“…In a discriminative scenario, a decision function is directly learned from manually annotated training images to characterize the difference between cancerous and normal tissues. A broad spectrum of algorithms have been used for learning the decision function (see for example [1,3,18,27,34,39]). In recent years, convolutional neural networks [1,18,20,21,34] have become an extremely popular choice as the base learner, achieving high rankings in BRATS competitions.…”