Geçer, BarışAksoy, SelimMercan, E.Shapiro, L. G.Weaver, D. L.Elmore, J. G.2019-02-212019-02-2120180031-3203http://hdl.handle.net/11693/49939Generalizability of algorithms for binary cancer vs. no cancer classification is unknown for clinically more significant multi-class scenarios where intermediate categories have different risk factors and treatment strategies. We present a system that classifies whole slide images (WSI) of breast biopsies into five diagnostic categories. First, a saliency detector that uses a pipeline of four fully convolutional networks, trained with samples from records of pathologists’ screenings, performs multi-scale localization of diagnostically relevant regions of interest in WSI. Then, a convolutional network, trained from consensus-derived reference samples, classifies image patches as non-proliferative or proliferative changes, atypical ductal hyperplasia, ductal carcinoma in situ, and invasive carcinoma. Finally, the saliency and classification maps are fused for pixel-wise labeling and slide-level categorization. Experiments using 240 WSI showed that both saliency detector and classifier networks performed better than competing algorithms, and the five-class slide-level accuracy of 55% was not statistically different from the predictions of 45 pathologists. We also present example visualizations of the learned representations for breast cancer diagnosis.EnglishBreast histopathologyDeep learningDigital pathologyMulti-class classificationRegion of interest detectionSaliency detectionWhole slide imagingArticle10.1016/j.patcog.2018.07.022