Deep neural network for water/fat separation: Supervised training, unsupervised training, and no training
Ramin Jafari, Pascal Spincemaille, Jinwei Zhang, Thanh D. Nguyen, Xianfu Luo, Junghun Cho, Daniel Margolis, Martin R. Prince, Yi Wang
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 ‐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 ‐IDEAL. Results All DNN methods generated consistent water/fat separation results that agreed well with ‐IDEAL under proper initialization. Conclusion The water/fat separation problem can be solved using unsupervised deep neural networks.