Important Material:

• GitHub Repository: Contains an example algorithm, JSON schemas for the individual data sources, and an extensive README to help you get started.
• HANCOCK download page: Here you can download the training data for this challenge.

Grand Challenge Setup¶

On Grand Challenge, you will be faced with four different phases for the two different tasks. For either of the tasks, there is an Open Development Phase and a Closed Testing Phase. The Open Development Phase should be used for testing if your algorithm is setup properly. We allow up to 10 submissions to these phases.

Open Development Phase¶

The Open Development Phases are intended for you to check if your algorithm performs properly within the Grand Challenge System. It will only be executed on 5 patients from the training dataset, so there is a high chance that the achieved score may not generalize to the Closed Testing Phase. The patients used during this phase are the following:

• Patient 001
• Patient 002
• Patient 006
• Patient 012
• Patient 016

We selected them based on their completeness for the usable modalities of the challenge. For further information on the single modalities and their accessibility, please check the data chapter.

Once your algorithm works and you are certain that you want to submit your solution, you can move on to submit to the Closed Testing Phase.

Closed Testing Phase¶

The Closed Testing Phases are the submissions that count for the final evaluation and will be evaluated for the prizes. You can only submit a single algorithm. So make sure that everything works properly. These phases will use unseen and unpublished new data that is setup in the same way as in the already publicly available HANCOCK dataset.