28th INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING
AND COMPUTER ASSISTED INTERVENTION
23-27 SEPTEMBER 2025 • DAEJEON CONVENTION CENTER

OPEN DATA

OPEN DATA 2025

OPEN DATA MICCAI 2025

Unlock Medical Machine Learning with Open Data

Daejeon Convention Centre - Daejeon, South Korea

WELCOME MESSAGE

Dear Researchers,

We are delighted to announce the second edition of Open Data at MICCAI 2025!

As the landscape of medical machine learning continues to evolve, access to diverse, representative, and inclusive datasets remains crucial for addressing global healthcare challenges effectively. The Open Data initiative aims to foster collaboration and innovation by promoting the sharing of medical imaging datasets.

Building on the foundation of the first edition, Open Data continues to emphasize underrepresented populations and diseases. Despite progress in medical imaging research and the availability of public datasets, critical gaps persist—particularly in regions such as South-East Asia. By highlighting datasets from underrepresented populations and diseases, we strive to reduce disparities in healthcare and promote inclusivity in machine learning research.

This year too, we plan to establish a dedicated repository to host publicly available high-quality medical imaging datasets, with a focus on underrepresented populations and diseases. Information regarding the repository structure and storage guidelines will be shared at a later stage. The initiative remains closely aligned with the principles of FAIR data and Data-centric AI, where data and its systematic engineering are at the forefront of model development. After all, there are no "good" models without "good" data.

MICCAI will be held on September 23-27, 2025, at the Daejon Convention Center, South Korea, and the Open Data event will run in parallel to the main track. Hence if you are visiting MICCAI, you can visit the Open Data event: no separate registration is required.

The presented datasets and related works will be selected through a peer-reviewed paper submission process. The MELBA journal will serve as the official journal for submissions from the MICCAI Open Data track.

We look forward to seeing you at the 2nd Open Data session at MICCAI 2025—welcome!

REPOSITORY

Guidelines on data submission, including upload procedures and storage details, will be provided in due course.

TOPICS OF INTEREST

The main focus is on:

  • New medical imaging datasets that encompass diverse demographics, ethnicities, and medical conditions. This year is especially focused on South-East Asia, but we also welcome datasets from other (underrepresented) populations or diseases.
  • Updated or re-designed datasets based on previously publicly available data.

Additional topics include:

  • Dataset collection and annotation techniques.
  • Data augmentation strategies for improving dataset diversity.
  • Ethical considerations in data sharing and privacy preservation.
  • Applications of open data in medical image analysis, diagnosis, and treatment planning.
  • Challenges and opportunities in accessing and utilizing underrepresented datasets.

IMPORTANT DATES

Call for papers
Expected May 2025
Paper submission deadline
23:59 CET, June 16, 2025
Review deadline
23:59 CET, June 30, 2025
Notification of acceptance
23:59 CET, July 4, 2025
Camera-ready paper submission
TBD

SUBMISSION

We welcome submissions of papers presenting novel datasets, particularly those from South-East Asia and other underrepresented populations and diseases - including methodologies for the data collection and curation, and innovative approaches for utilizing them in medical imaging research.

The paper submission site will be announced here and open in May.

SCOPE
  • Encourage and empower through an open repository the sharing and dissemination of open-access datasets to facilitate collaboration and reproducibility.
  • Promote awareness and understanding of the importance of inclusivity and representative data in developing robust and equitable healthcare solutions.
  • Facilitate networking opportunities among researchers, data custodians, and stakeholders interested in leveraging open data for medical machine learning.
CRITERIA
  • Guidelines on data submission, including upload procedures and storage details, will be provided at a later stage.
  • Adhere to the FAIR data guidelines.
  • Any associated code should be open source.
AUTHOR GUIDELINES

Listed below are important requirements, besides the above criteria, for preparing and submitting a manuscript to Open Data MICCAI 2025. Accepted papers will have the opportunity of oral presentation at the Open Data session, and will be invited for submission at the MELBA journal Resource track to be published in a special issue on Open Data MICCAI 2025.

