MICCAI 2026 CARDIAC IMAGING THEME  ·  JOINTLY WITH THE STACOM WORKSHOP

// Publications

Paper Submission

Accepted papers will be published in a Springer Lecture Notes in Computer Science (LNCS) volume. A valid paper submission is required for test-set evaluation, leaderboard inclusion, and award eligibility. Teams that do not submit a paper will not appear in the final ranking.

EchoRisk Paper First Page

Challenge Technical Reference

The detailed technical layout of the challenge, including comprehensive dataset statistics, annotation workflows, and baseline model protocols, is available on arXiv:
EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology.

Teams wishing to reference the official challenge setup, evaluation parameters, or baseline reference benchmarks in their methodology papers may use the following citation:

Show BibTeX Citation 
@misc{kalliatakis2026echorisk,
  title={EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology},
  author={Grigorios Kalliatakis and Georgia Karanasiou and Georgios Manikis and Manolis Tsiknakis and Dimitrios Fotiadis and Dorothea Tsekoura and Kalliopi Keramida and Vasileios Bouratzis and Lampros Lakkas and Katerina Naka and Andri Papakonstantinou and Anastasia Constantinidou and Kostas Marias},
  year={2026},
  eprint={2607.01039},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2607.01039},
}
1
Eligibility: Every team that submits to the test phase must submit a paper. Teams participating in multiple tasks may submit a single paper covering all methods and results, or separate papers per task — both are acceptable.
2
Submission Platform: Papers must be submitted via the EchoRisk OpenReview venue. OpenReview submission portal →
3
Key Dates:
  • Full paper submission deadline: 7 July 2026
  • Reviews due: 23 July 2026
  • Acceptance notifications: 31 July 2026
  • Camera-ready deadline: 13 August 2026

Papers submitted by 7 July should describe the method and validation-set results.

4
Paper Length & Format:
  • Initial submissions: up to 8 pages (text, tables, figures) + up to 2 pages for references.
  • Author names and affiliations must be included in the initial PDF submission. Our venue uses single-blind review: authors are visible to reviewers and organisers throughout the process. Include your registered team name at the end of the abstract, matching the name submitted in your Team Registration Form.
  • Supplementary materials (video, animations) may be submitted as a single ZIP file.
  • Submissions must be PDF only, prepared using the official LNCS templates and guidelines (LaTeX or Word), also available via Overleaf.
  • Accepted papers will be published in a Springer LNCS proceedings volume.
  • Springer encourages all authors to include their ORCID.
5
Review Process: The EchoRisk organising team will coordinate independent peer review of all submitted papers. Reviews and author responses will be made publicly visible on OpenReview. Camera-ready papers will remain hidden until publication.
6
Patent Disclosure: An open-access version of all accepted papers from the EchoRisk-MICCAI 2026 Satellite Event will be made available on the MICCAI Society website no earlier than one week before the first day of the conference. Authors intending to file patents are responsible for ensuring that all necessary filings are completed prior to this public release.

// Content Guidelines

Author Guidelines

Each paper must clearly describe the following. Keep sections on task motivation and dataset description concise — reviewers are familiar with the challenge setup.

i
Method: A clear description of the approach used, including architecture, training procedure, and any design choices specific to the challenge tasks.
ii
Training & Validation Setup: Dataset splits used, preprocessing steps, augmentation strategy, hyperparameter choices, and any external data or pretrained models used (all external resources must be explicitly disclosed).
iii
Results: Quantitative results on the validation set at minimum. Camera-ready versions should additionally report final test-set performance as returned by the official evaluation pipeline.
iv
Discussion & Interpretation: Analysis of results, failure cases, limitations, and any clinically relevant observations. Strong papers will contextualise performance relative to the clinical problem rather than reporting numbers in isolation.
v
Team Identification: To link your paper with your Synapse team, include your registered team name at the end of the abstract.

Ready to submit?

Submit on OpenReview →

Questions? echorisk.miccai@gmail.com

CARDIOCARE
FORTH
UOI
HMU
NKUA
BOCOC
IEO
KSBC