Hi Andreavs, many thanks for your answer.
In the "task and evaluation" section of the challenge information page, it says "We will use a metric (aggregated DSC) adapted from the Aggregated Jaccard Index in [Kumar et al. 2017], [...] In the end, we will divide the aggregated intersection by the aggregated union, both for GTVp and GTVn and will compute the average of these two aggregated Jaccard indices.".
However the notebook https://github.com/voreille/hecktor/blob/master/notebooks/evaluate_segmentation.ipynb is not doing this, as it is not up to date for this year. My question would be whether some code examples of how to compute the aggregated Dice score would be provided, so the results reported in our evaluation sets are consistent with the ones in the test set.
Many thanks in advance!