Premium
Deep neural network for water/fat separation: Supervised training, unsupervised training, and no training
Author(s) -
Jafari Ramin,
Spincemaille Pascal,
Zhang Jinwei,
Nguyen Thanh D.,
Luo Xianfu,
Cho Junghun,
Margolis Daniel,
Prince Martin R.,
Wang Yi
Publication year - 2021
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.28546
Subject(s) - initialization , computer science , artificial neural network , artificial intelligence , separation (statistics) , training (meteorology) , backpropagation , pattern recognition (psychology) , machine learning , ideal (ethics) , meteorology , philosophy , physics , epistemology , programming language
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.