  1. Manuscript template: Submissions must be limited to a maximum of 8 pages for text, figures, and tables and up to 2 additional pages for references. You must follow the MELBA journal latex template for submissions available here (i.e., melba-sample.tex).

    1. NO cover letter addressed to MELBA is needed at this stage.
    2. Please follow the format of MELBA Resource manuscripts for Data Resources, available here.
    3. In addition to the above, we request that you include information on how the presented data adhere to the FAIR data principles; licensing, access procedures, and ethical considerations (including anonymization/pseudonymization practices); detailed descriptions of the (meta)data, including collection, equipment and acquisition protocols, data model and format, processing, curation, ground truth definition, and known errors/limitations; and comprehensive visual examples.

  2. Dataset description: To ensure the quality and utility of shared medical imaging datasets, we have established the following minimal information requirements for data submissions:

    1. Dataset Overview

      1. Title: A concise and descriptive title of the dataset.
      2. Abstract: A summary outlining the dataset's purpose, scope, and potential applications.

    2. Data Acquisition Details

      1. Imaging Modality: Specify the type of imaging used (e.g., CT, MRI, pathology, microscopy).

      2. Equipment Specifications

        1. Manufacturer and Model: Detail the imaging device's manufacturer, model, and any relevant technical characteristics (e.g. field strength for MRI)
        2. Acquisition Settings: Provide key parameters such as resolution, magnification, and imaging protocols.

    3. Subject Information

      1. Demographics: Include anonymized data on age, sex, and relevant clinical information.
      2. Cohort Description: Describe the selection criteria, including inclusion and exclusion parameters.

    4. Annotation and Segmentation

      1. Annotation Protocols: Detail the methods and standards used for annotations or segmentations, including any automatic tools used in the annotation process.
      2. Annotator Expertise: Specify the qualifications of individuals who performed the annotations.
      3. Inter-Observer Variability: If applicable, report measures of consistency among different annotators.

    5. Data Format and Structure

      1. File Formats: List the formats of the image and annotation files (e.g., DICOM, TIFF, JPEG).
  3. Supplementary materials: An upload link (of maximum two files) will be made available in your author console after you have created your submission. DO NOT append your supplementary material at the end of your main paper. As supplementary material you should upload any supporting information for the presented datasets that do not lie to the main manuscript requirements, e.g., additional visual examples. .

REVIEW GUIDELINES

This is a single-blind review process. For general guidelines on "What Makes a Good Review" please refer to the corresponding section in the MICCAI reviewer guidelines.

For this track, pay special attention on the Submission guidelines listed above - scope and criteria, summarized below (in order of priority):

  1. Data availability and adherence to the FAIR data principles.
  2. Licensing, potential use cases, and ethical considerations/approvals.
  3. Methods used for the data and meta-data creation/collection: from the methods and equipment used for the acquisition to final processing, and the AI-ready state of the dataset (cleaning, curation, possible suggested splits, etc.).
  4. Clarity of the dataset specifics.
  5. Dataset usage showcase(s) with evaluation results.

ORGANIZING COMMITTEE

Martijn P.A. Starmans, PhD
Assistant Professor AI for Integrated Diagnostics (AIID)
Dept. of Radiology & Nuclear Medicine, Dept. of Pathology
Erasmus University Medical Center, Rotterdam, the Netherlands
Apostolia Tsirikoglou, PhD
Research Specialist, AI for Breast Imaging
Dept. of Oncology-Pathology,
Karolinska Institutet, Sweden
Namkug Kim, PhD
Assistant Professor of Convergence Medicine
Asan Medical Center, Seoul, South Korea
University of Ulsan College of Medicine, Ulsan, South Korea
Lidia Garrucho Moras
PhD Candidate, EUCanImage AI Lead
Artificial Intelligence in Medicine Lab
University of Barcelona, Barcelona, Spain
Kaouther Mouheb
PhD Candidate, Medical Image Analysis and Federated Learning
Dept. of Radiology & Nuclear Medicine
Erasmus University Medical Center, Rotterdam, the Netherlands