdgeMixup: Embarrassingly Simple Data Alteration to Improve Lyme Disease Lesion Segmentation and Diagnosis Fairness
  • EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition
  • FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification
  • FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification
  • Fine-Tuning Network in Federated Learning for Personalized Skin Diagnosis
  • MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
  • Medical Boundary Diffusion Model for Skin Lesion Segmentation
  • Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
  • Robust T-Loss for Medical Image Segmentation
  • Skin Lesion Correspondence Localization in Total Body Photography
  • Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis

    • Clinical applications - Fetal Imaging

  • An automated pipeline for quantitative T2* fetal body MRI and segmentation at low field
  • ASC: Appearance and Structure Consistency for Unsupervised Domain Adaptation in Fetal Brain MRI Segmentation
  • Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos
  • Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
  • HACL-Net: Hierarchical Attention and Contrastive Learning Network for MRI-Based Placenta Accreta Spectrum Diagnosis
  • Improving Automatic Fetal Biometry Measurement with Swoosh Activation Function
  • Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction
  • TabAttention: Learning Attention Conditionally on Tabular Data
  • UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation

    • Clinical applications - Lung

  • A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications
  • AirwayFormer: Structure-Aware Boundary-Adaptive Transformers for Airway Anatomical Labeling
  • AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
  • Ariadne's Thread: Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • Automated CT Lung Cancer Screening Workflow using 3D Camera
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Class Specific Feature Disentanglement And Text Embeddings For Multi-Label Generalized Zero Shot CXR Classification
  • CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
  • Contrastive Masked Image-Text Modeling for Medical Visual Representation Learning
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • COVID-19 Pneumonia Classification with Transformer from Incomplete Modalities
  • CT Kernel Conversion Using Multi-Domain Image-to-Image Translation with Generator-Guided Contrastive Learning
  • CTFlow: Mitigating Effects of Computed Tomography Acquisition and Reconstruction with Normalizing Flows
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Deep Learning-Based Air Trapping Quantification using Paired Inspiratory-Expiratory Ultra-Low Dose CT
  • Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy
  • Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification
  • GSDG: Exploring A Global Semantic-guided Dual-stream Graph Model for Automated Volume Differential Diagnosis and Prognosis
  • HENet: Hierarchical Enhancement Network for Pulmonary Vessel Segmentation in Non-contrast CT Images
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • Interpretable Medical Image Classification using Prototype Learning and Privileged Information
  • Inverse Consistency by Construction for Multistep Deep Registration
  • Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
  • Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists
  • Rad-ReStruct: A Novel VQA Benchmark and Method for Structured Radiology Reporting
  • Robust T-Loss for Medical Image Segmentation
  • SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  • Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
  • Topology-Preserving Computed Tomography Super-resolution Based on Dual-stream Diffusion Model
  • Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing
  • Triangular Analysis of Geographical Interplay of Lymphocytes (TriAnGIL): Predicting Immunotherapy Response in Lung Cancer
  • Unpaired Cross-modal Interaction Learning for COVID-19 Segmentation on Limited CT images
  • Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports
  • What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection
  • Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis

    • Clinical applications - Musculoskeletal

  • 3D Dental Mesh Segmentation Using Semantics-Based Feature Learning with Graph-Transformer
  • A Closed-form Solution to Electromagnetic Sensor Based Intraoperative Limb Length Measurement in Total Hip Arthroplasty
  • CAS-Net: Cross-view Aligned Segmentation by Graph Representation of Knees
  • Fine-grained Hand Bone Segmentation via Adaptive Multi-dimensional Convolutional Network and Anatomy-constraint Loss
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Intra-operative Forecasting of Standing Spine Shape with Articulated Neural Kernel Fields
  • Inverse Consistency by Construction for Multistep Deep Registration
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
  • Optimizing the 3D Plate Shape for Proximal Humerus Fractures
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Pelvic Fracture Segmentation Using a Multi-scale Distance-weighted Neural Network
  • Robust Hough and Spatial-To-Angular Transform Based Rotation Estimation for Orthopedic X-Ray Images
  • Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
  • Shape-based pose estimation for automatic standard views of the knee
  • Spatiotemporal Incremental Mechanics Modeling of Facial Tissue Change
  • Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • Thinking Like Sonographers: A Deep CNN Model for Diagnosing Gout from Musculoskeletal Ultrasound

    • Clinical applications - Neuroimaging - Brain Development

  • An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis
  • Brain Anatomy-Guided MRI Analysis for Assessing Clinical Progression of Cognitive Impairment with Structural MRI
  • Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction
  • Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
  • DBTrans: A Dual-Branch Vision Transformer for Multi-modal Brain Tumor Segmentation
  • Discovering Brain Network Dysfunction in Alzheimer’s Disease Using Brain Hypergraph Neural Network
  • Disentangling Site Effects with Cycle-Consistent Adversarial Autoencoder for Multi-site Cortical Data Harmonization
  • Exploring Brain Function-Structure Connectome Skeleton via Self-Supervised Graph-Transformer Approach
  • Joint Representation of Functional and Structural Profiles for Identifying Common and Consistent 3-Hinge Gyral Folding Landmark
  • LSOR: Longitudinally-Consistent Self-Organized Representation Learning
  • Mixing Temporal Graphs with MLP for Longitudinal Brain Connectome Analysis
  • NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
  • Path-based Heterogeneous Brain Transformer Network for Resting-State Functional Connectivity Analysis
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • Robust Segmentation via Topology Violation Detection and Feature Synthesis
  • Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
  • SurfFlow: A Flow-Based Approach for Rapid and Accurate Cortical Surface Reconstruction from Infant Brain MRI
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning

    • Clinical applications - Neuroimaging - DWI and Tractography

  • A coupled-mechanisms modelling framework for neurodegeneration
  • atTRACTive: Semi-automatic white matter tract segmentation using active learning
  • AUA-dE: An adaptive uncertainty guided attention for diffusion MRI models estimation
  • Convolving Directed Graph Edges via Hodge Laplacian for Brain Network Analysis
  • Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI
  • Enhance Early Diagnosis Accuracy of Alzheimer's Disease by Elucidating Interactions between Amyloid Cascade and Tau Propagation
  • Exploring Brain Function-Structure Connectome Skeleton via Self-Supervised Graph-Transformer Approach
  • Flow-based Geometric Interpolation of Fiber Orientation Distribution Functions
  • Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
  • Joint Representation of Functional and Structural Profiles for Identifying Common and Consistent 3-Hinge Gyral Folding Landmark
  • Maximum-entropy estimation of joint relaxation-diffusion distribution using multi-TE diffusion MRI
  • Microstructure Fingerprinting for Heterogeneously Oriented Tissue Microenvironments
  • Mixing Temporal Graphs with MLP for Longitudinal Brain Connectome Analysis
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Relaxation-Diffusion Spectrum Imaging for Probing Tissue Microarchitecture
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • TauFlowNet: Uncovering Propagation Mechanism of Tau Aggregates by Neural Transport Equation
  • Towards Accurate Microstructure Estimation via 3D Hybrid Graph Transformer
  • TractCloud: Registration-free Tractography Parcellation with a Novel Local-global Streamline Point Cloud Representation
  • Uncovering Structural-Functional Coupling Alterations for Neurodegenerative Diseases

    • Clinical applications - Neuroimaging - Functional Brain Networks

  • A coupled-mechanisms modelling framework for neurodegeneration
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • BrainUSL: Unsupervised Graph Structure Learning for Functional Brain Network Analysis
  • CL-ADDA: Contrastive Learning with Amplitude-Driven Data Augmentation for fMRI-Based Individualized Predictions
  • Community-Aware Transformer for Autism Prediction in fMRI Connectome
  • DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics
  • Development and Fast Transferring of General Connectivity-based Diagnosis Model to New Brain Disorders with Adaptive Graph Meta-learner
  • Dynamic Functional Connectome Harmonics
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • Exploring Brain Function-Structure Connectome Skeleton via Self-Supervised Graph-Transformer Approach
  • FE-STGNN: Spatio-Temporal Graph Neural Network with Functional and Effective Connectivity Fusion for MCI Diagnosis
  • Joint Representation of Functional and Structural Profiles for Identifying Common and Consistent 3-Hinge Gyral Folding Landmark
  • Learnable Subdivision Graph Neural Network for Functional Brain Network Analysis and Interpretable Cognitive Disorder Diagnosis
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Overall Survival Time Prediction of Glioblastoma on Preoperative MRI Using Lesion Network Mapping
  • Path-based Heterogeneous Brain Transformer Network for Resting-State Functional Connectivity Analysis
  • Positive Definite Wasserstein Graph Kernel for Brain Disease Diagnosis
  • Predicting Diverse Functional Connectivity from Structural Connectivity Based on Multi-Contexts Discriminator GAN
  • Prediction of Cognitive Scores by Joint Use of Movie-watching fMRI Connectivity and Eye Tracking via Attention-CensNet
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Prior-driven Dynamic Brain Networks for Multi-Modal Emotion Recognition
  • Progressively Coupling Network for Brain MRI Registration in Few-shot Situation
  • Spatiotemporal Hub Identification in Brain Network by Learning Dynamic Graph Embedding on Grassmannian Manifold
  • Uncovering Structural-Functional Coupling Alterations for Neurodegenerative Diseases
  • Wasserstein Distance-Preserving Vector Space of Persistent Homology

    • Clinical applications - Neuroimaging - Others

  • A coupled-mechanisms modelling framework for neurodegeneration
  • A Texture Neural Network to Predict the Abnormal Brachial Plexus from Routine Magnetic Resonance Imaging
  • Acute Ischemic Stroke Onset Time Classification with Dynamic Convolution and Perfusion Maps Fusion
  • Aneurysm Pose Estimation with Deep Learning
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • CoactSeg: Learning from Heterogeneous Data for New Multiple Sclerosis Lesion Segmentation
  • CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph
  • Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies
  • DCAug: Domain-aware & Content-consistent Cross-cycle Framework for Tumor Augmentation
  • DeDA: Deep Directed Accumulator
  • DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data
  • DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • Disentangling Site Effects with Cycle-Consistent Adversarial Autoencoder for Multi-site Cortical Data Harmonization
  • Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs
  • Flexible Unfolding of Circular Structures for Rendering Textbook-Style Cerebrovascular Maps
  • Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model
  • Graph Convolutional Network with Morphometric Similarity Networks for Schizophrenia Classification
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Implicit neural representations for joint decomposition and registration of gene expression images in the marmoset brain
  • Improved flexibility and interpretability of large vessel stroke prognostication using image synthesis and multi-task learning
  • Improving Image-Based Precision Medicine with Uncertainty-Aware Causal Models
  • Inverse Consistency by Construction for Multistep Deep Registration
  • Learning normal asymmetry representations for homologous brain structures
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • Maximum Entropy on Erroneous Predictions: Improving model calibration for medical image segmentation
  • Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
  • Multimodal brain age estimation using interpretable adaptive population-graph learning
  • Multimodal Deep Fusion in Hyperbolic Space for Mild Cognitive Impairment Study
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Neural Pre-Processing: A Learning Framework for End-to-end Brain MRI Pre-processing
  • Physics-Informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
  • Pre-operative Survival Prediction of Diffuse Glioma Patients with Joint Tumor Subtyping
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
  • Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  • Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
  • Simulation of Arbitrary Level Contrast Dose in MRI Using an Iterative Global Transformer Model
  • Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
  • SurfFlow: A Flow-Based Approach for Rapid and Accurate Cortical Surface Reconstruction from Infant Brain MRI
  • Towards frugal unsupervised detection of subtle abnormalities in medical imaging
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
  • Uncovering Heterogeneity in Alzheimer's Disease from Graphical Modeling of the Tau Spatiotemporal Topography
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • Unified surface and volumetric inference on functional imaging data
  • Vertex Correspondence in Cortical Surface Reconstruction
  • Visual-Attribute Prompt Learning for Progressive Mild Cognitive Impairment Prediction

    • Clinical applications - Oncology

  • A One-class Variational Autoencoder (OCVAE) cascade for classifying atypical bone marrow cell sub-types
  • A2FSeg: Adaptive Multi-Modal Fusion Network for Medical Image Segmentation
  • ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment
  • An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment
  • Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Clinical Evaluation of AI-assisted Virtual Contrast Enhanced MRI in Primary Gross Tumor Volume Delineation for Radiotherapy of Nasopharyngeal Carcinoma
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • Deep probability contour framework for tumour segmentation and dose painting in PET images
  • Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
  • Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network
  • Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Multi-Scale Self-Supervised Learning for Longitudinal Lesion Tracking with Optional Supervision
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • Noise2Aliasing: Unsupervised Deep Learning for View Aliasing and Noise Reduction in 4DCBCT
  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  • Second-course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information
  • Self-feedback Transformer: A Multi-label Diagnostic Model for Real-world Pancreatic Neuroendocrine Neoplasms Data
  • Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior

    • Clinical applications - Ophthalmology

  • A Modulatory Elongated Model for Delineating Retinal Microvasculature in OCTA Images
  • A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications
  • Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
  • Automatic Surgical Reconstruction for Orbital Blow-out Fracture via Symmetric Prior Anatomical Knowledge-Guided Adversarial Generative Network
  • Clustering disease trajectories in contrastive feature space for biomarker proposal in age-related macular degeneration
  • Content-Preserving Diffusion Model for Unsupervised AS-OCT image Despeckling
  • Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation
  • Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
  • DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
  • Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training
  • EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
  • Efficient Spatiotemporal Learning of Microscopic Video for Augmented Reality-Guided Phacoemulsification Cataract Surgery
  • Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
  • Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
  • Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Intelligent Virtual B-scan Mirror (IVBM)
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Lesion-aware Contrastive Learning for Diabetic Retinopathy Diagnosis
  • Polar Eyeball Shape Net for 3D Posterior Ocular Shape Representation
  • Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  • RBGNet: Reliable Boundary-Guided Segmentation of Choroidal Neovascularization
  • Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributions
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • RESToring Clarity: Unpaired Retina Image Enhancement using Scattering Transform
  • Retinal Age Estimation with Temporal Fundus Images Enhanced Progressive Label Distribution Learning
  • Retinal Thickness Prediction from Multi-modal Fundus Photography
  • Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology
  • Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
  • Semantic Virtual Shadows (SVS) for Improved Perception in 4D OCT Guided Surgery
  • Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
  • Transformer-based end-to-end classification of variable-length volumetric data
  • UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN
  • VF-HM: Vision Loss Estimation using Fundus Photograph for High Myopia

    • Clinical applications - Vascular

  • 3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images
  • A Modulatory Elongated Model for Delineating Retinal Microvasculature in OCTA Images
  • Aneurysm Pose Estimation with Deep Learning
  • AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
  • CenterlinePointNet++: A new point cloud based architecture for coronary artery pressure drop and vFFR estimation
  • ConTrack: Contextual Transformer for Device Tracking in X-ray
  • CorSegRec: A Topology-Preserving Scheme for Extracting Fully-Connected Coronary Arteries from CT Angiography
  • Flexible Unfolding of Circular Structures for Rendering Textbook-Style Cerebrovascular Maps
  • Geometric Ultrasound Localization Microscopy
  • HENet: Hierarchical Enhancement Network for Pulmonary Vessel Segmentation in Non-contrast CT Images
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Interpretable Deep Biomarker for Serial Monitoring of Carotid Atherosclerosis Based on Three-Dimensional Ultrasound Imaging
  • Intraoperative CT augmentation for needle-based liver interventions
  • MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization
  • Optical Ultrasound Imaging for Endovascular Repair of Abdominal Aortic Aneurysms: A Pilot Study
  • Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  • RBGNet: Reliable Boundary-Guided Segmentation of Choroidal Neovascularization
  • Self-feedback Transformer: A Multi-label Diagnostic Model for Real-world Pancreatic Neuroendocrine Neoplasms Data
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • SPR-Net: Structural Points based Registration for Coronary Arteries across Systolic and Diastolic Phases
  • Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
  • Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier
  • Trackerless Volume Reconstruction from Intraoperative Ultrasound Images
  • Ultrasonic tracking of a rapid-exchange microcatheter with simultaneous pressure sensing for cardiovascular interventions
  • Vision Transformer based Multi-Class Lesion Detection in IVOCT
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures

