Loss odyssey in medical image segmentation - ScienceDirect
https://www.sciencedirect.com/science/article/pii/S136184152100081501.07.2021 · Dice loss has been widely used in many top solutions of medical image segmentation challenges ( Bernard, Lalande, Zotti, Cervenansky, Yang, Heng, Cetin, Lekadir, Camara, Ballester, et al., 2018, Bakas, Reyes, et Int, Menze ). In addition to cross entropy and Dice loss, more than 10 loss functions have been proposed for segmentation CNNs.