Combining weakly and strongly supervised learning improves strong supervision in Gleason pattern classification

BMC Medical Imaging

Niccolò Marini¹  Sebastian Otálora¹  Manfredo Atzori²  Henning Müller³ 

[1] HES-SO Valais, Technopôle 3, 3960, Sierre, Switzerland;Computer Science Centre (CUI), University of Geneva, Route de Drize 7, Battelle A, Carouge, Switzerland;HES-SO Valais, Technopôle 3, 3960, Sierre, Switzerland;Department of Neuroscience, University of Padova, via Belzoni 160, 35121, Padova, Italy;HES-SO Valais, Technopôle 3, 3960, Sierre, Switzerland;Faculty of Medicine, University of Geneva, 1 rue Michel-Servet, 1211, Geneva, Switzerland;

关键词: Computational pathology;    Weak supervision;    Transfer learning;    Prostate cancer;    Deep learning;   

DOI  :  10.1186/s12880-021-00609-0

来源: Springer

【 授权许可】

CC BY