Meeting Banner
Abstract #3858

Segmentation of whole-body adipose tissue from magnetic resonance fat-fraction images with U-net deep-learning framework

Chuanli Cheng1, Zhiming Wang1, Qian Wan1, Yangzi Qiao1, Changjun Tie1, Hairong Zheng1, Xin Liu1, and Chao Zou1
1Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, Shenzhen, China

Over the past several decades, the worldwide obesity epidemic has become a significant public health. As a consequence, accurate measurement of obesity is critical for obesity management. In the present study, an automated algorithm is proposed to segment subcutaneous adipose tissue (SAT) and internal adipose tissue (IAT) from the total adipose tissue for whole-body fat distribution analysis using proton density fat fraction (PDFF) magnetic resonance images. The dice coefficient of the network achieved 97.6%, and the processing time was less than 0.1s/image.

This abstract and the presentation materials are available to members only; a login is required.

Join Here