    • Computational (Integrative) Pathology

  • A One-class Variational Autoencoder (OCVAE) cascade for classifying atypical bone marrow cell sub-types
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment
  • An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment
  • An Anti-Biased TBSRTC-Category Aware Nuclei Segmentation Framework with A Multi-Label Thyroid Cytology Benchmark
  • B-Cos Aligned Transformers Learn Human-Interpretable Features
  • Black-box Domain Adaptative Cell Segmentation via Multi-source Distillation
  • CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
  • Centroid-aware feature recalibration for cancer grading in pathology images
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • Deep Learning for Tumor-associated Stroma Identification in Prostate Histopathology Slides
  • Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning
  • Detection of basal cell carcinoma in whole slide images
  • Detection-free Pipeline for Cervical Cancer Screening of Whole Slide Images
  • Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • Gene-induced Multimodal Pre-training for Image-omic Classification
  • HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis
  • Histopathology Image Classification using Deep Manifold Contrastive Learning
  • IIB-MIL: Integrated instance-level and bag-level multiple instances learning with label disambiguation for pathological image analysis
  • Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification
  • MulHiST: Multiple Histological Staining for Thick Biological Samples via Unsupervised Image-to-Image Translation
  • Multi-modal Pathological Pre-training via Masked Autoencoders for Breast Cancer Diagnosis
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Multi-scope Analysis Driven Hierarchical Graph Transformer for Whole Slide Image based Cancer Survival Prediction
  • Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
  • NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
  • OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image Classification
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • Patients and Slides are Equal: A Multi-level Multi-instance Learning Framework for Pathological Image Analysis
  • Position-aware masked autoencoder for histopathology WSI representation learning
  • Progressive Attention Guidance for Whole Slide Vulvovaginal Candidiasis Screening
  • Recruiting the best teacher modality: A customized knowledge distillation method for IF based nephropathy diagnosis
  • Robust Cervical Abnormal Cell Detection via Distillation from Local-scale Consistency Refinement
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • Transfer Learning-Assisted Survival Analysis of Breast Cancer Relying on the Spatial Interaction Between Tumor-Infiltrating Lymphocytes and Tumors
  • Triangular Analysis of Geographical Interplay of Lymphocytes (TriAnGIL): Predicting Immunotherapy Response in Lung Cancer

    • Computational Anatomy and Physiology

  • A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
  • A Spatial-Temporally Adaptive PINN Framework for 3D Bi-Ventricular Electrophysiological Simulations and Parameter Inference
  • Anatomy-Driven Pathology Detection on Chest X-rays
  • Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
  • Can point cloud networks learn statistical shape models of anatomies?
  • Conditional Physics-Informed Graph Neural Network For Fractional Flow Reserve Assessment
  • CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph
  • CT-guided, Unsupervised Super-resolution Reconstruction of Single 3D Magnetic Resonance Image
  • Flow-based Geometric Interpolation of Fiber Orientation Distribution Functions
  • Fully Bayesian VIB-DeepSSM
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Optimizing the 3D Plate Shape for Proximal Humerus Fractures
  • Personalized Patch-based Normality Assessment of Brain Atrophy in Alzheimer's Disease
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
  • Uncovering Heterogeneity in Alzheimer's Disease from Graphical Modeling of the Tau Spatiotemporal Topography
  • UOD: Universal One-shot Detection of Anatomical Landmarks
  • VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesis
  • Virtual Heart models help elucidate the role of border zone in sustained monomorphic Ventricular Tachycardia
  • Whole-Heart Reconstruction with Explicit Topology Integrated Learning

    • Computer Aided Diagnosis

  • A Model-Agnostic Framework for Universal Anomaly Detection of Multi-Organ and Multi-Modal Images
  • A Multi-Task Method for Immunofixation Electrophoresis Image Classification
  • A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images
  • A One-class Variational Autoencoder (OCVAE) cascade for classifying atypical bone marrow cell sub-types
  • A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging
  • A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  • A Style Transfer-based Augmentation Framework for Improving Segmentation and Classification Performance across Different Sources in Ultrasound Images
  • A Texture Neural Network to Predict the Abnormal Brachial Plexus from Routine Magnetic Resonance Imaging
  • Acute Ischemic Stroke Onset Time Classification with Dynamic Convolution and Perfusion Maps Fusion
  • Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
  • Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
  • AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • Anatomical Landmark Detection Using a Multiresolution Learning Approach with a Hybrid Transformer-CNN Model
  • Anatomy-Driven Pathology Detection on Chest X-rays
  • Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
  • Aneurysm Pose Estimation with Deep Learning
  • ASC: Appearance and Structure Consistency for Unsupervised Domain Adaptation in Fetal Brain MRI Segmentation
  • Automatic Bleeding Risk Rating System of Gastric Varices
  • Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • CARL: Cross-aligned Representation Learning for Multi-view Lung Cancer Histology Classification
  • Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • Combat Long-tails in Medical Classification with Relation-aware Consistency and Virtual Features Compensation
  • Combating Medical Label Noise via Robust Semi-supervised Contrastive Learning
  • Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
  • Contrastive Feature Decoupling for Weakly-supervised Disease Detection
  • Contrastive Masked Image-Text Modeling for Medical Visual Representation Learning
  • Convolving Directed Graph Edges via Hodge Laplacian for Brain Network Analysis
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • Coupling Bracket Segmentation and Tooth Surface Reconstruction on 3D Dental Models
  • COVID-19 Pneumonia Classification with Transformer from Incomplete Modalities
  • Cross-view Deformable Transformer for Non-displaced Hip Fracture Classification from Frontal-Lateral X-ray Pair
  • DCAug: Domain-aware & Content-consistent Cross-cycle Framework for Tumor Augmentation
  • DeDA: Deep Directed Accumulator
  • Deep Learning for Tumor-associated Stroma Identification in Prostate Histopathology Slides
  • DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data
  • Detecting domain shift in multiple instance learning for digital pathology using Fréchet Domain Distance
  • Detection of basal cell carcinoma in whole slide images
  • Detection-free Pipeline for Cervical Cancer Screening of Whole Slide Images
  • DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
  • DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
  • DiffULD: Diffusive Universal Lesion Detection
  • Diffusion-based Data Augmentation for Nuclei Image Segmentation
  • Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
  • DiMix: Disentangle-and-Mix based domain generalizable medical image segmentation
  • Discovering Brain Network Dysfunction in Alzheimer’s Disease Using Brain Hypergraph Neural Network
  • Distributionally Robust Image Classifiers for Stroke Diagnosis in Accelerated MRI
  • Diversity-preserving Chest Radiographs Generation from Reports in One Stage
  • Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
  • Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • ECL: Class-Enhancement Contrastive Learning for Long-tailed Skin Lesion Classification
  • EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Enhancing Breast Cancer Risk Prediction by Incorporating Prior Images
  • EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition
  • Evidence Reconciled Neural Network for Out-of-Distribution Detection in Medical Images
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • Explaining Massive-Training Artificial Neural Networks in Medical Image Analysis Task through Visualizing Functions within the Models
  • Eye-Guided Dual-Path Network for Multi-organ Segmentation of Abdomen
  • Fast Non-Markovian Diffusion Model for Weakly Supervised Anomaly Detection in Brain MR Images
  • FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification
  • FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
  • Fine-Tuning Network in Federated Learning for Personalized Skin Diagnosis
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation
  • From Mesh Completion to AI Designed Crown
  • Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images
  • Gradient and Feature Conformity-Steered Medical Image Classification with Noisy Labels
  • GSDG: Exploring A Global Semantic-guided Dual-stream Graph Model for Automated Volume Differential Diagnosis and Prognosis
  • HACL-Net: Hierarchical Attention and Contrastive Learning Network for MRI-Based Placenta Accreta Spectrum Diagnosis
  • HC-Net: Hybrid Classification Network for Automatic Periodontal Disease Diagnosis
  • Hierarchical Vision Transformers for Disease Progression Detection in Chest X-Ray Images
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • How Reliable are the Metrics Used for Assessing Reliability in Medical Imaging?
  • IIB-MIL: Integrated instance-level and bag-level multiple instances learning with label disambiguation for pathological image analysis
  • Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
  • Improving Outcome Prediction of Pulmonary Embolism by De-Biased Multi-Modality Model
  • Improving Pathology Localization: Multi-Series Joint Attention Takes the Lead
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Interpretable Deep Biomarker for Serial Monitoring of Carotid Atherosclerosis Based on Three-Dimensional Ultrasound Imaging
  • Interpretable Medical Image Classification using Prototype Learning and Privileged Information
  • Joint optimization of a β-VAE for ECG task-specific feature extraction
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-Training
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
  • Learning Robust Classifier for Imbalanced Medical Image Dataset with Noisy Labels by Minimizing Invariant Risk
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • Learning with Synthesized Data for Generalizable Lesion Detection in Real PET Images
  • Lesion-aware Contrastive Learning for Diabetic Retinopathy Diagnosis
  • Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network
  • LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
  • Localized Questions in Medical Visual Question Answering
  • M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
  • Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
  • MedIM: Boost Medical Image Representation via Radiology Report-guided Masking
  • Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
  • MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • Multimodal Deep Fusion in Hyperbolic Space for Mild Cognitive Impairment Study
  • Multi-modality contrastive learning for sarcopenia screening from hip X-rays and clinical information
  • Multiple Prompt Fusion for Zero-Shot Lesion Detection Using Vision-Language Models
  • Multi-Scale Prototypical Transformer for Whole Slide Image Classification
  • Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
  • Multi-View Vertebra Localization and Identification from CT Images
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • One-shot Federated Learning on Medical Data using Knowledge Distillation with Image Synthesis and Client Model Adaptation
  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue
  • Overall Survival Time Prediction of Glioblastoma on Preoperative MRI Using Lesion Network Mapping
  • Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists
  • PAS-Net: Rapid Prediction of Antibiotic Susceptibility from Fluorescence Images of Bacterial Cells Using Parallel Dual-branch Network
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • Patients and Slides are Equal: A Multi-level Multi-instance Learning Framework for Pathological Image Analysis
  • Performance Metrics for Probabilistic Ordinal Classifiers
  • Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  • Positive Definite Wasserstein Graph Kernel for Brain Disease Diagnosis
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Privacy-preserving Early Detection of Epileptic Seizures in Videos
  • Progressive Attention Guidance for Whole Slide Vulvovaginal Candidiasis Screening
  • Prompt-based Grouping Transformer for Nucleus Detection and Classification
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
  • Rad-ReStruct: A Novel VQA Benchmark and Method for Structured Radiology Reporting
  • Recruiting the best teacher modality: A customized knowledge distillation method for IF based nephropathy diagnosis
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models
  • Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
  • Revisiting Feature Propagation and Aggregation in Polyp Segmentation
  • Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?
  • Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  • Robust Exclusive Adaptive Sparse Feature Selection for Biomarker Discovery and Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus
  • S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
  • SCOL: Supervised Contrastive Ordinal Loss for Abdominal Aortic Calcification Scoring on Vertebral Fracture Assessment Scans
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks
  • Self- and Semi-Supervised Learning for Gastroscopic Lesion Detection
  • Self-feedback Transformer: A Multi-label Diagnostic Model for Real-world Pancreatic Neuroendocrine Neoplasms Data
  • Self-Supervised Domain Adaptive Segmentation of Breast Cancer via Test-Time Fine-Tuning
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-Supervised Polyp Re-Identification in Colonoscopy
  • SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
  • Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
  • Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
  • Spatiotemporal Hub Identification in Brain Network by Learning Dynamic Graph Embedding on Grassmannian Manifold
  • STAR-Echo: A Novel Biomarker for Prognosis of MACE in Chronic Kidney Disease Patients using Spatiotemporal Analysis and Transformer-Based Radiomics Models
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • TabAttention: Learning Attention Conditionally on Tabular Data
  • TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction
  • Text-Guided Cross-Position Attention for Segmentation: Case of Medical Image
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • The Role of Subgroup Separability in Group-Fair Medical Image Classification
  • Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
  • Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
  • Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Transformer-based end-to-end classification of variable-length volumetric data
  • Transformer-based tooth segmentation, identification and pulp calcification recognition in CBCT
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer
  • Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks
  • Uncertainty Inspired Autism Spectrum Disorder Screening
  • Uncovering Heterogeneity in Alzheimer's Disease from Graphical Modeling of the Tau Spatiotemporal Topography
  • Unsupervised classification of congenital inner ear malformations using DeepDiffusion for latent space representation
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • VF-HM: Vision Loss Estimation using Fundus Photograph for High Myopia
  • Vision Transformer based Multi-Class Lesion Detection in IVOCT
  • Visual Grounding of Whole Radiology Reports for 3D CT Images
  • Visual-Attribute Prompt Learning for Progressive Mild Cognitive Impairment Prediction
  • Wall thickness estimation from short axis ultrasound images via temporal compatible deformation learning
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification
  • What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior
  • Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis
  • YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection
  • You Don’t Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images
  • You’ve Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray

