作者
Matthew T MacLean, Qasim Jehangir, Marijana Vujkovic, Yi-An Ko, Harold Litt, Arijitt Borthakur, Hersh Sagreiya, Mark Rosen, David A Mankoff, Mitchell D Schnall, Haochang Shou, Julio Chirinos, Scott M Damrauer, Drew A Torigian, Rotonya Carr, Daniel J Rader, Walter R Witschey
发表日期
2021/6/1
期刊
Journal of the American Medical Informatics Association
卷号
28
期号
6
页码范围
1178-1187
出版商
Oxford University Press
简介
Objective
The objective was to develop a fully automated algorithm for abdominal fat segmentation and to deploy this method at scale in an academic biobank.
Materials and Methods
We built a fully automated image curation and labeling technique using deep learning and distributive computing to identify subcutaneous and visceral abdominal fat compartments from 52,844 computed tomography scans in 13,502 patients in the Penn Medicine Biobank (PMBB). A classification network identified the inferior and superior borders of the abdomen, and a segmentation network differentiated visceral and subcutaneous fat. Following technical evaluation of our method, we conducted studies to validate known relationships with visceral and subcutaneous fat.
Results
When compared with 100 manually annotated cases, the classification network was on average …
学术搜索中的文章
MT MacLean, Q Jehangir, M Vujkovic, YA Ko, H Litt… - Journal of the American Medical Informatics …, 2021