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

======

This repository contains the training and testing codes for the paper "Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography". For simulating dose reduction on clinical images, we used the codes available here. Also, we used a model-based (MB) restoration as a benchmark, also available here, which uses the commonly known BM3D.

Reference:

@article{shan2023impact,
  title={Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography},
  author={Shan, Hongming and Vimieiro, Rodrigo B and Borges, Lucas R and Vieira, Marcelo AC and Wang, Ge},
  journal={Artificial Intelligence in Medicine},
  volume={142},
  pages={102555},
  year={2023},
  publisher={Elsevier}
}

---

AI-based X-ray Imaging System (AXIS)
Department of Biomedical Engineering
Rensselaer Polytechnic Institute
Troy - USA

Laboratory of Computer Vision (Lavi)
Department of Electrical and Computer Engineering
São Carlos School of Engineering, University of São Paulo
São Carlos - Brazil