    • Image Reconstruction

  • 3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions
  • A Semantic-guided and Knowledge-based Generative Framework for Orthodontic Visual Outcome Preview
  • Accurate multi-contrast MRI super-resolution via a dual cross-attention transformer network
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • Alias-Free Co-Modulated Network for Cross-Modality Synthesis and Super-Resolution of MR Images
  • An Auto-Encoder to Reconstruct Structure with Cryo-EM Images via Theoretically Guaranteed Isometric Latent Space, and its Application for Automatically Computing the Conformational Pathway
  • An automated pipeline for quantitative T2* fetal body MRI and segmentation at low field
  • An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis
  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
  • BigFUSE: Global Context-Aware Image Fusion in Dual-View Light-Sheet Fluorescence Microscopy with Image Formation Prior
  • Building A Bridge: Close The Domain Gap in CT Metal Artifact Reduction
  • CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  • Computationally Efficient 3D MRI Reconstruction with Adaptive MLP
  • Content-Preserving Diffusion Model for Unsupervised AS-OCT image Despeckling
  • Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
  • CT Kernel Conversion Using Multi-Domain Image-to-Image Translation with Generator-Guided Contrastive Learning
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction
  • Differentiable Beamforming for Ultrasound Autofocusing
  • DiffuseIR: Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
  • DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis
  • Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
  • Dual Domain Motion Artifacts Correction for MR Imaging Under Guidance of K-space Uncertainty
  • DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
  • Estimation of 3T MR images from 1.5T images regularized with Physics based Constraint
  • Fast Reconstruction for Deep Learning PET Head Motion Correction
  • Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis
  • FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • Generating High-Resolution 3D CT with 12-bit Depth using a Diffusion Model with Adjacent Slice and Intensity Calibration Network
  • Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model
  • Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling
  • High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights
  • Improved flexibility and interpretability of large vessel stroke prognostication using image synthesis and multi-task learning
  • Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
  • Infusing physically inspired known operators in deep models of ultrasound elastography
  • Intraoperative CT augmentation for needle-based liver interventions
  • InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model
  • JCCS-PFGM: A Novel Circle-Supervision based Poisson Flow Generative Model for Multiphase CECT Progressive Low-Dose Reconstruction with Joint Condition
  • Joint optimization of a β-VAE for ECG task-specific feature extraction
  • Learned Alternating Minimization Algorithm for Dual-Domain Sparse-View CT Reconstruction
  • Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction
  • LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
  • LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
  • Low-dose CT image super-resolution network with dual-guidance feature distillation and dual-path content communication
  • LUCYD: A Feature-Driven Richardson-Lucy Deconvolution Network
  • MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images
  • MoCoSR: Respiratory Motion Correction and Super-Resolution for 3D Abdominal MRI
  • Motion Compensated Unsupervised Deep Learning for 5D MRI
  • MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • MulHiST: Multiple Histological Staining for Thick Biological Samples via Unsupervised Image-to-Image Translation
  • Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
  • Multi-perspective Adaptive Iteration Network for Metal Artifact Reduction
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
  • NISF: Neural Implicit Segmentation Functions
  • Noise Conditioned Weight Modulation for Robust and Generalizable Low Dose CT Denoising
  • Noise2Aliasing: Unsupervised Deep Learning for View Aliasing and Noise Reduction in 4DCBCT
  • PET Image Denoising with Score-Based Diffusion Probabilistic Models
  • PET-diffusion: Unsupervised PET Enhancement based on the Latent Diffusion Model
  • Physics-Informed Neural Networks for Tissue Elasticity Reconstruction in Magnetic Resonance Elastography
  • Polar Eyeball Shape Net for 3D Posterior Ocular Shape Representation
  • Predicting Diverse Functional Connectivity from Structural Connectivity Based on Multi-Contexts Discriminator GAN
  • Reflectance Mode Fluorescence Optical Tomography with Consumer-Grade Cameras
  • RESToring Clarity: Unpaired Retina Image Enhancement using Scattering Transform
  • Revealing Anatomical Structures in PET to Generate CT for Attenuation Correction
  • Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • Self-Supervised MRI Reconstruction with Unrolled Diffusion Models
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
  • Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction
  • Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
  • Solving Low-Dose CT Reconstruction via GAN with Local Coherence
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Topology-Preserving Computed Tomography Super-resolution Based on Dual-stream Diffusion Model
  • Trackerless Volume Reconstruction from Intraoperative Ultrasound Images
  • Transformer-based Dual-domain Network for Few-view Dedicated Cardiac SPECT Image Reconstructions
  • TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
  • Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior

    • Image Registration

  • A denoised Mean Teacher for domain adaptive point cloud registration
  • A Patient-Specific Self-supervised Model for Automatic X-ray/CT Registration
  • An Unsupervised Multispectral Image Registration Network for Skin Diseases
  • AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
  • Co-Learning Semantic-aware Unsupervised Segmentation for Pathological Image Registration
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • Fast Reconstruction for Deep Learning PET Head Motion Correction
  • FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery
  • FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images
  • GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
  • H2GM: A Hierarchical Hypergraph Matching Framework for Brain Landmark Alignment
  • Implicit neural representations for joint decomposition and registration of gene expression images in the marmoset brain
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Inverse Consistency by Construction for Multistep Deep Registration
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration
  • Nonuniformly Spaced Control Points based on Variational Cardiac Image Registration
  • Optimizing the 3D Plate Shape for Proximal Humerus Fractures
  • PCMC-T1: Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Personalized Patch-based Normality Assessment of Brain Atrophy in Alzheimer's Disease
  • PIViT: Large Deformation Image Registration with Pyramid-Iterative Vision Transformer
  • Progressively Coupling Network for Brain MRI Registration in Few-shot Situation
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
  • SPR-Net: Structural Points based Registration for Coronary Arteries across Systolic and Diastolic Phases
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • Unsupervised 3D registration through optimization-guided cyclical self-training
  • Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior
  • X-Ray to CT Rigid Registration Using Scene Coordinate Regression

    • Image Segmentation

  • 3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images
  • 3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks
  • 3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers
  • 3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions
  • A General Stitching Solution for Whole-Brain 3D Nuclei Instance Segmentation from Microscopy Images
  • A Multi-Task Network for Anatomy Identification in Endoscopic Pituitary Surgery
  • A Semantic-guided and Knowledge-based Generative Framework for Orthodontic Visual Outcome Preview
  • A Sheaf Theoretic Perspective for Robust Prostate Segmentation
  • A Style Transfer-based Augmentation Framework for Improving Segmentation and Classification Performance across Different Sources in Ultrasound Images
  • A2FSeg: Adaptive Multi-Modal Fusion Network for Medical Image Segmentation
  • ACC-UNet: A Completely Convolutional UNet model for the 2020s
  • ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast
  • Adult-like Phase and Multi-scale Assistance for Isointense Infant Brain Tissue Segmentation
  • AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor
  • Anatomical-aware Point-Voxel Network for Couinaud Segmentation in Liver CT
  • AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
  • Annotator Consensus Prediction for Medical Image Segmentation with Diffusion Models
  • Anti-Adversarial Consistency Regularization for Data Augmentation: Applications to Robust Medical Image Segmentation
  • Ariadne's Thread: Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images
  • ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models
  • Assignment Theory-Augmented Neural Network for Dental Arch Labeling
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • Automatic Retrieval of Corresponding US Views in Longitudinal Examinations
  • Automatic Segmentation of Internal Tooth Structure from CBCT Images using Hierarchical Deep Learning
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Black-box Domain Adaptative Cell Segmentation via Multi-source Distillation
  • Boundary Difference Over Union Loss For Medical Image Segmentation
  • Boundary-weighted logit consistency improves calibration of segmentation networks
  • Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
  • CAS-Net: Cross-view Aligned Segmentation by Graph Representation of Knees
  • Category-level Regularized Unlabeled-to-labeled Learning for Semi-supervised Prostate Segmentation with Multi-site Unlabeled Data
  • Certification of Deep Learning Models for Medical Image Segmentation
  • CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention
  • Class-Aware Feature Alignment for Domain Adaptative Mitochondria Segmentation
  • Collaborative modality generation and tissue segmentation for early-developing macaque brain MR images
  • COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
  • Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
  • Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction
  • Consistency-guided Meta-Learning for Bootstrapping Semi-Supervised Medical Image Segmentation
  • Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
  • ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
  • CorSegRec: A Topology-Preserving Scheme for Extracting Fully-Connected Coronary Arteries from CT Angiography
  • Coupling Bracket Segmentation and Tooth Surface Reconstruction on 3D Dental Models
  • Cross-adversarial local distribution regularization for semi-supervised medical image segmentation
  • DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation
  • DAST: Differentiable Architecture Search with Transformer for 3D Medical Image Segmentation
  • DBTrans: A Dual-Branch Vision Transformer for Multi-modal Brain Tumor Segmentation
  • DCAug: Domain-aware & Content-consistent Cross-cycle Framework for Tumor Augmentation
  • Decoupled Consistency for Semi-supervised Medical Image Segmentation
  • Deep probability contour framework for tumour segmentation and dose painting in PET images
  • Developing Large Pre-trained Model for Breast Tumor Segmentation from Ultrasound Images
  • Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation
  • DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation
  • Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels
  • DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets
  • DiffULD: Diffusive Universal Lesion Detection
  • Diffusion Kinetic Model for Breast Cancer Segmentation in Incomplete DCE-MRI
  • Diffusion Transformer U-Net for Medical Image Segmentation
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training
  • Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI
  • DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
  • Dose Guidance for Radiotherapy-oriented Deep Learning Segmentation
  • EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
  • EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
  • Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI
  • EdgeMixup: Embarrassingly Simple Data Alteration to Improve Lyme Disease Lesion Segmentation and Diagnosis Fairness
  • Efficient Subclass Segmentation in Medical Images
  • EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation
  • Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
  • Enabling Geometry Aware Learning Through Differentiable Epipolar View Translation
  • EoFormer: Edge-oriented Transformer for Brain Tumor Segmentation
  • Evolutionary normalization optimization boosts semantic segmentation network performance
  • Explaining Massive-Training Artificial Neural Networks in Medical Image Analysis Task through Visualizing Functions within the Models
  • Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
  • FedContrast-GPA: Heterogeneous Federated Optimization via Local Contrastive Learning and Global Process-aware Aggregation
  • FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification
  • FedGrav: An Adaptive Federated Aggregation Algorithm for Multi-institutional Medical Image Segmentation
  • Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
  • Fine-grained Hand Bone Segmentation via Adaptive Multi-dimensional Convolutional Network and Anatomy-constraint Loss
  • FocalUNETR: A Focal Transformer for Boundary-aware Prostate Segmentation using CT Images
  • Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
  • Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation
  • From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation
  • Geometry-invariant abnormality detection
  • GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation
  • Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
  • HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
  • H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation
  • HENet: Hierarchical Enhancement Network for Pulmonary Vessel Segmentation in Non-contrast CT Images
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Ischemic stroke segmentation from a cross-domain representation in multimodal diffusion studies
  • Joint Dense-Point Representation for Contour-Aware Graph Segmentation
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • Label-Free Nuclei Segmentation Using Intra-Image Self Similarity
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection
  • Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
  • Learnable Query Initialization for Surgical Instrument Instance Segmentation
  • Learning Ontology-based Hierarchical Structural Relationship for Whole Brain Segmentation
  • Learning Reliability of Multi-Modality Medical Images for Tumor Segmentation via Evidence-Identified Denoising Diffusion Probabilistic Models
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network
  • Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
  • LOTUS: Learning to Optimize Task-based US representations
  • M3D-NCA: Robust 3D Segmentation with Built-in Quality Control
  • Masked Frequency Consistency for Domain-Adaptive Semantic Segmentation of Laparoscopic Images
  • Maximum Entropy on Erroneous Predictions: Improving model calibration for medical image segmentation
  • MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
  • MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation
  • Medical Boundary Diffusion Model for Skin Lesion Segmentation
  • MedIM: Boost Medical Image Representation via Radiology Report-guided Masking
  • MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
  • Memory Replay for Continual Medical Image Segmentation through Atypical Sample Selection
  • M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision
  • Minimal-supervised Medical Image Segmentation via Vector Quantization Memory
  • MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization
  • Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic Grouping
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Multi-Target Domain Adaptation with Prompt Learning for Medical Image Segmentation
  • NISF: Neural Implicit Segmentation Functions
  • One-Shot Traumatic Brain Segmentation with Adversarial Training and Uncertainty Rectification
  • Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning
  • Partially Supervised Multi-Organ Segmentation via Affinity-aware Consistency Learning and Cross Site Feature Alignment
  • Pelvic Fracture Segmentation Using a Multi-scale Distance-weighted Neural Network
  • Pick and Trace: Instance Segmentation for Filamentous Objects with a Recurrent Neural Network
  • Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation
  • PLD-AL: Pseudo-Label Divergence-Based Active Learning in Carotid Intima-Media Segmentation for Ultrasound Images
  • Pre-operative Survival Prediction of Diffuse Glioma Patients with Joint Tumor Subtyping
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • Progressively Coupling Network for Brain MRI Registration in Few-shot Situation
  • Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • RBGNet: Reliable Boundary-Guided Segmentation of Choroidal Neovascularization
  • RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Revisiting Feature Propagation and Aggregation in Polyp Segmentation
  • Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  • Robust Segmentation via Topology Violation Detection and Feature Synthesis
  • Robust T-Loss for Medical Image Segmentation
  • S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
  • Scaling Up 3D Kernels with Bayesian Frequency Re-Parameterization for Medical Image Segmentation
  • Second-course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information
  • Segment Membranes and Nuclei from Histopathological Images via Nuclei Point-level Supervision
  • Segmentation Distortion: Quantifying Segmentation Uncertainty under Domain Shift via the Effects of Anomalous Activations
  • Segmentation of Kidney Tumors on Non-Contrast CT Images using Protuberance Detection Network
  • SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks
  • Self-adaptive Adversarial Training for Robust Medical Segmentation
  • Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  • Self-Supervised Domain Adaptive Segmentation of Breast Cancer via Test-Time Fine-Tuning
  • Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
  • Semantic difference guidance for the uncertain boundary segmentation of CT left atrial appendage
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts
  • Semi-supervised Class Imbalanced Deep Learning for Cardiac MRI Segmentation
  • Semi-supervised Domain Adaptive Medical Image Segmentation through Consistency Regularized Disentangled Contrastive Learning
  • Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
  • SFusion: Self-attention based N-to-One Multimodal Fusion Block
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI
  • SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
  • Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • Structure-decoupled Adaptive Part Alignment Network for Domain Adaptive Mitochondria Segmentation
  • Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • SwinUNETR-V2: Stronger Swin Transformers with Stagewise Convolutions for 3D Medical Image Segmentation
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets
  • Text-Guided Cross-Position Attention for Segmentation: Case of Medical Image
  • Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing
  • Towards Expert-Amateur Collaboration: Prototypical Label Isolation Learning for Left Atrium Segmentation with Mixed-Quality Labels
  • Towards frugal unsupervised detection of subtle abnormalities in medical imaging
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Transformer-based Annotation Bias-aware Medical Image Segmentation
  • TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation
  • Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation
  • Trust your neighbours: Penalty-based constraints for model calibration
  • TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer
  • Uncertainty and Shape-Aware Continual Test-Time Adaptation for Cross-Domain Segmentation of Medical Images
  • Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
  • UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
  • Unpaired Cross-modal Interaction Learning for COVID-19 Segmentation on Limited CT images
  • Unsupervised Discovery of 3D Hierarchical Structure with Generative Diffusion Features
  • UPCoL: Uncertainty-informed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
  • Vertex Correspondence in Cortical Surface Reconstruction
  • vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
  • Wall thickness estimation from short axis ultrasound images via temporal compatible deformation learning
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning
  • Weakly Supervised Medical Image Segmentation via Superpixel-guided Scribble Walking and Class-wise Contrastive Regularization
  • WeakPolyp: You Only Look Bounding Box for Polyp Segmentation

    • Image-Guided Interventions and Surgery

  • A Novel Video-CTU Registration Method with Structural Point Similarity for FURS Navigation
  • A Patient-Specific Self-supervised Model for Automatic X-ray/CT Registration
  • A Transfer Learning Approach to Localise a Deep Brain Stimulation Target
  • A Unified Deep-Learning-Based Framework for Cochlear Implant Electrode Array Localization
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • ConTrack: Contextual Transformer for Device Tracking in X-ray
  • Deep Homography Prediction for Endoscopic Camera Motion Imitation Learning
  • Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing
  • Detecting the Sensing Area of A Laparoscopic Probe in Minimally Invasive Cancer Surgery
  • Dose Guidance for Radiotherapy-oriented Deep Learning Segmentation
  • Efficient Spatiotemporal Learning of Microscopic Video for Augmented Reality-Guided Phacoemulsification Cataract Surgery
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery
  • From Tissue to Sound: Model-based Sonification of Medical Imaging
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Imitation Learning from Expert Video Data for Dissection Trajectory Prediction in Endoscopic Surgical Procedure
  • Intelligent Virtual B-scan Mirror (IVBM)
  • Intraoperative CT augmentation for needle-based liver interventions
  • Learning Expected Appearances for Intraoperative Registration during Neurosurgery
  • Multi-task Joint Prediction of Infant Cortical Morphological and Cognitive Development
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue
  • Optical Ultrasound Imaging for Endovascular Repair of Abdominal Aortic Aneurysms: A Pilot Study
  • Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Pelvic Fracture Segmentation Using a Multi-scale Distance-weighted Neural Network
  • Point Cloud Diffusion Models for Automatic Implant Generation
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Realistic endoscopic illumination modeling for NeRF-based data generation
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Reflectance Mode Fluorescence Optical Tomography with Consumer-Grade Cameras
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts
  • Semantic Virtual Shadows (SVS) for Improved Perception in 4D OCT Guided Surgery
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
  • Shape-based pose estimation for automatic standard views of the knee
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • TCL: Triplet Consistent Learning for Odometry Estimation of Monocular Endoscope
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • Ultrasonic tracking of a rapid-exchange microcatheter with simultaneous pressure sensing for cardiovascular interventions
  • Uncertainty Inspired Autism Spectrum Disorder Screening
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior

