Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI $-$Should Different Clinical Objectives Mandate Different Loss Functions?

Anindo Saha, Joeran Bosma, Jasper Linmans +2

We hypothesize that probabilistic voxel-level classification of anatomy and malignancy in prostate MRI, although typically posed as near-identical segmentation tasks via U-Nets, re…