Open AccessDeep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment
Author(s) -
Robert Hemke,
Colleen Buckless,
Andrew Tsao,
Benjamin Wang,
Martin Torriani
Publication year - 2019
Publication title -
skeletal radiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.571
H-Index - 91
eISSN - 1432-2161
pISSN - 0364-2348
DOI - 10.1007/s00256-019-03289-8
Subject(s) - segmentation , medicine , convolutional neural network , artificial intelligence , pelvis , deep learning , sørensen–dice coefficient , computer science , pattern recognition (psychology) , nuclear medicine , image segmentation , radiology
To develop a deep convolutional neural network (CNN) to automatically segment an axial CT image of the pelvis for body composition measures. We hypothesized that a deep CNN approach would achieve high accuracy when compared to manual segmentations as the reference standard.