    • Integration of Imaging with Non-Imaging Biomarkers

  • A Multimodal Disease Progression Model for Genetic Associations with Disease Dynamics
  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
  • Multimodal brain age estimation using interpretable adaptive population-graph learning
  • Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • Treatment Outcome Prediction for Intracerebral Hemorrhage via Generative Prognostic Model with Imaging and Tabular Data

    • Interventional Imaging Systems

  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • Cascade Transformer Encoded Boundary-Aware Multibranch Fusion Networks for Real-Time and Accurate Colonoscopic Lesion Segmentation
  • ConTrack: Contextual Transformer for Device Tracking in X-ray
  • Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing
  • Detecting the Sensing Area of A Laparoscopic Probe in Minimally Invasive Cancer Surgery
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Intraoperative CT augmentation for needle-based liver interventions
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue
  • Optical Ultrasound Imaging for Endovascular Repair of Abdominal Aortic Aneurysms: A Pilot Study
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts

    • Interventional Simulation Systems

  • A Spatial-Temporally Adaptive PINN Framework for 3D Bi-Ventricular Electrophysiological Simulations and Parameter Inference
  • Spatiotemporal Incremental Mechanics Modeling of Facial Tissue Change
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations

    • Machine Learning - Active Learning

  • A Small-Sample Method with EEG Signals Based on Abductive Learning for Motor Imagery Decoding
  • Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation
  • Anti-Adversarial Consistency Regularization for Data Augmentation: Applications to Robust Medical Image Segmentation
  • atTRACTive: Semi-automatic white matter tract segmentation using active learning
  • COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
  • EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
  • OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image Classification
  • PLD-AL: Pseudo-Label Divergence-Based Active Learning in Carotid Intima-Media Segmentation for Ultrasound Images
  • SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning

    • Machine Learning - Attention models

  • 3D Dental Mesh Segmentation Using Semantics-Based Feature Learning with Graph-Transformer
  • A Motion Transformer for Single Particle Tracking in Fluorescence Microscopy Images
  • A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  • A2FSeg: Adaptive Multi-Modal Fusion Network for Medical Image Segmentation
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography
  • Anatomical Landmark Detection Using a Multiresolution Learning Approach with a Hybrid Transformer-CNN Model
  • ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
  • Centroid-aware feature recalibration for cancer grading in pathology images
  • CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  • Community-Aware Transformer for Autism Prediction in fMRI Connectome
  • Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction
  • ConTrack: Contextual Transformer for Device Tracking in X-ray
  • ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  • COVID-19 Pneumonia Classification with Transformer from Incomplete Modalities
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • DCAug: Domain-aware & Content-consistent Cross-cycle Framework for Tumor Augmentation
  • Debiasing Medical Visual Question Answering via Counterfactual Training
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data
  • Detecting domain shift in multiple instance learning for digital pathology using Fréchet Domain Distance
  • Diffusion Transformer U-Net for Medical Image Segmentation
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation
  • Federated Condition Generalization on Low-dose CT Reconstruction via Cross-domain Learning
  • FE-STGNN: Spatio-Temporal Graph Neural Network with Functional and Effective Connectivity Fusion for MCI Diagnosis
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • From Mesh Completion to AI Designed Crown
  • Gadolinium-Free Cardiac MRI Myocardial Scar Detection by 4D Convolution Factorization
  • Geometry-invariant abnormality detection
  • Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling
  • HACL-Net: Hierarchical Attention and Contrastive Learning Network for MRI-Based Placenta Accreta Spectrum Diagnosis
  • HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
  • Hierarchical Vision Transformers for Disease Progression Detection in Chest X-Ray Images
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Improving Pathology Localization: Multi-Series Joint Attention Takes the Lead
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Intra-operative Forecasting of Standing Spine Shape with Articulated Neural Kernel Fields
  • Ischemic stroke segmentation from a cross-domain representation in multimodal diffusion studies
  • Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection
  • Learnable Subdivision Graph Neural Network for Functional Brain Network Analysis and Interpretable Cognitive Disorder Diagnosis
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Localized Questions in Medical Visual Question Answering
  • Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
  • Low-dose CT image super-resolution network with dual-guidance feature distillation and dual-path content communication
  • M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
  • MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
  • MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
  • ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • Path-based Heterogeneous Brain Transformer Network for Resting-State Functional Connectivity Analysis
  • Pelvic Fracture Segmentation Using a Multi-scale Distance-weighted Neural Network
  • PIViT: Large Deformation Image Registration with Pyramid-Iterative Vision Transformer
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Prediction of Cognitive Scores by Joint Use of Movie-watching fMRI Connectivity and Eye Tracking via Attention-CensNet
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Reconstructing the Hemodynamic Response Function via a Bimodal Transformer
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • Retinal Thickness Prediction from Multi-modal Fundus Photography
  • Second-course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information
  • SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks
  • Self-Supervised MRI Reconstruction with Unrolled Diffusion Models
  • Self-Supervised Polyp Re-Identification in Colonoscopy
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Text-Guided Cross-Position Attention for Segmentation: Case of Medical Image
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • Vision Transformer based Multi-Class Lesion Detection in IVOCT
  • Visual Grounding of Whole Radiology Reports for 3D CT Images
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning

    • Machine Learning - Continual Learning

  • Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
  • Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
  • Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
  • Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI
  • L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
  • Memory Replay for Continual Medical Image Segmentation through Atypical Sample Selection
  • Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery

    • Machine Learning - Data Efficient Learning

  • 3D Dental Mesh Segmentation Using Semantics-Based Feature Learning with Graph-Transformer
  • A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants
  • ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast
  • Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation
  • Aneurysm Pose Estimation with Deep Learning
  • Anti-Adversarial Consistency Regularization for Data Augmentation: Applications to Robust Medical Image Segmentation
  • Boundary-weighted logit consistency improves calibration of segmentation networks
  • Category-level Regularized Unlabeled-to-labeled Learning for Semi-supervised Prostate Segmentation with Multi-site Unlabeled Data
  • Class Specific Feature Disentanglement And Text Embeddings For Multi-Label Generalized Zero Shot CXR Classification
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
  • Combat Long-tails in Medical Classification with Relation-aware Consistency and Virtual Features Compensation
  • Contrastive Masked Image-Text Modeling for Medical Visual Representation Learning
  • Cross-adversarial local distribution regularization for semi-supervised medical image segmentation
  • CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training
  • DeDA: Deep Directed Accumulator
  • Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning
  • Diffusion-based Data Augmentation for Nuclei Image Segmentation
  • Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
  • Efficient Subclass Segmentation in Medical Images
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs
  • FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification
  • Few Shot Medical Image Segmentation with Cross Attention Transformer
  • Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance
  • Gradient and Feature Conformity-Steered Medical Image Classification with Noisy Labels
  • Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization
  • M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision
  • Mixing Temporal Graphs with MLP for Longitudinal Brain Connectome Analysis
  • MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Multimodal Deep Fusion in Hyperbolic Space for Mild Cognitive Impairment Study
  • Multi-Modal Semi-supervised Evidential Recycle Framework for Alzheimer's Disease Classification
  • Multiple Prompt Fusion for Zero-Shot Lesion Detection Using Vision-Language Models
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning
  • Partially Supervised Multi-Organ Segmentation via Affinity-aware Consistency Learning and Cross Site Feature Alignment
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
  • Second-course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation
  • Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
  • Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
  • SFusion: Self-attention based N-to-One Multimodal Fusion Block
  • SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Synthetic Augmentation with Large-scale Unconditional Pre-training
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • Thinking Like Sonographers: A Deep CNN Model for Diagnosing Gout from Musculoskeletal Ultrasound
  • Towards Expert-Amateur Collaboration: Prototypical Label Isolation Learning for Left Atrium Segmentation with Mixed-Quality Labels
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Transferability-Guided Multi-Source Model Adaptation for Medical Image Segmentation
  • UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation
  • Unsupervised classification of congenital inner ear malformations using DeepDiffusion for latent space representation
  • Unsupervised Domain Adaptation for Anatomical Landmark Detection
  • Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos
  • UOD: Universal One-shot Detection of Anatomical Landmarks
  • vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
  • Weakly Supervised Medical Image Segmentation via Superpixel-guided Scribble Walking and Class-wise Contrastive Regularization
  • YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection
  • Zero-shot Nuclei Detection via Visual-Language Pre-trained Models

    • Machine Learning - Interpretability / Explainability

  • A flexible framework for simulating and evaluating biases in deep learning-based medical image analysis
  • A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging
  • An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • Anatomy-Driven Pathology Detection on Chest X-rays
  • ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • B-Cos Aligned Transformers Learn Human-Interpretable Features
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • BrainUSL: Unsupervised Graph Structure Learning for Functional Brain Network Analysis
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Category-independent Visual Explanation for Medical Deep Network Understanding
  • CheXstray: A Real-Time Multi-Modal Monitoring Workflow for Medical Imaging AI
  • Community-Aware Transformer for Autism Prediction in fMRI Connectome
  • Debiasing Medical Visual Question Answering via Counterfactual Training
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • Deep probability contour framework for tumour segmentation and dose painting in PET images
  • DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics
  • Deployment of Image Analysis Algorithms under Prevalence Shifts
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • Distilling BlackBox to Interpretable models for Efficient Transfer Learning
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • Enhance Early Diagnosis Accuracy of Alzheimer's Disease by Elucidating Interactions between Amyloid Cascade and Tau Propagation
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • Explaining Massive-Training Artificial Neural Networks in Medical Image Analysis Task through Visualizing Functions within the Models
  • Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
  • GSDG: Exploring A Global Semantic-guided Dual-stream Graph Model for Automated Volume Differential Diagnosis and Prognosis
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Interpretable Deep Biomarker for Serial Monitoring of Carotid Atherosclerosis Based on Three-Dimensional Ultrasound Imaging
  • Interpretable Medical Image Classification using Prototype Learning and Privileged Information
  • Joint optimization of a β-VAE for ECG task-specific feature extraction
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Learnable Subdivision Graph Neural Network for Functional Brain Network Analysis and Interpretable Cognitive Disorder Diagnosis
  • Learned Alternating Minimization Algorithm for Dual-Domain Sparse-View CT Reconstruction
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Localized Questions in Medical Visual Question Answering
  • Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
  • LSOR: Longitudinally-Consistent Self-Organized Representation Learning
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • Modularity-Constrained Dynamic Representation Learning for Interpretable Brain Disorder Analysis with Functional MRI
  • Multi-Head Multi-Loss Model Calibration
  • Multimodal brain age estimation using interpretable adaptive population-graph learning
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • Performance Metrics for Probabilistic Ordinal Classifiers
  • Physics-Informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models
  • Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?
  • Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
  • Spatiotemporal Hub Identification in Brain Network by Learning Dynamic Graph Embedding on Grassmannian Manifold
  • Spatiotemporal Incremental Mechanics Modeling of Facial Tissue Change
  • STAR-Echo: A Novel Biomarker for Prognosis of MACE in Chronic Kidney Disease Patients using Spatiotemporal Analysis and Transformer-Based Radiomics Models
  • Style-based Manifold for Weakly-supervised Disease Characteristic Discovery
  • TauFlowNet: Uncovering Propagation Mechanism of Tau Aggregates by Neural Transport Equation
  • Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets
  • The Role of Subgroup Separability in Group-Fair Medical Image Classification
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection
  • Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis

    • Machine Learning - Meta-learning

  • Development and Fast Transferring of General Connectivity-based Diagnosis Model to New Brain Disorders with Adaptive Graph Meta-learner
  • GRACE: A Generalized and Personalized Federated Learning Method for Medical Imaging
  • Identification of Disease-sensitive Brain Imaging Phenotypes and Genetic Factors using GWAS Summary Statistics
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • VISA-FSS: A Volume-Informed Self Supervised Approach for Few-Shot 3D Segmentation

    • Machine Learning - Model Generalizability / Federated Learning

  • A flexible framework for simulating and evaluating biases in deep learning-based medical image analysis
  • A Sheaf Theoretic Perspective for Robust Prostate Segmentation
  • Black-box Domain Adaptative Cell Segmentation via Multi-source Distillation
  • Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
  • CheXstray: A Real-Time Multi-Modal Monitoring Workflow for Medical Imaging AI
  • Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging
  • Co-assistant Networks for Label Correction
  • Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
  • Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Models
  • Deployment of Image Analysis Algorithms under Prevalence Shifts
  • Detecting domain shift in multiple instance learning for digital pathology using Fréchet Domain Distance
  • Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation
  • DiMix: Disentangle-and-Mix based domain generalizable medical image segmentation
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
  • EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition
  • FedContrast-GPA: Heterogeneous Federated Optimization via Local Contrastive Learning and Global Process-aware Aggregation
  • Federated Condition Generalization on Low-dose CT Reconstruction via Cross-domain Learning
  • Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
  • FedGrav: An Adaptive Federated Aggregation Algorithm for Multi-institutional Medical Image Segmentation
  • FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
  • FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
  • FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling
  • Fine-Tuning Network in Federated Learning for Personalized Skin Diagnosis
  • Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
  • Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation
  • Geometry-invariant abnormality detection
  • GRACE: A Generalized and Personalized Federated Learning Method for Medical Imaging
  • Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Learned Alternating Minimization Algorithm for Dual-Domain Sparse-View CT Reconstruction
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
  • MoCoSR: Respiratory Motion Correction and Super-Resolution for 3D Abdominal MRI
  • Noise Conditioned Weight Modulation for Robust and Generalizable Low Dose CT Denoising
  • One-shot Federated Learning on Medical Data using Knowledge Distillation with Image Synthesis and Client Model Adaptation
  • Physics-based Decoding Improves Magnetic Resonance Fingerprinting
  • Pre-trained Diffusion Models for Plug-and-Play Medical Image Enhancement
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
  • Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data
  • S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
  • SATTA: Semantic-Aware Test-Time Adaptation for Cross-Domain Medical Image Segmentation
  • Scale Federated Learning for Label Set Mismatch in Medical Image Classification
  • Self-adaptive Adversarial Training for Robust Medical Segmentation
  • SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • The Role of Subgroup Separability in Group-Fair Medical Image Classification
  • Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
  • Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation

