Validation Phase - The LEOPARD Challenge

📢 The LEOPARD challenge workshop will happen live at MICCAI 2024 in Marrakesh, on 6th October in the afternoon session, room Jade.

Data. Altogether, the validation dataset consists of 99 whole slide images, corresponding to 99 patients. The data in the Validation phase comes from two sources: Radboud UMC (also the source of training data) and an anonymous external center. The tissue masks are available for each case in the validation set during the submission. There are cases in validation data that have artifacts. The artifacts (e.g. pen marks) have been excluded from validation tissue masks. It is up to participants to decide on whether to use the provided tissue masks or not. The testing set masks will follow the same procedure. The format, resolution, and magnification of validation slides are identical to training ones.
Evaluation. The LEOPARD challenge uses a censored C-index as a main challenge metric. In the validation phase, the C-index is first computed on each dataset center separately and then averaged across centers. The participants can see their performance on each of the centers by clicking "Show all metrics" on the Leaderboard: Radboud UMC as well as an anonymous external center.