The amounts of muscle and fat in a person's body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate the analysis of CT body composition using a DenseNet to select the CT slice and U-Net to perform segmentation. We train and test our methods on independent cohorts. Our results show Dice scores (0.95-0.98) and correlation coefficients (R=0.99) that are favorable compared to human readers. These results suggest that fully automated body composition analysis is feasible, which could enable both clinical use and large-scale population studies.
@article{arxiv.1808.03844,
title = {Fully-Automated Analysis of Body Composition from CT in Cancer Patients Using Convolutional Neural Networks},
author = {Christopher P. Bridge and Michael Rosenthal and Bradley Wright and Gopal Kotecha and Florian Fintelmann and Fabian Troschel and Nityanand Miskin and Khanant Desai and William Wrobel and Ana Babic and Natalia Khalaf and Lauren Brais and Marisa Welch and Caitlin Zellers and Neil Tenenholtz and Mark Michalski and Brian Wolpin and Katherine Andriole},
journal= {arXiv preprint arXiv:1808.03844},
year = {2018}
}