    • Machine Learning - Other

  • 3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions
  • A flexible framework for simulating and evaluating biases in deep learning-based medical image analysis
  • A Model-Agnostic Framework for Universal Anomaly Detection of Multi-Organ and Multi-Modal Images
  • A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications
  • A Spatial-Temporally Adaptive PINN Framework for 3D Bi-Ventricular Electrophysiological Simulations and Parameter Inference
  • A Texture Neural Network to Predict the Abnormal Brachial Plexus from Routine Magnetic Resonance Imaging
  • A Unified Deep-Learning-Based Framework for Cochlear Implant Electrode Array Localization
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • AirwayFormer: Structure-Aware Boundary-Adaptive Transformers for Airway Anatomical Labeling
  • Alias-Free Co-Modulated Network for Cross-Modality Synthesis and Super-Resolution of MR Images
  • Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
  • Ariadne's Thread: Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images
  • ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models
  • ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
  • Assignment Theory-Augmented Neural Network for Dental Arch Labeling
  • AUA-dE: An adaptive uncertainty guided attention for diffusion MRI models estimation
  • Automatic Retrieval of Corresponding US Views in Longitudinal Examinations
  • Automatic Segmentation of Internal Tooth Structure from CBCT Images using Hierarchical Deep Learning
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • CARL: Cross-aligned Representation Learning for Multi-view Lung Cancer Histology Classification
  • CenterlinePointNet++: A new point cloud based architecture for coronary artery pressure drop and vFFR estimation
  • Centroid-aware feature recalibration for cancer grading in pathology images
  • CheXstray: A Real-Time Multi-Modal Monitoring Workflow for Medical Imaging AI
  • Class Specific Feature Disentanglement And Text Embeddings For Multi-Label Generalized Zero Shot CXR Classification
  • CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  • COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
  • Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
  • Convolving Directed Graph Edges via Hodge Laplacian for Brain Network Analysis
  • CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph
  • Coupling Bracket Segmentation and Tooth Surface Reconstruction on 3D Dental Models
  • Cross-modulated Few-shot Image Generation for Colorectal Tissue Classification
  • CT-guided, Unsupervised Super-resolution Reconstruction of Single 3D Magnetic Resonance Image
  • CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Models
  • Debiasing Medical Visual Question Answering via Counterfactual Training
  • Deep Learning-Based Air Trapping Quantification using Paired Inspiratory-Expiratory Ultra-Low Dose CT
  • Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy
  • DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics
  • Detection of basal cell carcinoma in whole slide images
  • Developing Large Pre-trained Model for Breast Tumor Segmentation from Ultrasound Images
  • DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets
  • Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • Diversity-preserving Chest Radiographs Generation from Reports in One Stage
  • Dynamic Functional Connectome Harmonics
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • ECL: Class-Enhancement Contrastive Learning for Long-tailed Skin Lesion Classification
  • Enabling Geometry Aware Learning Through Differentiable Epipolar View Translation
  • Enhance Early Diagnosis Accuracy of Alzheimer's Disease by Elucidating Interactions between Amyloid Cascade and Tau Propagation
  • Evolutionary normalization optimization boosts semantic segmentation network performance
  • FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification
  • FE-STGNN: Spatio-Temporal Graph Neural Network with Functional and Effective Connectivity Fusion for MCI Diagnosis
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
  • From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation
  • FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images
  • Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model
  • Geometry-adaptive Network for Robust Detection of Placenta Accreta Spectrum Disorders
  • H2GM: A Hierarchical Hypergraph Matching Framework for Brain Landmark Alignment
  • Hierarchical Vision Transformers for Disease Progression Detection in Chest X-Ray Images
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
  • Intra-operative Forecasting of Standing Spine Shape with Articulated Neural Kernel Fields
  • Joint Dense-Point Representation for Contour-Aware Graph Segmentation
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
  • Learning normal asymmetry representations for homologous brain structures
  • Learning Ontology-based Hierarchical Structural Relationship for Whole Brain Segmentation
  • LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
  • Localized Questions in Medical Visual Question Answering
  • LUCYD: A Feature-Driven Richardson-Lucy Deconvolution Network
  • M3D-NCA: Robust 3D Segmentation with Built-in Quality Control
  • Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
  • Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis
  • Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
  • MPBD-LSTM: A Predictive Model For Colorectal Liver Metastases Using Time Series Multi-phase Contrast-Enhanced CT Scans
  • Multimodal brain age estimation using interpretable adaptive population-graph learning
  • Multiple Prompt Fusion for Zero-Shot Lesion Detection Using Vision-Language Models
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
  • NISF: Neural Implicit Segmentation Functions
  • Noise2Aliasing: Unsupervised Deep Learning for View Aliasing and Noise Reduction in 4DCBCT
  • Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
  • Path-based Heterogeneous Brain Transformer Network for Resting-State Functional Connectivity Analysis
  • Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
  • Physics-Informed Neural Networks for Tissue Elasticity Reconstruction in Magnetic Resonance Elastography
  • Point Cloud Diffusion Models for Automatic Implant Generation
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Prior-driven Dynamic Brain Networks for Multi-Modal Emotion Recognition
  • Privacy-preserving Early Detection of Epileptic Seizures in Videos
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
  • Realistic endoscopic illumination modeling for NeRF-based data generation
  • Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
  • Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • Robust Exclusive Adaptive Sparse Feature Selection for Biomarker Discovery and Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus
  • Robust Hough and Spatial-To-Angular Transform Based Rotation Estimation for Orthopedic X-Ray Images
  • Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
  • Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
  • Scaling Up 3D Kernels with Bayesian Frequency Re-Parameterization for Medical Image Segmentation
  • Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
  • Self-Supervised MRI Reconstruction with Unrolled Diffusion Models
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
  • Simulation of Arbitrary Level Contrast Dose in MRI Using an Iterative Global Transformer Model
  • Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction
  • SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
  • Solving Low-Dose CT Reconstruction via GAN with Local Coherence
  • Spatiotemporal Hub Identification in Brain Network by Learning Dynamic Graph Embedding on Grassmannian Manifold
  • Spatiotemporal Incremental Mechanics Modeling of Facial Tissue Change
  • Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
  • SurfFlow: A Flow-Based Approach for Rapid and Accurate Cortical Surface Reconstruction from Infant Brain MRI
  • Synthesis of Contrast-Enhanced Breast MRI Using T1- and Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanism
  • Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models
  • TauFlowNet: Uncovering Propagation Mechanism of Tau Aggregates by Neural Transport Equation
  • Tensor-based Multimodal Learning for Prediction of Pulmonary Arterial Wedge Pressure from Cardiac MRI
  • The Role of Subgroup Separability in Group-Fair Medical Image Classification
  • Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis
  • Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing
  • Towards frugal unsupervised detection of subtle abnormalities in medical imaging
  • Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
  • TractCloud: Registration-free Tractography Parcellation with a Novel Local-global Streamline Point Cloud Representation
  • Triangular Analysis of Geographical Interplay of Lymphocytes (TriAnGIL): Predicting Immunotherapy Response in Lung Cancer
  • Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks
  • Uncovering Structural-Functional Coupling Alterations for Neurodegenerative Diseases
  • Unified surface and volumetric inference on functional imaging data
  • UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
  • Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports
  • Vertex Correspondence in Cortical Surface Reconstruction
  • Visual Grounding of Whole Radiology Reports for 3D CT Images
  • Wall thickness estimation from short axis ultrasound images via temporal compatible deformation learning
  • Wasserstein Distance-Preserving Vector Space of Persistent Homology
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior
  • You Don’t Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

    • Machine Learning - Reinforcement Learning

  • Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing
  • Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
  • Imitation Learning from Expert Video Data for Dissection Trajectory Prediction in Endoscopic Surgical Procedure

    • Machine Learning - Semi-/Weakly-/Un-/Self-supervised Representation Learning

  • 3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images
  • 3D Dental Mesh Segmentation Using Semantics-Based Feature Learning with Graph-Transformer
  • 3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks
  • A Small-Sample Method with EEG Signals Based on Abductive Learning for Motor Imagery Decoding
  • ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast
  • Additional Positive Enables Better Representation Learning for Medical Images
  • AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
  • AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor
  • An Anti-Biased TBSRTC-Category Aware Nuclei Segmentation Framework with A Multi-Label Thyroid Cytology Benchmark
  • An Auto-Encoder to Reconstruct Structure with Cryo-EM Images via Theoretically Guaranteed Isometric Latent Space, and its Application for Automatically Computing the Conformational Pathway
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • An Unsupervised Multispectral Image Registration Network for Skin Diseases
  • Anatomy-Driven Pathology Detection on Chest X-rays
  • Automated CT Lung Cancer Screening Workflow using 3D Camera
  • Automatic Retrieval of Corresponding US Views in Longitudinal Examinations
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • Boundary-weighted logit consistency improves calibration of segmentation networks
  • BrainUSL: Unsupervised Graph Structure Learning for Functional Brain Network Analysis
  • Can point cloud networks learn statistical shape models of anatomies?
  • Category-level Regularized Unlabeled-to-labeled Learning for Semi-supervised Prostate Segmentation with Multi-site Unlabeled Data
  • Chest X-ray Image Classification: A Causal Perspective
  • CL-ADDA: Contrastive Learning with Amplitude-Driven Data Augmentation for fMRI-Based Individualized Predictions
  • Class-Aware Feature Alignment for Domain Adaptative Mitochondria Segmentation
  • CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
  • Clustering disease trajectories in contrastive feature space for biomarker proposal in age-related macular degeneration
  • Combating Medical Label Noise via Robust Semi-supervised Contrastive Learning
  • Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
  • Consistency-guided Meta-Learning for Bootstrapping Semi-Supervised Medical Image Segmentation
  • Content-Preserving Diffusion Model for Unsupervised AS-OCT image Despeckling
  • Contrastive Feature Decoupling for Weakly-supervised Disease Detection
  • Contrastive Masked Image-Text Modeling for Medical Visual Representation Learning
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
  • Cross-adversarial local distribution regularization for semi-supervised medical image segmentation
  • CT Kernel Conversion Using Multi-Domain Image-to-Image Translation with Generator-Guided Contrastive Learning
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition
  • Decoupled Consistency for Semi-supervised Medical Image Segmentation
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • Deep unsupervised clustering for conditional identification of subgroups within a digital pathology image set
  • DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics
  • Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction
  • Detection-free Pipeline for Cervical Cancer Screening of Whole Slide Images
  • DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • Disentangling Site Effects with Cycle-Consistent Adversarial Autoencoder for Multi-site Cortical Data Harmonization
  • Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training
  • Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Exploring Brain Function-Structure Connectome Skeleton via Self-Supervised Graph-Transformer Approach
  • Exploring Unsupervised Cell Recognition with Prior Self-activation Maps
  • Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • Gall Bladder Cancer Detection from US Images with Only Image Level Labels
  • Geometry-invariant abnormality detection
  • GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation
  • Gradient and Feature Conformity-Steered Medical Image Classification with Noisy Labels
  • Graph Convolutional Network with Morphometric Similarity Networks for Schizophrenia Classification
  • GSDG: Exploring A Global Semantic-guided Dual-stream Graph Model for Automated Volume Differential Diagnosis and Prognosis
  • Histopathology Image Classification using Deep Manifold Contrastive Learning
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
  • Infusing physically inspired known operators in deep models of ultrasound elastography
  • Inter-slice Consistency for Unpaired Low-Dose CT Denoising using Boosted Contrastive Learning
  • Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification
  • Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-Training
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • Lesion-aware Contrastive Learning for Diabetic Retinopathy Diagnosis
  • LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
  • LOTUS: Learning to Optimize Task-based US representations
  • LSOR: Longitudinally-Consistent Self-Organized Representation Learning
  • M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
  • Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
  • Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
  • Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
  • MDA-SR: Multi-level Domain Adaptation Super-Resolution for Wireless Capsule Endoscopy Images
  • MedIM: Boost Medical Image Representation via Radiology Report-guided Masking
  • Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy
  • M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization
  • M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision
  • Minimal-supervised Medical Image Segmentation via Vector Quantization Memory
  • Mitosis Detection from Partial Annotation by Dataset Generation via Frame-Order Flipping
  • Modeling Alzheimers' Disease Progression from Multi-task and Self-supervised Learning Perspective with Brain Networks
  • Modularity-Constrained Dynamic Representation Learning for Interpretable Brain Disorder Analysis with Functional MRI
  • MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
  • Multi-Modal Semi-supervised Evidential Recycle Framework for Alzheimer's Disease Classification
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection
  • Multi-Scale Prototypical Transformer for Whole Slide Image Classification
  • Multi-Scale Self-Supervised Learning for Longitudinal Lesion Tracking with Optional Supervision
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
  • One-Shot Traumatic Brain Segmentation with Adversarial Training and Uncertainty Rectification
  • Overall Survival Time Prediction of Glioblastoma on Preoperative MRI Using Lesion Network Mapping
  • Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • PET Image Denoising with Score-Based Diffusion Probabilistic Models
  • PET-diffusion: Unsupervised PET Enhancement based on the Latent Diffusion Model
  • Physics-Informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Position-aware masked autoencoder for histopathology WSI representation learning
  • Prediction of Cognitive Scores by Joint Use of Movie-watching fMRI Connectivity and Eye Tracking via Attention-CensNet
  • Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning
  • PROnet: Point Refinement using Shape-guided Offset Map for Nuclei Instance Segmentation
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
  • S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • SATTA: Semantic-Aware Test-Time Adaptation for Cross-Domain Medical Image Segmentation
  • Scale Federated Learning for Label Set Mismatch in Medical Image Classification
  • Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self- and Semi-Supervised Learning for Gastroscopic Lesion Detection
  • Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  • Self-Supervised Domain Adaptive Segmentation of Breast Cancer via Test-Time Fine-Tuning
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
  • Self-Supervised Polyp Re-Identification in Colonoscopy
  • Semi-supervised Class Imbalanced Deep Learning for Cardiac MRI Segmentation
  • Semi-supervised Domain Adaptive Medical Image Segmentation through Consistency Regularized Disentangled Contrastive Learning
  • Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI
  • SLPD: Slide-level Prototypical Distillation for WSIs
  • Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Structured State Space Models for Multiple Instance Learning in Digital Pathology
  • Style-based Manifold for Weakly-supervised Disease Characteristic Discovery
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Towards Accurate Microstructure Estimation via 3D Hybrid Graph Transformer
  • Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing
  • Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Tracking adaptation to improve SuperPoint for 3D reconstruction in endoscopy
  • Transformer-based Annotation Bias-aware Medical Image Segmentation
  • UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • Unsupervised 3D out-of-distribution detection with latent diffusion models
  • Unsupervised 3D registration through optimization-guided cyclical self-training
  • Unsupervised classification of congenital inner ear malformations using DeepDiffusion for latent space representation
  • Unsupervised Discovery of 3D Hierarchical Structure with Generative Diffusion Features
  • Unsupervised Domain Adaptation for Anatomical Landmark Detection
  • Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos
  • UOD: Universal One-shot Detection of Anatomical Landmarks
  • UPCoL: Uncertainty-informed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
  • VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesis
  • vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
  • Weakly Supervised Lesion Localization of Nascent Geographic Atrophy in Age-Related Macular Degeneration
  • Weakly Supervised Medical Image Segmentation via Superpixel-guided Scribble Walking and Class-wise Contrastive Regularization
  • Weakly-supervised Drug Efficiency Estimation with Confidence Score: Application to COVID-19 Drug Discovery
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification
  • WeakPolyp: You Only Look Bounding Box for Polyp Segmentation
  • What Do AEs Learn? Challenging Common Assumptions in Unsupervised Anomaly Detection
  • Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis
  • You’ve Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray

