Artificial Intelligence in the Evaluation of Body Composition

Abstract

Body composition entails the measurement of muscle and fat mass in the body and has been shown to impact clinical outcomes in various aspects of human health. As a result, the need is growing for reliable and efficient noninvasive tools to measure body composition. Traditional methods of estimating body composition, anthropomorphic measurements, dual-energy X-ray absorptiometry, and bioelectrical impedance, are limited in their application. Cross-sectional imaging remains the reference standard for body composition analysis and is accomplished through segmentation of computed tomography and magnetic resonance imaging studies. However, manual segmentation of images by an expert reader is labor intensive and time consuming, limiting its implementation in large-scale studies and in routine clinical practice. In this review, novel methods to automate the process of body composition measurement are discussed including the application of artificial intelligence and deep learning to tissue segmentation.

Artificial intelligence‐based analysis of body composition in Marfan: skeletal muscle density and psoas muscle index predict aortic enlargement

“…As manual segmentation of CT datasets is time consuming, earlier studies investigating body composition analysis have often been performed in small patient populations. Artificial intelligence‐based automated tissue segmentation can dramatically decrease post‐processing time of these datasets 20 …”

AI MSK clinical applications: spine imaging

“…However, this task is tedious and trivial to the educated radiologist reader. In order to streamline segmentation processes and subsequent strategies of quantitative image analysis (such as TA), much effort has recently been invested in developing automatic segmentation algorithms, with variable success [39,40].…”

Applications of Artificial Intelligence in Musculoskeletal Imaging: From the Request to the Report

“…For example, increased visceral fat is associated with impaired glucose and lipid metabolism with increased cardiometabolic risk and all-cause mortality, decreased bone mineral density, nonalcoholic fatty liver disease, and increased risk for neoplasm. 30 Decreased muscle mass or sarcopenia is linked to poorer prognosis in intensive care unit patients, soft tissue sarcoma recurrence, as well as increased mortality post liver transplant, after colorectal surgery, and in hepatocellular carcinoma. 30 Various methods exist to measure the different tissue types in the human body.…”

“…30 Decreased muscle mass or sarcopenia is linked to poorer prognosis in intensive care unit patients, soft tissue sarcoma recurrence, as well as increased mortality post liver transplant, after colorectal surgery, and in hepatocellular carcinoma. 30 Various methods exist to measure the different tissue types in the human body. Conventional approaches include anthropomorphic measures, bioelectrical impedance analysis, and dual-energy X-ray absorptiometry.…”

“…Conventional approaches include anthropomorphic measures, bioelectrical impedance analysis, and dual-energy X-ray absorptiometry. 30 The quantitative assessment of body composition may be obtained from segmentation of cross-sectional images, including computed tomography and MRI examinations. Manual segmentation is tedious and impractical in the clinical setting.…”