Challenge Banner

Participation

Submission

The algorithms are submitted as Docker container images according to the Grand Challenge documentation. You can find a submission template in the TopAneu-26 Repository.

Expected outputs are:

  • Task1: A json file containing the detected locations of the sample, formatted as below. NOTE This is different from the json format the training data is provided as in location_jsons due to compatibility with existing Grand Challenge sockets.
[ 
  34,
  35
]
  • Task2: A 1 Channel 3D mask containing the (multi-)instance segmentations as provided in the location_masks in the training data. Must be in the range of our data labels (0-50) and in the datatype 8 bit unsigned integer (np.uint8/torch.uint8).

TIP Take a look at our submission templates to base your docker image on, a more detailed description of the template is in the README.

Limits

Every team or person can only submit once to each phase. The sanity check phase is meant to first test if your implementation works and debug if it doesn't (Only successful runs contribute to the submission limit).

Leaderboards

The results are hidden and will be revealed by us at a later date.

Account and Team

  • Each participant can join at most one team.
  • Only one member of each team can submit algorithms, we will exclude duplicate submissions from the final leaderboards.
  • Normally, each participant/team can only submit one algorithm to each final test phase.
  • If you or your team have sufficiently distinct algorithms, you may submit more than one algorithm to a final test phase, subject to approval from us.
  • Please reach out to us if want to split into sub-teams or submit different algorithms.
  • We will exclude anonymous submissions unless we can verify your profile.

Members of the Organizing 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.

Data Usage

We provide training data from multiple centers for this challenge. Usage of external data is permitted, however in this case you also need to provide your models trained without external data for a more fair comparison in our challenge manuscript.

Last Updated: 02 Jul 2026