    • Machine Learning - Transfer learning

  • A denoised Mean Teacher for domain adaptive point cloud registration
  • A Transfer Learning Approach to Localise a Deep Brain Stimulation Target
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Anatomy-Driven Pathology Detection on Chest X-rays
  • Black-box Domain Adaptative Cell Segmentation via Multi-source Distillation
  • Brain Anatomy-Guided MRI Analysis for Assessing Clinical Progression of Cognitive Impairment with Structural MRI
  • Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
  • Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation
  • Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • DCAug: Domain-aware & Content-consistent Cross-cycle Framework for Tumor Augmentation
  • Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
  • Distilling BlackBox to Interpretable models for Efficient Transfer Learning
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance
  • GRACE: A Generalized and Personalized Federated Learning Method for Medical Imaging
  • Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Label-preserving Data Augmentation in Latent Space for Diabetic Retinopathy Recognition
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • LOTUS: Learning to Optimize Task-based US representations
  • Masked Frequency Consistency for Domain-Adaptive Semantic Segmentation of Laparoscopic Images
  • Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
  • MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation
  • MedIM: Boost Medical Image Representation via Radiology Report-guided Masking
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Multiple Prompt Fusion for Zero-Shot Lesion Detection Using Vision-Language Models
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Multi-Target Domain Adaptation with Prompt Learning for Medical Image Segmentation
  • Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
  • Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation
  • Privacy-preserving Early Detection of Epileptic Seizures in Videos
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • Recruiting the best teacher modality: A customized knowledge distillation method for IF based nephropathy diagnosis
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • SCOL: Supervised Contrastive Ordinal Loss for Abdominal Aortic Calcification Scoring on Vertebral Fracture Assessment Scans
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
  • SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
  • Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • Transferability-Guided Multi-Source Model Adaptation for Medical Image Segmentation
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • Uncertainty and Shape-Aware Continual Test-Time Adaptation for Cross-Domain Segmentation of Medical Images
  • Unsupervised Domain Adaptation for Anatomical Landmark Detection
  • Unsupervised Domain Transfer with Conditional Invertible Neural Networks
  • vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
  • Weakly Supervised Cerebellar Cortical Surface Parcellation with Self-Visual Representation Learning
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification
  • X-Ray to CT Rigid Registration Using Scene Coordinate Regression

    • Machine Learning - Uncertainty

  • A coupled-mechanisms modelling framework for neurodegeneration
  • A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging
  • Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Boundary-weighted logit consistency improves calibration of segmentation networks
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Certification of Deep Learning Models for Medical Image Segmentation
  • Chest X-ray Image Classification: A Causal Perspective
  • CheXstray: A Real-Time Multi-Modal Monitoring Workflow for Medical Imaging AI
  • CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  • COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Deep probability contour framework for tumour segmentation and dose painting in PET images
  • DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data
  • Deployment of Image Analysis Algorithms under Prevalence Shifts
  • Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
  • Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification
  • Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
  • Evidence Reconciled Neural Network for Out-of-Distribution Detection in Medical Images
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
  • Fully Bayesian VIB-DeepSSM
  • How Reliable are the Metrics Used for Assessing Reliability in Medical Imaging?
  • Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Improving Image-Based Precision Medicine with Uncertainty-Aware Causal Models
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Maximum Entropy on Erroneous Predictions: Improving model calibration for medical image segmentation
  • Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
  • Multi-Head Multi-Loss Model Calibration
  • Multi-Modal Semi-supervised Evidential Recycle Framework for Alzheimer's Disease Classification
  • Nonuniformly Spaced Control Points based on Variational Cardiac Image Registration
  • One-Shot Traumatic Brain Segmentation with Adversarial Training and Uncertainty Rectification
  • Performance Metrics for Probabilistic Ordinal Classifiers
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributions
  • SATTA: Semantic-Aware Test-Time Adaptation for Cross-Domain Medical Image Segmentation
  • Segmentation Distortion: Quantifying Segmentation Uncertainty under Domain Shift via the Effects of Anomalous Activations
  • Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets
  • Transformer-based Annotation Bias-aware Medical Image Segmentation
  • Trust your neighbours: Penalty-based constraints for model calibration
  • Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
  • Understanding Silent Failures in Medical Image Classification
  • Unsupervised 3D out-of-distribution detection with latent diffusion models
  • UPCoL: Uncertainty-informed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
  • Weakly-supervised Drug Efficiency Estimation with Confidence Score: Application to COVID-19 Drug Discovery

    • Medical Robotics and Haptics

  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue

    • Modalities - Biophotonics

  • Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • Optical Coherence Elastography Needle for Biomechanical Characterization of Deep Tissue
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts
  • Unsupervised Domain Transfer with Conditional Invertible Neural Networks

    • Modalities - CT

  • 3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images
  • 3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions
  • A Novel Video-CTU Registration Method with Structural Point Similarity for FURS Navigation
  • A Patient-Specific Self-supervised Model for Automatic X-ray/CT Registration
  • A Unified Deep-Learning-Based Framework for Cochlear Implant Electrode Array Localization
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation
  • Anatomical Landmark Detection Using a Multiresolution Learning Approach with a Hybrid Transformer-CNN Model
  • Anatomical-aware Point-Voxel Network for Couinaud Segmentation in Liver CT
  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • Automated CT Lung Cancer Screening Workflow using 3D Camera
  • Automatic Segmentation of Internal Tooth Structure from CBCT Images using Hierarchical Deep Learning
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Boundary Difference Over Union Loss For Medical Image Segmentation
  • CARL: Cross-aligned Representation Learning for Multi-view Lung Cancer Histology Classification
  • CenterlinePointNet++: A new point cloud based architecture for coronary artery pressure drop and vFFR estimation
  • Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
  • Conditional Physics-Informed Graph Neural Network For Fractional Flow Reserve Assessment
  • Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
  • ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • CorSegRec: A Topology-Preserving Scheme for Extracting Fully-Connected Coronary Arteries from CT Angiography
  • CT Kernel Conversion Using Multi-Domain Image-to-Image Translation with Generator-Guided Contrastive Learning
  • CTFlow: Mitigating Effects of Computed Tomography Acquisition and Reconstruction with Normalizing Flows
  • CT-guided, Unsupervised Super-resolution Reconstruction of Single 3D Magnetic Resonance Image
  • Deep Learning-Based Air Trapping Quantification using Paired Inspiratory-Expiratory Ultra-Low Dose CT
  • Deep Mutual Distillation for Semi-Supervised Medical Image Segmentation
  • Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction
  • DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
  • DiffULD: Diffusive Universal Lesion Detection
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
  • Enabling Geometry Aware Learning Through Differentiable Epipolar View Translation
  • Evolutionary normalization optimization boosts semantic segmentation network performance
  • Explaining Massive-Training Artificial Neural Networks in Medical Image Analysis Task through Visualizing Functions within the Models
  • Federated Condition Generalization on Low-dose CT Reconstruction via Cross-domain Learning
  • FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
  • Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
  • Flexible Unfolding of Circular Structures for Rendering Textbook-Style Cerebrovascular Maps
  • FocalUNETR: A Focal Transformer for Boundary-aware Prostate Segmentation using CT Images
  • FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • Generating High-Resolution 3D CT with 12-bit Depth using a Diffusion Model with Adjacent Slice and Intensity Calibration Network
  • Graph-theoretic automatic lesion tracking and detection of patterns of lesion changes in longitudinal CT studies
  • GSDG: Exploring A Global Semantic-guided Dual-stream Graph Model for Automated Volume Differential Diagnosis and Prognosis
  • Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
  • H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation
  • HENet: Hierarchical Enhancement Network for Pulmonary Vessel Segmentation in Non-contrast CT Images
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Improved flexibility and interpretability of large vessel stroke prognostication using image synthesis and multi-task learning
  • Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Interpretable Medical Image Classification using Prototype Learning and Privileged Information
  • Inter-slice Consistency for Unpaired Low-Dose CT Denoising using Boosted Contrastive Learning
  • Intraoperative CT augmentation for needle-based liver interventions
  • Intra-operative Forecasting of Standing Spine Shape with Articulated Neural Kernel Fields
  • Inverse Consistency by Construction for Multistep Deep Registration
  • JCCS-PFGM: A Novel Circle-Supervision based Poisson Flow Generative Model for Multiphase CECT Progressive Low-Dose Reconstruction with Joint Condition
  • Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection
  • Learned Alternating Minimization Algorithm for Dual-Domain Sparse-View CT Reconstruction
  • Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction
  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation
  • Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network
  • Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
  • MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • MPBD-LSTM: A Predictive Model For Colorectal Liver Metastases Using Time Series Multi-phase Contrast-Enhanced CT Scans
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Multi-perspective Adaptive Iteration Network for Metal Artifact Reduction
  • Multi-Scale Self-Supervised Learning for Longitudinal Lesion Tracking with Optional Supervision
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
  • Multi-View Vertebra Localization and Identification from CT Images
  • Noise Conditioned Weight Modulation for Robust and Generalizable Low Dose CT Denoising
  • Optimizing the 3D Plate Shape for Proximal Humerus Fractures
  • Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists
  • Partially Supervised Multi-Organ Segmentation via Affinity-aware Consistency Learning and Cross Site Feature Alignment
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Pelvic Fracture Segmentation Using a Multi-scale Distance-weighted Neural Network
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Point Cloud Diffusion Models for Automatic Implant Generation
  • Pre-trained Diffusion Models for Plug-and-Play Medical Image Enhancement
  • Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
  • Revealing Anatomical Structures in PET to Generate CT for Attenuation Correction
  • Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
  • SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  • Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
  • Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
  • Second-course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information
  • Segmentation of Kidney Tumors on Non-Contrast CT Images using Protuberance Detection Network
  • Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation
  • Semantic difference guidance for the uncertain boundary segmentation of CT left atrial appendage
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • SwinUNETR-V2: Stronger Swin Transformers with Stagewise Convolutions for 3D Medical Image Segmentation
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction
  • Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier
  • Topology-Preserving Computed Tomography Super-resolution Based on Dual-stream Diffusion Model
  • Transformer-based tooth segmentation, identification and pulp calcification recognition in CBCT
  • TransLiver: A Hybrid Transformer Model for Multi-phase Liver Lesion Classification
  • Uncertainty and Shape-Aware Continual Test-Time Adaptation for Cross-Domain Segmentation of Medical Images
  • UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
  • Unpaired Cross-modal Interaction Learning for COVID-19 Segmentation on Limited CT images
  • Unsupervised classification of congenital inner ear malformations using DeepDiffusion for latent space representation
  • UPCoL: Uncertainty-informed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
  • VISA-FSS: A Volume-Informed Self Supervised Approach for Few-Shot 3D Segmentation
  • Visual Grounding of Whole Radiology Reports for 3D CT Images
  • vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior

    • Modalities - EEG/ECG

  • A Small-Sample Method with EEG Signals Based on Abductive Learning for Motor Imagery Decoding
  • A Spatial-Temporally Adaptive PINN Framework for 3D Bi-Ventricular Electrophysiological Simulations and Parameter Inference
  • An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography
  • DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data
  • Forward-solution aided deep-learning framework for patient-specific noninvasive cardiac ectopic pacing localization
  • Joint optimization of a β-VAE for ECG task-specific feature extraction
  • Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Prior-driven Dynamic Brain Networks for Multi-Modal Emotion Recognition
  • Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks
  • Wasserstein Distance-Preserving Vector Space of Persistent Homology

    • Modalities - Histopathology

  • A One-class Variational Autoencoder (OCVAE) cascade for classifying atypical bone marrow cell sub-types
  • Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment
  • An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment
  • An Anti-Biased TBSRTC-Category Aware Nuclei Segmentation Framework with A Multi-Label Thyroid Cytology Benchmark
  • Artifact Restoration in Histology Images with Diffusion Probabilistic Models
  • B-Cos Aligned Transformers Learn Human-Interpretable Features
  • Black-box Domain Adaptative Cell Segmentation via Multi-source Distillation
  • CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
  • Centroid-aware feature recalibration for cancer grading in pathology images
  • Contrastive Feature Decoupling for Weakly-supervised Disease Detection
  • Cross-modulated Few-shot Image Generation for Colorectal Tissue Classification
  • DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Deep Cellular Embeddings: An Explainable Plug and Play Improvement for Feature Representation in Histopathology
  • Deep Learning for Tumor-associated Stroma Identification in Prostate Histopathology Slides
  • Deep unsupervised clustering for conditional identification of subgroups within a digital pathology image set
  • Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning
  • Detecting domain shift in multiple instance learning for digital pathology using Fréchet Domain Distance
  • Detection of basal cell carcinoma in whole slide images
  • DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets
  • Diffusion-based Data Augmentation for Nuclei Image Segmentation
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
  • FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • Gene-induced Multimodal Pre-training for Image-omic Classification
  • HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis
  • Instance-Aware Diffusion Model for Gland Segmentation in Colon Histology Images
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification
  • Label-Free Nuclei Segmentation Using Intra-Image Self Similarity
  • MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis
  • Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic Grouping
  • MulHiST: Multiple Histological Staining for Thick Biological Samples via Unsupervised Image-to-Image Translation
  • Multi-modal Pathological Pre-training via Masked Autoencoders for Breast Cancer Diagnosis
  • Multi-Scale Prototypical Transformer for Whole Slide Image Classification
  • NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
  • OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image Classification
  • Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Prompt-based Grouping Transformer for Nucleus Detection and Classification
  • Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning
  • PROnet: Point Refinement using Shape-guided Offset Map for Nuclei Instance Segmentation
  • Recruiting the best teacher modality: A customized knowledge distillation method for IF based nephropathy diagnosis
  • Robust Cervical Abnormal Cell Detection via Distillation from Local-scale Consistency Refinement
  • Segment Membranes and Nuclei from Histopathological Images via Nuclei Point-level Supervision
  • Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
  • SLPD: Slide-level Prototypical Distillation for WSIs
  • StainDiff: Transfer Stain Styles of Histology Images with Denoising Diffusion Probabilistic Models and Self-Ensemble
  • Structured State Space Models for Multiple Instance Learning in Digital Pathology
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform
  • Synthetic Augmentation with Large-scale Unconditional Pre-training
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Transfer Learning-Assisted Survival Analysis of Breast Cancer Relying on the Spatial Interaction Between Tumor-Infiltrating Lymphocytes and Tumors
  • Triangular Analysis of Geographical Interplay of Lymphocytes (TriAnGIL): Predicting Immunotherapy Response in Lung Cancer
  • Weakly-supervised positional contrastive learning: application to cirrhosis classification
  • Zero-shot Nuclei Detection via Visual-Language Pre-trained Models

