List of Papers By topics Author List
| Paper Info | Reviews | Meta-review | Author Feedback | Post-Rebuttal Meta-reviews |
Authors
Xi-Yao Ma, Shi-Qi Liu, Xiao-Liang Xie, Xiao-Hu Zhou, Zeng-Guang Hou, Yan-Jie Zhou, Meng Song, Lin-Sen Zhang, Chao-Nan Wang
Abstract
During percutaneous coronary intervention (PCI), severe elastic deformation of coronary arteries caused by cardiac movement is a serious disturbance to physicians. It increases the difficulty of estimating the relative position between interventional instruments and vessels, leading to inaccurate operation and higher intraoperative mortality. Providing doctors with dynamic angiographic images can be helpful. However, it often faces the challenges of indistinguishable features between consecutive frames and multiple modalities caused by individual differences. In this paper a novel deeply-supervised pseudo-siamese network (DSP-Net) is developed to solve the problem. A pseudo siamese attention dense (PSAD) block is designed to extract salient features from X-ray images with noisy background, and the deep supervision architecture is integrated to accelerate convergence. Evaluations are conducted on the CVM X-ray Database built by us, which consists of 51 sequences, showing that the proposed network can not only achieve state-of-the-art matching performance of 3.48 Hausdorff distance and 84.09% guidewire recall rate, but also demonstrate the great generality to images with different heart structures or fluoroscopic angles. Exhaustive experiment results indicate that our DSP-Net has the potential to assist doctors to overcome the visual misjudgment caused by the elastic deformation of the arteries and achieve safer procedure.
Link to paper
DOI: https://link.springer.com/chapter/10.1007/978-3-031-16449-1_5
SharedIt: https://rdcu.be/cVRUL
Link to the code repository
N/A
Link to the dataset(s)
N/A
Reviews
Review #1
- Please describe the contribution of the paper
The authors proposed a novel framework DSP-Net to automatically match the intra-operative X-ray fluoroscopic images to the dynamic angiographic images, which can provide doctors with dynamic reference images in PCI.
- Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
The proposed DSP-Net processes X-ray fluoroscopic and angiographic images parallelly, achieving state-of-the-art performance on their medical image datasets. The designed PSAD block successfully distinguishes nuanced frames by learning the representative features and efficiently overcomes the noisy background, showing great generality to images from different sequences.
- Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
This study mainly focused on searching the matched image of the X-ray fluoroscopic image from the angiographic image gallery, and lacks the evaluation of time efficiency.
- Please rate the clarity and organization of this paper
Very Good
- Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance
Most of the implementation details have been addressd.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
The authors proposed a novel framework DSP-Net to automatically match the intra-operative X-ray fluoroscopic images to the dynamic angiographic images, which can provide doctors with dynamic reference images in PCI. The writting and organization of this paper is good. I suggest the authors to add the time cost of the proposed method for this matching task.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
5
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
The authors has proposed an effective method to automatically match the intra-operative X-ray fluoroscopic images to the dynamic angiographic images. However, the segmentation of the guidewire and vessels is achived by an existing method, the projection method or the registration method has not been introduced clearly, and the time cost evaluation is not available.
- Number of papers in your stack
4
- What is the ranking of this paper in your review stack?
2
- Reviewer confidence
Confident but not absolutely certain
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
Review #2
- Please describe the contribution of the paper
To solve a series of problems caused by cardiac motion during PCI treatment:
- DSP-Net realizes automatic matching of dynamic angiography images;
- The PSAD block is designed to successfully distinguish subtle frames, overcome the noise background, and enhance generality.
- Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
The method proposed in this paper is novel: Use the transmissing information and the compensating details to connect the two inputs, extract the significant features, and improve the accuracy; The comparative experiments of the methods proposed in this paper are sufficient: there are many similar methods compared, and the comparative results are more detailed.
- Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
- Incorrectly written order of references;
- Excessively long sentence structure;
- Lack of theoretical support for some of the descriptions;
- The experimental test data accounts for less;
- Please rate the clarity and organization of this paper
Good
- Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance
The network architecture is clear and the algorithm logic is rigorous. The experimental part uses comparative and ablation experiments, which are rich in type. And the comparison test is full. But, the experimental datasets are not clinical data and the effectiveness of clinical use is debatable.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
- P1 : References throughout the paper are marked in a confusing order in the text.
- P2 line4-8: The sentences are too long and not easy for the reader to read and understand.
- P2 line3 from last: Lack of theoretical basis. Can you add a recent paper with similar content for illustration?
- P3 Fig.2.: Does ‘gallery’ have any special meaning? Can it be replaced by ‘datasets’?
- P3 line2: Can you give a simple explanation for this?
- P3 line5: Can you add a relevant comparative test to confirm this benefit?
- P3 2.1 line7: Can you give specific comparative tests or add a paper with corresponding conclusions?
- P6 3.1 line6 74: The proportion of test sets is relatively small.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
6
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
The paper is clearly structured and logically sound. It has some bright spots, the experiments are adequate, and the experimental results have been improved compared to other methods. But, as the datasets are not from the clinic, the clinical use effect is uncertain, and there are also problems such as unclear description of some details and lack of supporting materials.
- Number of papers in your stack
4
- What is the ranking of this paper in your review stack?
3
- Reviewer confidence
Very confident
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
Review #3
- Please describe the contribution of the paper
- the first automatic approach exploring the task of dynamic angiographic image matching problem
- DSP-Net processes X-ray fluoroscopic and angiographic images parallelly in a proposed dataset.
- Please list the main strengths of the paper; you should write about a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
- The dataset is constructed, in which the performance is competitive compared to other methods.
- The depiction is clear with loss.
- Well written and well oeganized.
- Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
- More comparison with other SOTA Siamense structure is recommended.
- Registration methods literature review.
- Please rate the clarity and organization of this paper
Excellent
- Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance
- Easy to follow
- Dataset is expected to release.
- The method is clear.
- Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
- As the structure outputs a binary number, the authors are encouraged compare the intuition compared with GAN.
- More methods compared with non-rigid registration methids.
- Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making
6
- Please justify your recommendation. What were the major factors that led you to your overall score for this paper?
- Clear contributions and organization.
- Solid work and contributions.
- Extensive comaparison.
- Number of papers in your stack
4
- What is the ranking of this paper in your review stack?
1
- Reviewer confidence
Confident but not absolutely certain
- [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed
N/A
- [Post rebuttal] Please justify your decision
N/A
Primary Meta-Review
- Please provide your assessment of this work, taking into account all reviews. Summarize the key strengths and weaknesses of the paper and justify your recommendation. In case you deviate from the reviewers’ recommendations, explain in detail the reasons why. In case of an invitation for rebuttal, clarify which points are important to address in the rebuttal.
All three reviewers have highlighted the novelty in the paper with no major weaknesses. R1 suggested the inclusion of the time efficiency of the algorithm while R3 requested more comparisons with state-of-the-art Siamese structures.
- What is the ranking of this paper in your stack? Use a number between 1 (best paper in your stack) and n (worst paper in your stack of n papers). If this paper is among the bottom 30% of your stack, feel free to use NR (not ranked).
2
Author Feedback
N/A