Deep neural network for water/fat separation: Supervised training, unsupervised training, and no training. Issue 4 (26th October 2020)

• Record Type: Journal Article
• Authors: Jafari, Ramin; Spincemaille, Pascal; Zhang, Jinwei; Nguyen, Thanh D.; Luo, Xianfu; Cho, Junghun; Margolis, Daniel; Prince, Martin R.; Wang, Yi
• Is Part Of: Magnetic resonance in medicine. Volume 85:Issue 4(2021)
• Page Start: 2263
• Page End: 2277
• Publication Date: 2020-10-26
• Subjects: deep learning -- label free -- unsupervised -- water/fat separation; Nuclear magnetic resonance -- Periodicals; Electron paramagnetic resonance -- Periodicals; 616.07548
• DOI: 10.1002/mrm.28546
• Languages: English
• ISSNs: 0740-3194

Abstract

Abstract : Purpose: To use a deep neural network (DNN) for solving the optimization problem of water/fat separation and to compare supervised and unsupervised training. Methods: The current T 2 ∗ ‐IDEAL algorithm for solving water/fat separation is dependent on initialization. Recently, DNN has been proposed to solve water/fat separation without the need for suitable initialization. However, this approach requires supervised training of DNN using the reference water/fat separation images. Here we propose 2 novel DNN water/fat separation methods: 1) unsupervised training of DNN (UTD) using the physical forward problem as the cost function during training, and 2) no training of DNN using physical cost and backpropagation to directly reconstruct a single dataset. The supervised training of DNN, unsupervised training of DNN, and no training of DNN methods were compared with the reference T 2 ∗ ‐IDEAL. Results: All DNN methods generated consistent water/fat separation results that agreed well with T 2 ∗ ‐IDEAL under proper initialization. Conclusion: The water/fat separation problem can be solved using unsupervised deep neural networks.