    • Modalities - MRI

  • A flexible framework for simulating and evaluating biases in deep learning-based medical image analysis
  • A Sheaf Theoretic Perspective for Robust Prostate Segmentation
  • A Texture Neural Network to Predict the Abnormal Brachial Plexus from Routine Magnetic Resonance Imaging
  • A Transfer Learning Approach to Localise a Deep Brain Stimulation Target
  • A2FSeg: Adaptive Multi-Modal Fusion Network for Medical Image Segmentation
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Accurate multi-contrast MRI super-resolution via a dual cross-attention transformer network
  • Adult-like Phase and Multi-scale Assistance for Isointense Infant Brain Tissue Segmentation
  • Alias-Free Co-Modulated Network for Cross-Modality Synthesis and Super-Resolution of MR Images
  • An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis
  • An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
  • Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
  • Aneurysm Pose Estimation with Deep Learning
  • ASC: Appearance and Structure Consistency for Unsupervised Domain Adaptation in Fetal Brain MRI Segmentation
  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • atTRACTive: Semi-automatic white matter tract segmentation using active learning
  • AUA-dE: An adaptive uncertainty guided attention for diffusion MRI models estimation
  • BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
  • Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • Boundary Difference Over Union Loss For Medical Image Segmentation
  • Boundary-weighted logit consistency improves calibration of segmentation networks
  • Brain Anatomy-Guided MRI Analysis for Assessing Clinical Progression of Cognitive Impairment with Structural MRI
  • CAS-Net: Cross-view Aligned Segmentation by Graph Representation of Knees
  • Category-level Regularized Unlabeled-to-labeled Learning for Semi-supervised Prostate Segmentation with Multi-site Unlabeled Data
  • CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
  • CL-ADDA: Contrastive Learning with Amplitude-Driven Data Augmentation for fMRI-Based Individualized Predictions
  • Clinical Evaluation of AI-assisted Virtual Contrast Enhanced MRI in Primary Gross Tumor Volume Delineation for Radiotherapy of Nasopharyngeal Carcinoma
  • CoactSeg: Learning from Heterogeneous Data for New Multiple Sclerosis Lesion Segmentation
  • CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  • Collaborative modality generation and tissue segmentation for early-developing macaque brain MR images
  • Community-Aware Transformer for Autism Prediction in fMRI Connectome
  • Computationally Efficient 3D MRI Reconstruction with Adaptive MLP
  • Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
  • Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction
  • Convolving Directed Graph Edges via Hodge Laplacian for Brain Network Analysis
  • Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
  • CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph
  • Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies
  • CT-guided, Unsupervised Super-resolution Reconstruction of Single 3D Magnetic Resonance Image
  • DBTrans: A Dual-Branch Vision Transformer for Multi-modal Brain Tumor Segmentation
  • DeDA: Deep Directed Accumulator
  • Diffusion Kinetic Model for Breast Cancer Segmentation in Incomplete DCE-MRI
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
  • Discovering Brain Network Dysfunction in Alzheimer’s Disease Using Brain Hypergraph Neural Network
  • Disentangling Site Effects with Cycle-Consistent Adversarial Autoencoder for Multi-site Cortical Data Harmonization
  • Distributionally Robust Image Classifiers for Stroke Diagnosis in Accelerated MRI
  • DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI
  • DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
  • Dose Guidance for Radiotherapy-oriented Deep Learning Segmentation
  • Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
  • Dual Domain Motion Artifacts Correction for MR Imaging Under Guidance of K-space Uncertainty
  • Dynamic Functional Connectome Harmonics
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
  • Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI
  • Efficient Subclass Segmentation in Medical Images
  • Enhance Early Diagnosis Accuracy of Alzheimer's Disease by Elucidating Interactions between Amyloid Cascade and Tau Propagation
  • EoFormer: Edge-oriented Transformer for Brain Tumor Segmentation
  • Evolutionary normalization optimization boosts semantic segmentation network performance
  • Exploring Brain Function-Structure Connectome Skeleton via Self-Supervised Graph-Transformer Approach
  • Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs
  • Fast Non-Markovian Diffusion Model for Weakly Supervised Anomaly Detection in Brain MR Images
  • FedContrast-GPA: Heterogeneous Federated Optimization via Local Contrastive Learning and Global Process-aware Aggregation
  • FedGrav: An Adaptive Federated Aggregation Algorithm for Multi-institutional Medical Image Segmentation
  • Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
  • FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery
  • FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images
  • Gadolinium-Free Cardiac MRI Myocardial Scar Detection by 4D Convolution Factorization
  • Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model
  • Geometry-adaptive Network for Robust Detection of Placenta Accreta Spectrum Disorders
  • Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling
  • Graph Convolutional Network with Morphometric Similarity Networks for Schizophrenia Classification
  • GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
  • H2GM: A Hierarchical Hypergraph Matching Framework for Brain Landmark Alignment
  • HACL-Net: Hierarchical Attention and Contrastive Learning Network for MRI-Based Placenta Accreta Spectrum Diagnosis
  • H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  • Importance Weighted Variational Cardiac MRI Registration Using Transformer and Implicit Prior
  • Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
  • Improving Pathology Localization: Multi-Series Joint Attention Takes the Lead
  • Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI
  • Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
  • Inverse Consistency by Construction for Multistep Deep Registration
  • InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model
  • Ischemic stroke segmentation from a cross-domain representation in multimodal diffusion studies
  • Joint Representation of Functional and Structural Profiles for Identifying Common and Consistent 3-Hinge Gyral Folding Landmark
  • Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
  • Learning Ontology-based Hierarchical Structural Relationship for Whole Brain Segmentation
  • Learning Reliability of Multi-Modality Medical Images for Tumor Segmentation via Evidence-Identified Denoising Diffusion Probabilistic Models
  • Learning with Domain-Knowledge for Generalizable Prediction of Alzheimer's Disease from Multi-Site Structural MRI
  • LSOR: Longitudinally-Consistent Self-Organized Representation Learning
  • M3D-NCA: Robust 3D Segmentation with Built-in Quality Control
  • Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
  • Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis
  • Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
  • Maximum Entropy on Erroneous Predictions: Improving model calibration for medical image segmentation
  • Maximum-entropy estimation of joint relaxation-diffusion distribution using multi-TE diffusion MRI
  • MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
  • Memory Replay for Continual Medical Image Segmentation through Atypical Sample Selection
  • M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision
  • Microstructure Fingerprinting for Heterogeneously Oriented Tissue Microenvironments
  • Mixing Temporal Graphs with MLP for Longitudinal Brain Connectome Analysis
  • MoCoSR: Respiratory Motion Correction and Super-Resolution for 3D Abdominal MRI
  • Modeling Alzheimers' Disease Progression from Multi-task and Self-supervised Learning Perspective with Brain Networks
  • ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Motion Compensated Unsupervised Deep Learning for 5D MRI
  • MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities
  • Multimodal brain age estimation using interpretable adaptive population-graph learning
  • Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk
  • Multimodal Deep Fusion in Hyperbolic Space for Mild Cognitive Impairment Study
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Multi-shot Prototype Contrastive Learning and Semantic Reasoning for Medical Image Segmentation
  • Multi-Target Domain Adaptation with Prompt Learning for Medical Image Segmentation
  • Multi-task Joint Prediction of Infant Cortical Morphological and Cognitive Development
  • Neural Pre-Processing: A Learning Framework for End-to-end Brain MRI Pre-processing
  • NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
  • NISF: Neural Implicit Segmentation Functions
  • Nonuniformly Spaced Control Points based on Variational Cardiac Image Registration
  • One-Shot Traumatic Brain Segmentation with Adversarial Training and Uncertainty Rectification
  • Overall Survival Time Prediction of Glioblastoma on Preoperative MRI Using Lesion Network Mapping
  • Path-based Heterogeneous Brain Transformer Network for Resting-State Functional Connectivity Analysis
  • PCMC-T1: Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction
  • Personalized Patch-based Normality Assessment of Brain Atrophy in Alzheimer's Disease
  • Physics-based Decoding Improves Magnetic Resonance Fingerprinting
  • Physics-Informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
  • Physics-Informed Neural Networks for Tissue Elasticity Reconstruction in Magnetic Resonance Elastography
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Positive Definite Wasserstein Graph Kernel for Brain Disease Diagnosis
  • Predicting Diverse Functional Connectivity from Structural Connectivity Based on Multi-Contexts Discriminator GAN
  • Prediction of Cognitive Scores by Joint Use of Movie-watching fMRI Connectivity and Eye Tracking via Attention-CensNet
  • Prediction of Infant Cognitive Development with Cortical Surface-based Multimodal Learning
  • Progressively Coupling Network for Brain MRI Registration in Few-shot Situation
  • Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
  • QCResUNet: Joint Subject-level and Voxel-level Prediction of Segmentation Quality
  • RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • Relaxation-Diffusion Spectrum Imaging for Probing Tissue Microarchitecture
  • Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
  • Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  • Robust estimation of the microstructure of the early developing brain using deep learning
  • Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation
  • Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
  • Semi-supervised Class Imbalanced Deep Learning for Cardiac MRI Segmentation
  • SFusion: Self-attention based N-to-One Multimodal Fusion Block
  • Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention
  • SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI
  • Simulation of Arbitrary Level Contrast Dose in MRI Using an Iterative Global Transformer Model
  • Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction
  • Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
  • SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
  • Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  • Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
  • StructuRegNet: Structure-guided Multimodal 2D-3D Registration
  • Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
  • Style-based Manifold for Weakly-supervised Disease Characteristic Discovery
  • SurfFlow: A Flow-Based Approach for Rapid and Accurate Cortical Surface Reconstruction from Infant Brain MRI
  • SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
  • Synthesis of Contrast-Enhanced Breast MRI Using T1- and Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanism
  • TauFlowNet: Uncovering Propagation Mechanism of Tau Aggregates by Neural Transport Equation
  • Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets
  • Tensor-based Multimodal Learning for Prediction of Pulmonary Arterial Wedge Pressure from Cardiac MRI
  • Towards Accurate Microstructure Estimation via 3D Hybrid Graph Transformer
  • Towards Expert-Amateur Collaboration: Prototypical Label Isolation Learning for Left Atrium Segmentation with Mixed-Quality Labels
  • Towards frugal unsupervised detection of subtle abnormalities in medical imaging
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • TractCloud: Registration-free Tractography Parcellation with a Novel Local-global Streamline Point Cloud Representation
  • Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation
  • UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation
  • Uncertainty and Shape-Aware Continual Test-Time Adaptation for Cross-Domain Segmentation of Medical Images
  • Uncovering Structural-Functional Coupling Alterations for Neurodegenerative Diseases
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • Unified surface and volumetric inference on functional imaging data
  • UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
  • UPCoL: Uncertainty-informed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
  • Vertex Correspondence in Cortical Surface Reconstruction
  • VISA-FSS: A Volume-Informed Self Supervised Approach for Few-Shot 3D Segmentation
  • Visual-Attribute Prompt Learning for Progressive Mild Cognitive Impairment Prediction
  • WarpEM: Dynamic Time Warping for Accurate Catheter Registration in EM-guided Procedures
  • Weakly Supervised Medical Image Segmentation via Superpixel-guided Scribble Walking and Class-wise Contrastive Regularization

    • Modalities - Microscopy

  • 3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers
  • A General Stitching Solution for Whole-Brain 3D Nuclei Instance Segmentation from Microscopy Images
  • A Motion Transformer for Single Particle Tracking in Fluorescence Microscopy Images
  • A One-class Variational Autoencoder (OCVAE) cascade for classifying atypical bone marrow cell sub-types
  • Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs
  • B-Cos Aligned Transformers Learn Human-Interpretable Features
  • BigFUSE: Global Context-Aware Image Fusion in Dual-View Light-Sheet Fluorescence Microscopy with Image Formation Prior
  • CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
  • CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention
  • Class-Aware Feature Alignment for Domain Adaptative Mitochondria Segmentation
  • Deep unsupervised clustering for conditional identification of subgroups within a digital pathology image set
  • Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning
  • DiffuseIR: Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
  • Diffusion-based Data Augmentation for Nuclei Image Segmentation
  • Efficient Spatiotemporal Learning of Microscopic Video for Augmented Reality-Guided Phacoemulsification Cataract Surgery
  • Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • Exploring Unsupervised Cell Recognition with Prior Self-activation Maps
  • Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
  • Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
  • LUCYD: A Feature-Driven Richardson-Lucy Deconvolution Network
  • Mitosis Detection from Partial Annotation by Dataset Generation via Frame-Order Flipping
  • PAS-Net: Rapid Prediction of Antibiotic Susceptibility from Fluorescence Images of Bacterial Cells Using Parallel Dual-branch Network
  • Pick and Trace: Instance Segmentation for Filamentous Objects with a Recurrent Neural Network
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Prompt-based Grouping Transformer for Nucleus Detection and Classification
  • Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning
  • Reconstructing the Hemodynamic Response Function via a Bimodal Transformer
  • Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  • Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
  • Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos
  • Weakly-supervised Drug Efficiency Estimation with Confidence Score: Application to COVID-19 Drug Discovery

    • Modalities - PET/SPECT

  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
  • Deep probability contour framework for tumour segmentation and dose painting in PET images
  • Discovering Brain Network Dysfunction in Alzheimer’s Disease Using Brain Hypergraph Neural Network
  • DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis
  • DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
  • Fast Reconstruction for Deep Learning PET Head Motion Correction
  • Geometry-invariant abnormality detection
  • Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
  • H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation
  • Learning with Synthesized Data for Generalizable Lesion Detection in Real PET Images
  • Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
  • Mixing Temporal Graphs with MLP for Longitudinal Brain Connectome Analysis
  • PET Image Denoising with Score-Based Diffusion Probabilistic Models
  • PET-diffusion: Unsupervised PET Enhancement based on the Latent Diffusion Model
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Revealing Anatomical Structures in PET to Generate CT for Attenuation Correction
  • Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
  • TauFlowNet: Uncovering Propagation Mechanism of Tau Aggregates by Neural Transport Equation
  • Transformer-based Dual-domain Network for Few-view Dedicated Cardiac SPECT Image Reconstructions
  • TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
  • UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner

    • Modalities - Text (clinical/radiology reports)

  • Ariadne's Thread: Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images
  • CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
  • CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training
  • Diversity-preserving Chest Radiographs Generation from Reports in One Stage
  • Enhancing Automatic Placenta Analysis through Distributional Feature Recomposition in Vision-Language Contrastive Learning
  • Improving Outcome Prediction of Pulmonary Embolism by De-Biased Multi-Modality Model
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-Training
  • Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
  • MedIM: Boost Medical Image Representation via Radiology Report-guided Masking
  • M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization
  • Multi-modality contrastive learning for sarcopenia screening from hip X-rays and clinical information
  • Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Rad-ReStruct: A Novel VQA Benchmark and Method for Structured Radiology Reporting
  • Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
  • Surgical Video Captioning with Mutual-Modal Concept Alignment
  • Text-Guided Cross-Position Attention for Segmentation: Case of Medical Image
  • Text-guided Foundation Model Adaptation for Pathological Image Classification
  • TPRO: Text-prompting-based Weakly Supervised Histopathology Tissue Segmentation
  • Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports
  • Xplainer: From X-Ray Observations to Explainable Zero-Shot Diagnosis
  • You’ve Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray

    • Modalities - Ultrasound

  • A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  • A Style Transfer-based Augmentation Framework for Improving Segmentation and Classification Performance across Different Sources in Ultrasound Images
  • Asymmetric Contour Uncertainty Estimation for Medical Image Segmentation
  • Automatic Retrieval of Corresponding US Views in Longitudinal Examinations
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • Combating Medical Label Noise via Robust Semi-supervised Contrastive Learning
  • Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition
  • Developing Large Pre-trained Model for Breast Tumor Segmentation from Ultrasound Images
  • Differentiable Beamforming for Ultrasound Autofocusing
  • DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
  • DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  • Do we really need that skip-connection? Understanding its interplay with task complexity
  • Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos
  • EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
  • Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis
  • Fine-grained Hand Bone Segmentation via Adaptive Multi-dimensional Convolutional Network and Anatomy-constraint Loss
  • FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery
  • Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
  • From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation
  • Gall Bladder Cancer Detection from US Images with Only Image Level Labels
  • Geometric Ultrasound Localization Microscopy
  • GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation
  • Improving Automatic Fetal Biometry Measurement with Swoosh Activation Function
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Infusing physically inspired known operators in deep models of ultrasound elastography
  • Interpretable Deep Biomarker for Serial Monitoring of Carotid Atherosclerosis Based on Three-Dimensional Ultrasound Imaging
  • LOTUS: Learning to Optimize Task-based US representations
  • MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
  • Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection
  • MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization
  • Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
  • Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • Optical Ultrasound Imaging for Endovascular Repair of Abdominal Aortic Aneurysms: A Pilot Study
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Self-Supervised Domain Adaptive Segmentation of Breast Cancer via Test-Time Fine-Tuning
  • Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
  • STAR-Echo: A Novel Biomarker for Prognosis of MACE in Chronic Kidney Disease Patients using Spatiotemporal Analysis and Transformer-Based Radiomics Models
  • TabAttention: Learning Attention Conditionally on Tabular Data
  • Thinking Like Sonographers: A Deep CNN Model for Diagnosing Gout from Musculoskeletal Ultrasound
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning
  • Trackerless Volume Reconstruction from Intraoperative Ultrasound Images
  • Ultrasonic tracking of a rapid-exchange microcatheter with simultaneous pressure sensing for cardiovascular interventions
  • Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • Wall thickness estimation from short axis ultrasound images via temporal compatible deformation learning

