Metrics
Evaluation will be done according to the following metrics:
Task 1 – Circle of Willis classification:
- balanced accuracy (BA)
Task 2 – Circle of Willis quantification:
- mean absolute error (MAE)
- Pearson correlation coefficient
Ranking
Each metric is averaged over all test images. For each metric, the participating teams are sorted from best to worst. The best team receives a rank of 0 and the worst team a rank of 1; all other teams are ranked (0,1) relative to their performance within the range of that metric. Finally, these ranks are averaged into the overall rank that is used for the Results.
Code
The code used for evaluation will be published as soon as possible.