Deep neural network for automatic volumetric segmentation of whole-body CT images for body composition assessment. Issue 8 (August 2021)

• Record Type: Journal Article
• Authors: Lee, Yoon Seong; Hong, Namki; Witanto, Joseph Nathanael; Choi, Ye Ra; Park, Junghoan; Decazes, Pierre; Eude, Florian; Kim, Chang Oh; Chang Kim, Hyeon; Goo, Jin Mo; Rhee, Yumie; Yoon, Soon Ho
• Is Part Of: Clinical nutrition. Volume 40:Issue 8(2021)
• Page Start: 5038
• Page End: 5046
• Publication Date: 2021-08
• Subjects: Sarcopenia -- Computed tomography -- Deep learning -- Segmentation -- Body composition; BIA bioelectrical impedance analysis -- KURE Korean Urban Rural Elderly -- AVF abdominal visceral fat -- SF subcutaneous fat -- IO internal organs and vessels -- CNS central nervous system -- DSC dice similarity coefficient -- PPV positive predictive value -- BMI body mass index -- SMA skeletal muscle area -- BFA body fat area -- SMI skeletal muscle index -- BFI body fat index -- AUROC area under the receiver operating characteristic curve; Critically ill -- Nutrition -- Periodicals; Diet therapy -- Periodicals; Parenteral feeding -- Periodicals; Enteral feeding -- Periodicals; Enteral Nutrition -- Periodicals; Parenteral Nutrition -- Periodicals; Metabolism -- Periodicals; Diétothérapie -- Périodiques; Alimentation parentérale -- Périodiques; Alimentation entérale -- Périodiques; Nutrition -- Périodiques; Diet therapy; Enteral feeding; Nutrition; Parenteral feeding; Electronic journals; Periodicals; Electronic journals; 615.854
• DOI: 10.1016/j.clnu.2021.06.025
• Languages: English
• ISSNs: 0261-5614

Abstract

Summary: Background & aims: 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. Methods: For model development, one hundred whole-body or torso 18 F-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). Results: 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). Conclusions: 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.