Fully-Automated Analysis of Body Composition from CT in Cancer Patients Using Convolutional Neural Networks

TL;DR

This paper presents a fully automated method using deep learning to analyze body composition from CT scans, achieving high accuracy comparable to human experts, enabling scalable clinical and research applications.

Contribution

The study introduces a novel two-step deep learning approach combining DenseNet and U-Net for fully automated CT body composition analysis, outperforming manual methods.

Findings

Dice scores between 0.95 and 0.98

Correlation coefficient R=0.99 with human readers

Feasibility of automated analysis for clinical and large-scale studies

Abstract

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.