Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography.

Autor: Shan H; Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China; Shanghai Center for Brain Science and Brain-inspired Technology, Shanghai, China; Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, USA. Electronic address: hmshan@fudan.edu.cn., Vimieiro RB; Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, USA; Department of Electrical and Computer Engineering, São Carlos School of Engineering, University of São Paulo, São Carlos, Brazil. Electronic address: rodrigo.vimieiro@usp.br., Borges LR; Department of Electrical and Computer Engineering, São Carlos School of Engineering, University of São Paulo, São Carlos, Brazil; Real Time Tomography, LLC, Villanova, USA. Electronic address: lucas.borges@realtimetomography.com., Vieira MAC; Department of Electrical and Computer Engineering, São Carlos School of Engineering, University of São Paulo, São Carlos, Brazil. Electronic address: mvieira@sc.usp.br., Wang G; Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, USA. Electronic address: wangg6@rpi.edu.

Publikováno v: Artificial intelligence in medicine [Artif Intell Med] 2023 Aug; Vol. 142, pp. 102555. Date of Electronic Publication: 2023 Apr 28.