User submissions are evaluated by comparing their Submission CSV to the ground truth Solution CSV with respect to the
[Area Under the ROC Curve](https://it.wikipedia.org/wiki/Area_Under_the_Curve)
(AUC) metric.
The Submission CSV file must contain a prediction score or probability for each classified study, corresponding to the probability of that lesion(s) to belong to class "Malignant" or "Benign".
It is expected that the probability to belong to class "Benign" ranges from 0 to 0.5, and that the probability to belong to class "Malignant" ranges from 0.5 to 1 (p < 0.5 -> "Benign", p > 0.5 -> "Malignant").