Fig. 1From: Translating prognostic quantification of c-MYC and BCL2 from tissue microarrays to whole slide images in diffuse large B-cell lymphoma using deep learningOverview of the proposed methodology. (a) AB-MIL is trained to predict c-MYC and BCL2 scores from TMAs. (b) Each WSI is decomposed into TMA-sized regions that are passed through the TMA-trained AB-MIL model. This generates a distribution of local WSI scores which are summarized using their median to predict the overall slide-level c-MYC or BCL2 scoreBack to article page