Abstract
Body composition analysis on CT images is a valuable tool for sarcopenia assessment. We aimed to develop and validate a deep neural network applicable to whole-body CT images of PET-CT scan for the automatic volumetric segmentation of body composition. For model development, one hundred whole-body or torso 18F-fluorodeoxyglucose PET-CT scans of 100 patients were retrospectively included. Two radiologists semi-automatically labeled the following seven body components in every CT image slice, providing a total of 46,967 image slices from the 100 scans for training the 3D U-Net (training, 39,268 slices; tuning, 3116 slices; internal validation, 4583 slices): skin, bone, muscle, abdominal visceral fat, subcutaneous fat, internal organs with vessels, and central nervous system. The segmentation accuracy was assessed using reference masks from three external datasets: two Korean centers (4668 and 4796 image slices from 20 CT scans, each) and a French public dataset (3763 image slices from 24 CT scans). The 3D U-Net-driven values were clinically validated using bioelectrical impedance analysis (BIA) and by assessing the model's diagnostic performance for sarcopenia in a community-based elderly cohort (n=522). The 3D U-Net achieved accurate body composition segmentation with an average dice similarity coefficient of 96.5%-98.9% for all masks and 92.3%-99.3% for muscle, abdominal visceral fat, and subcutaneous fat in the validation datasets. The 3D U-Net-derived torso volume of skeletal muscle and fat tissue and the average area of those tissues in the waist were correlated with BIA-derived appendicular lean mass (correlation coefficients: 0.71 and 0.72, each) and fat mass (correlation coefficients: 0.95 and 0.93, each). The 3D U-Net-derived average areas of skeletal muscle and fat tissue in the waist were independently associated with sarcopenia (P<.001, each) with adjustment for age and sex, providing an area under the curve of 0.858 (95% CI, 0.815 to 0.901). This deep neural network model enabled the automatic volumetric segmentation of body composition on whole-body CT images, potentially expanding adjunctive sarcopenia assessment on PET-CT scan and volumetric assessment of metabolism in whole-body muscle and fat tissues.
Highlights
Sarcopenia is a progressive and generalized skeletal muscle disorder involving the loss of muscle volume and function [1]
A body composition analysis of a single CT image at the L3 vertebra level can estimate the amount of whole-body muscle and fat [6e8], and this method is widely used to evaluate sarcopenia and visceral obesity [9,10]
The mean age and sex distribution of the subjects in the development set and the three external validation sets for segmentation accuracy were 62.3 ± 13.3 years, 68.0 ± 10.5 years, 74.0 ± 3.7 years, and 58.5 ± 9.3 years, respectively (Table 1). Both the 2D and 3D U-Net achieved accurate body composition segmentation (Table 2 and Fig. 2), and the 3D U-Net performed significantly better than the 2D U-Net for all seven masks (Table S1)
Summary
Sarcopenia is a progressive and generalized skeletal muscle disorder involving the loss of muscle volume and function [1]. Dual-energy X-ray absorptiometry and bioelectrical impedance analysis (BIA) are typically used to assess the mass of appendicular skeletal muscle in the general population [3]. A body composition analysis of a single CT image at the L3 vertebra level can estimate the amount of whole-body muscle and fat [6e8], and this method is widely used to evaluate sarcopenia and visceral obesity [9,10]. The 3D U-Net-driven values were clinically validated using bioelectrical impedance analysis (BIA) and by assessing the model's diagnostic performance for sarcopenia in a community-based elderly cohort (n 1⁄4 522). Results: The 3D U-Net achieved accurate body composition segmentation with an average dice similarity coefficient of 96.5%e98.9% for all masks and 92.3%e99.3% for muscle, abdominal visceral fat, and subcutaneous fat in the validation datasets. The 3D U-Net-derived average areas of skeletal muscle and fat tissue in the waist were independently associated with sarcopenia (P < .001, each) with adjustment for age and sex, providing an area under the curve of 0.858 (95% CI, 0.815 to 0.901)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
