: A hybrid deep learning model for interpretable diagnosis of breast cancer in whole-slide images

Felipe André Zeiser, Cristiano André da Costa, Gabriel de Oliveira Ramos, Henrique Bohn, Ismael Santos, Adriana Vial Roehe

Abstract: Highlights•Deep learning model able to predict a refined segmentation of breast cancer in WSI.•Cascade of CNNs working together inferring global and local characteristics.•We provide the diagnosis in an interpretable way through segmentation and heat maps.•Our model identified suspicious regions not labeled in a public dataset.