    • Modalities - Video

  • A Motion Transformer for Single Particle Tracking in Fluorescence Microscopy Images
  • A Novel Video-CTU Registration Method with Structural Point Similarity for FURS Navigation
  • A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  • A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants
  • ACT-Net: Anchor-context Action Detection in Surgery Videos
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  • CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
  • Contrastive Feature Decoupling for Weakly-supervised Disease Detection
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing
  • Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training
  • EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
  • Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis
  • Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
  • GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos
  • Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • Learning Expected Appearances for Intraoperative Registration during Neurosurgery
  • Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection
  • MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
  • On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
  • Prior-driven Dynamic Brain Networks for Multi-Modal Emotion Recognition
  • Privacy-preserving Early Detection of Epileptic Seizures in Videos
  • ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography
  • Realistic endoscopic illumination modeling for NeRF-based data generation
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-Supervised Polyp Re-Identification in Colonoscopy
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
  • Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
  • Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • STAR-Echo: A Novel Biomarker for Prognosis of MACE in Chronic Kidney Disease Patients using Spatiotemporal Analysis and Transformer-Based Radiomics Models
  • Surgical Video Captioning with Mutual-Modal Concept Alignment
  • TabAttention: Learning Attention Conditionally on Tabular Data
  • TCL: Triplet Consistent Learning for Odometry Estimation of Monocular Endoscope
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • Tracking adaptation to improve SuperPoint for 3D reconstruction in endoscopy
  • YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection

    • Modalities - other

  • 3D Dental Mesh Segmentation Using Semantics-Based Feature Learning with Graph-Transformer
  • 3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions
  • A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
  • A Multi-Task Method for Immunofixation Electrophoresis Image Classification
  • A Semantic-guided and Knowledge-based Generative Framework for Orthodontic Visual Outcome Preview
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
  • AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
  • ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models
  • Assignment Theory-Augmented Neural Network for Dental Arch Labeling
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Certification of Deep Learning Models for Medical Image Segmentation
  • Conditional Physics-Informed Graph Neural Network For Fractional Flow Reserve Assessment
  • Content-Preserving Diffusion Model for Unsupervised AS-OCT image Despeckling
  • Cross-view Deformable Transformer for Non-displaced Hip Fracture Classification from Frontal-Lateral X-ray Pair
  • Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Models
  • Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy
  • Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation
  • Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays
  • DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
  • Diversity-preserving Chest Radiographs Generation from Reports in One Stage
  • Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
  • Evolutionary normalization optimization boosts semantic segmentation network performance
  • Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
  • FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling
  • Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
  • Incomplete Multimodal Learning for Visual Acuity Prediction after Cataract Surgery Using Masked Self-Attention
  • Joint Dense-Point Representation for Contour-Aware Graph Segmentation
  • Joint Segmentation and Sub-Pixel Localization in Structured Light Laryngoscopy
  • Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
  • LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
  • Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
  • MDA-SR: Multi-level Domain Adaptation Super-Resolution for Wireless Capsule Endoscopy Images
  • M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization
  • MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities
  • MSKdeX: Musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume
  • Multi-modality contrastive learning for sarcopenia screening from hip X-rays and clinical information
  • Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Physics-Informed Neural Networks for Tissue Elasticity Reconstruction in Magnetic Resonance Elastography
  • PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
  • Polar Eyeball Shape Net for 3D Posterior Ocular Shape Representation
  • Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  • Probabilistic Modeling Ensemble Vision Transformer Improves Complex Polyp Segmentation
  • Representation, Alignment, Fusion: A Generic Transformer-based Framework for Multi-modal Glaucoma Recognition
  • Retinal Thickness Prediction from Multi-modal Fundus Photography
  • SATTA: Semantic-Aware Test-Time Adaptation for Cross-Domain Medical Image Segmentation
  • SCOL: Supervised Contrastive Ordinal Loss for Abdominal Aortic Calcification Scoring on Vertebral Fracture Assessment Scans
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • Skin Lesion Correspondence Localization in Total Body Photography
  • SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
  • Transformer-based end-to-end classification of variable-length volumetric data
  • Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation
  • TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer
  • Unsupervised Domain Adaptation for Anatomical Landmark Detection
  • UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • VF-HM: Vision Loss Estimation using Fundus Photograph for High Myopia
  • Vision Transformer based Multi-Class Lesion Detection in IVOCT
  • Weakly Supervised Lesion Localization of Nascent Geographic Atrophy in Age-Related Macular Degeneration
  • X2Vision : 3D CT Reconstruction from Biplanar X-Rays with Deep Structure Prior

    • Population Imaging and Imaging Genetics

  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • Identification of Disease-sensitive Brain Imaging Phenotypes and Genetic Factors using GWAS Summary Statistics
  • Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions

    • Rigorous Evaluations of Methodology in Clinical Workflows

  • A Closed-form Solution to Electromagnetic Sensor Based Intraoperative Limb Length Measurement in Total Hip Arthroplasty
  • Accurate and Robust Patient Height and Weight Estimation in Clinical Imaging using a Depth Camera
  • Clinical Evaluation of AI-assisted Virtual Contrast Enhanced MRI in Primary Gross Tumor Volume Delineation for Radiotherapy of Nasopharyngeal Carcinoma
  • You Don’t Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

    • Surgical Data Science

  • A Multi-Task Network for Anatomy Identification in Endoscopic Pituitary Surgery
  • A Novel Video-CTU Registration Method with Structural Point Similarity for FURS Navigation
  • A Transfer Learning Approach to Localise a Deep Brain Stimulation Target
  • Bridging ex-vivo training and intra-operative deployment for surgical margin assessment with Evidential Graph Transformer
  • Cascade Transformer Encoded Boundary-Aware Multibranch Fusion Networks for Real-Time and Accurate Colonoscopic Lesion Segmentation
  • CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
  • Deep Homography Prediction for Endoscopic Camera Motion Imitation Learning
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • Estimated time to surgical procedure completion: An exploration of video analysis methods
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms
  • Learnable Query Initialization for Surgical Instrument Instance Segmentation
  • Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Realistic endoscopic illumination modeling for NeRF-based data generation
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Reflectance Mode Fluorescence Optical Tomography with Consumer-Grade Cameras
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self-distillation for surgical action recognition
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts
  • Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions
  • SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery
  • Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models
  • Unsupervised Domain Transfer with Conditional Invertible Neural Networks

    • Surgical Planning and Simulation

  • A Transfer Learning Approach to Localise a Deep Brain Stimulation Target
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • Automatic Surgical Reconstruction for Orbital Blow-out Fracture via Symmetric Prior Anatomical Knowledge-Guided Adversarial Generative Network
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • From Mesh Completion to AI Designed Crown
  • High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
  • Intra-operative Forecasting of Standing Spine Shape with Articulated Neural Kernel Fields
  • Optimizing the 3D Plate Shape for Proximal Humerus Fractures
  • Pelvic Fracture Reduction Planning Based on Morphable Models and Structural Constraints
  • Point Cloud Diffusion Models for Automatic Implant Generation
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
  • Semantic difference guidance for the uncertain boundary segmentation of CT left atrial appendage
  • Soft-tissue Driven Craniomaxillofacial Surgical Planning
  • Spatiotemporal Incremental Mechanics Modeling of Facial Tissue Change
  • TCL: Triplet Consistent Learning for Odometry Estimation of Monocular Endoscope
  • Virtual Heart models help elucidate the role of border zone in sustained monomorphic Ventricular Tachycardia

    • Surgical Scene Understanding

  • A Multi-Task Network for Anatomy Identification in Endoscopic Pituitary Surgery
  • ACT-Net: Anchor-context Action Detection in Surgery Videos
  • CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
  • CycleSTTN: A Learning-Based Temporal Model for Specular Augmentation in Endoscopy
  • Detecting the Sensing Area of A Laparoscopic Probe in Minimally Invasive Cancer Surgery
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights
  • LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
  • Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
  • SEDSkill: Surgical Events Driven Method for Skill Assessment from Thoracoscopic Surgical Videos
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self-distillation for surgical action recognition
  • Self-Supervised Learning for Endoscopic Video Analysis
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • Semantic segmentation of surgical hyperspectral images under geometric domain shifts
  • Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  • Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions
  • Surgical Activity Triplet Recognition via Triplet Disentanglement
  • SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery

    • Surgical Skill and Work Flow Analysis

  • A Multi-Task Network for Anatomy Identification in Endoscopic Pituitary Surgery
  • ACT-Net: Anchor-context Action Detection in Surgery Videos
  • Cochlear Implant Fold Detection in Intra-operative CT using Weakly Supervised Multi-Task Deep Learning
  • Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
  • GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos
  • LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms
  • Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Regressing Simulation to Real: Unsupervised Domain Adaptation for Automated Quality Assessment in Transoesophageal Echocardiography
  • SEDSkill: Surgical Events Driven Method for Skill Assessment from Thoracoscopic Surgical Videos
  • SegmentOR: Obtaining Efficient Operating Room Semantics Through Temporal Propagation
  • Self-distillation for surgical action recognition
  • Self-supervised Sim-to-Real Kinematics Reconstruction for Video-based Assessment of Intraoperative Suturing Skills
  • Soft-tissue Driven Craniomaxillofacial Surgical Planning
  • Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions
  • Surgical Activity Triplet Recognition via Triplet Disentanglement
  • Surgical Video Captioning with Mutual-Modal Concept Alignment
  • Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models

    • Surgical Visualization and Mixed/Augmented/Virtual Reality

  • A Closed-form Solution to Electromagnetic Sensor Based Intraoperative Limb Length Measurement in Total Hip Arthroplasty
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • Detecting the Sensing Area of A Laparoscopic Probe in Minimally Invasive Cancer Surgery
  • EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • From Tissue to Sound: Model-based Sonification of Medical Imaging
  • High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights
  • Intelligent Virtual B-scan Mirror (IVBM)
  • Learning Expected Appearances for Intraoperative Registration during Neurosurgery
  • Multi-view Guidance for Self-supervised Monocular Depth Estimation on Laparoscopic Images via Spatio-temporal Correspondence
  • Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues
  • POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  • Regularized Kelvinlet Functions to Model Linear Elasticity for Image-to-Physical Registration of the Breast
  • Semantic Virtual Shadows (SVS) for Improved Perception in 4D OCT Guided Surgery
  • SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking

    • Treatment Response and Outcome/Disease Prediction

  • A Multimodal Disease Progression Model for Genetic Associations with Disease Dynamics
  • A Semantic-guided and Knowledge-based Generative Framework for Orthodontic Visual Outcome Preview
  • ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment
  • Attentive Deep Canonical Correlation Analysis for Diagnosing Alzheimer's Disease using Multimodal Imaging Genetics
  • Automatic Bleeding Risk Rating System of Gastric Varices
  • Bidirectional Mapping with Contrastive Learning on Multimodal Neuroimaging Data
  • CARL: Cross-aligned Representation Learning for Multi-view Lung Cancer Histology Classification
  • Clustering disease trajectories in contrastive feature space for biomarker proposal in age-related macular degeneration
  • cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
  • DAS-MIL: Distilling Across Scales for MIL Classification of Histological WSIs
  • Distributionally Robust Image Classifiers for Stroke Diagnosis in Accelerated MRI
  • Dynamic Curriculum Learning via In-Domain Uncertainty for Medical Image Classification
  • Dynamic Graph Neural Representation Based Multi-modal Fusion Model for Cognitive Outcome Prediction in Stroke Cases
  • FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification
  • Graph Convolutional Network with Morphometric Similarity Networks for Schizophrenia Classification
  • Graph-theoretic automatic lesion tracking and detection of patterns of lesion changes in longitudinal CT studies
  • HC-Net: Hybrid Classification Network for Automatic Periodontal Disease Diagnosis
  • Improved flexibility and interpretability of large vessel stroke prognostication using image synthesis and multi-task learning
  • Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
  • Improving Image-Based Precision Medicine with Uncertainty-Aware Causal Models
  • Improving Outcome Prediction of Pulmonary Embolism by De-Biased Multi-Modality Model
  • Interpretable Deep Biomarker for Serial Monitoring of Carotid Atherosclerosis Based on Three-Dimensional Ultrasound Imaging
  • Joint prediction of response to therapy, molecular traits, and spatial organisation in colorectal cancer biopsies
  • Learning Asynchronous Common and Individual Functional Brain Network for AD Diagnosis
  • Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
  • Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
  • Multi-modal Variational Autoencoders for normative modelling across multiple imaging modalities
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Multi-scope Analysis Driven Hierarchical Graph Transformer for Whole Slide Image based Cancer Survival Prediction
  • Overall Survival Time Prediction of Glioblastoma on Preoperative MRI Using Lesion Network Mapping
  • Patients and Slides are Equal: A Multi-level Multi-instance Learning Framework for Pathological Image Analysis
  • Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
  • Retinal Age Estimation with Temporal Fundus Images Enhanced Progressive Label Distribution Learning
  • Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
  • Tensor-based Multimodal Learning for Prediction of Pulmonary Arterial Wedge Pressure from Cardiac MRI
  • Thyroid Nodule Diagnosis in Dynamic Contrast-enhanced Ultrasound via Microvessel Infiltration Awareness
  • Treatment Outcome Prediction for Intracerebral Hemorrhage via Generative Prognostic Model with Imaging and Tabular Data
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • VF-HM: Vision Loss Estimation using Fundus Photograph for High Myopia
  • Weakly-supervised Drug Efficiency Estimation with Confidence Score: Application to COVID-19 Drug Discovery

    • Visualization in Biomedical Imaging

  • A Unified Deep-Learning-Based Framework for Cochlear Implant Electrode Array Localization
  • An AI-Ready Multiplex Staining Dataset for Reproducible and Accurate Characterization of Tumor Immune Microenvironment
  • An Auto-Encoder to Reconstruct Structure with Cryo-EM Images via Theoretically Guaranteed Isometric Latent Space, and its Application for Automatically Computing the Conformational Pathway
  • Analysis of Suture Force Simulations for Optimal Orientation of Rhomboid Skin Flaps
  • Anatomical Landmark Detection Using a Multiresolution Learning Approach with a Hybrid Transformer-CNN Model
  • AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
  • AR2T: Advanced Realistic Rendering Technique for Biomedical Volumes
  • Category-independent Visual Explanation for Medical Deep Network Understanding
  • CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
  • Explainable Image Classification with Improved Trustworthiness for Tissue Characterisation
  • Flexible Unfolding of Circular Structures for Rendering Textbook-Style Cerebrovascular Maps
  • FLIm-based In Vivo Classification of Residual Cancer in the Surgical Cavity during Transoral Robotic Surgery
  • Full Image-index Remainder based Single Low-dose DR/CT Self-supervised Denoising
  • Geometric Ultrasound Localization Microscopy
  • Intelligent Virtual B-scan Mirror (IVBM)
  • Intraoperative CT augmentation for needle-based liver interventions
  • Joint optimization of a β-VAE for ECG task-specific feature extraction
  • Joint prediction of response to therapy, molecular traits, and spatial organisation in colorectal cancer biopsies
  • LUCYD: A Feature-Driven Richardson-Lucy Deconvolution Network
  • Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classification
  • ModusGraph: Automated 3D and 4D Mesh Model Reconstruction from cine CMR with Improved Accuracy and Efficiency
  • Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  • Physics-Informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
  • Polar Eyeball Shape Net for 3D Posterior Ocular Shape Representation
  • Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  • S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  • Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
  • Semantic Virtual Shadows (SVS) for Improved Perception in 4D OCT Guided Surgery
  • Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
  • Style-based Manifold for Weakly-supervised Disease Characteristic Discovery
  • Understanding Silent Failures in Medical Image Classification
  • Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos
  • UXDiff: Synthesis of X-ray Image from Ultrasound Coronal Image of Spine with Diffusion Probabilistic Network
  • Whole-Heart Reconstruction with Explicit Topology Integrated Learning