How to Participate

Tips

  • 👉 Please refer to our TopCoW_Algo_Submission repo on GitHub as a template and guide on the submission process.
  • The validation phase is not used for final evaluation.
    • Please use validation phase to debug and validate your docker submission workflow.
    • Or better still, test locally and use the "Try-out Algorithm" on your algorithm page
      • Please refer to the carefully written README of our submission template repo for more instructions
  • The final test phases only allow for one submission per team for each phase
    • The test phases take much longer than the smaller validation phases to be evaluated (might take half a day!)
    • Please plan ahead and do not cram last minute for the final test phases.
  • Submissions to multi-class segmentation tasks are automatically evaluated by us for binary segmentation performance.

Participation Rules

Usage of training data

Participants may use any other public datasets and private in-house data, or modify the supplied TopCoW 2023 training data, provided that they disclose and mention any additional or modified training datasets in their description of the submitted algorithm (please see "Publication policy" below).

Members of the organizers' institutes

Members of the organizers' direct research groups can participate and their results can be included in the publications and the leaderboard. However, they are not eligible for awards.

Award and result announcement policy

Top 3 teams for segmentation performance from each of the two tracks and two tasks will be publicly named and given a certificate along with a Swiss wooden toy cow 🇨🇭🐄 as a souvenir at the in-person challenge event.

Participants are invited to prepare a 4-minute presentation/video for the challenge session to present and discuss their methods.

After the public announcement, a detailed analysis of the submitted results will be available upon request.

🏆 📰 Publication policy

The challenge results will be summarized and published in a journal manuscript. All participants with a (reasonable) submission are invited to contribute to our challenge publication!

In order for us to include you in our paper, please

  1. Fill up this contact form. (Same link as in the forum's announcement https://grand-challenge.org/forums/forum/topology-aware-anatomical-segmentation-of-the-circle-of-willis-698/topic/contact-form-for-miccai-event-prize-and-publication-1843/)
  2. Send us 4 paragraphs of your algorithm submission before the MICCAI event:
What to submit for the challenge paper:
  • 1 para: method description ~3-4 lines (or more)
  • 2 para: data used, data preprocessing, data augmentation
    • roi treatment, image sampling, image orientation and voxel size treatment, patches, and discuss the differences in the results with additional/modified data if any
  • 3 para: training strategies, amount of compute and the type of resources used
    • e.g., type and number of GPUs, internal cluster, or cloud provider, and high-performance computing cluster used for training
  • 4 para: acknowledgement and availability of docker/code/data

Link to references

Preferably in LaTeX/Overleaf and with figures

The above are the minimal requirements. You are of course welcome to send us more than just 4 paragraphs + figures about your submission.

NOTE: this is required for the co-authorship even if you are awarded and announced for winner or have presented in the event. (for the academic value of the summary paper)

👉 Submit BEFORE the MICCAI event on Oct 12 📅

Each submission can have maximum three co-authorships for the challenge paper. Additional authors from the top submissions can be included upon request with justification according to the ICMJE authorship guidelines.

Participating teams may submit their results separately without any publication embargo.