Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks.

ABSTRACT:

Purpose

To perform and evaluate water-fat signal separation of whole-body gradient echo scans using convolutional neural networks.

Methods

Whole-body gradient echo scans of 240 subjects, each consisting of 5 bipolar echoes, were used. Reference fat fraction maps were created using a conventional method. Convolutional neural networks, more specifically 2D U-nets, were trained using 5-fold cross-validation with 1 or several echoes as input, using the squared difference between the output and the reference fat fraction maps as the loss function. The outputs of the networks were assessed by the loss function, measured liver fat fractions, and visually. Training was performed using a graphics processing unit (GPU). Inference was performed using the GPU as well as a central proces

SUBMITTER: Andersson J 

PROVIDER: S-EPMC6618066 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature