Deep neural network for automatic volumetric segmentation of whole-body CT images for body composition assessment.
Abdomen
/ diagnostic imaging
Aged
Body Composition
Female
Fluorodeoxyglucose F18
Humans
Intra-Abdominal Fat
/ diagnostic imaging
Male
Middle Aged
Muscle, Skeletal
/ diagnostic imaging
Neural Networks, Computer
Nutrition Assessment
Positron Emission Tomography Computed Tomography
/ methods
Radiopharmaceuticals
Republic of Korea
Retrospective Studies
Sarcopenia
/ diagnosis
Subcutaneous Fat
/ diagnostic imaging
Whole Body Imaging
/ methods
Body composition
Computed tomography
Deep learning
Sarcopenia
Segmentation
Journal
Clinical nutrition (Edinburgh, Scotland)
ISSN: 1532-1983
Titre abrégé: Clin Nutr
Pays: England
ID NLM: 8309603
Informations de publication
Date de publication:
08 2021
08 2021
Historique:
received:
23
12
2020
revised:
04
06
2021
accepted:
23
06
2021
pubmed:
9
8
2021
medline:
28
12
2021
entrez:
8
8
2021
Statut:
ppublish
Résumé
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 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.
Sections du résumé
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
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.
Identifiants
pubmed: 34365038
pii: S0261-5614(21)00321-6
doi: 10.1016/j.clnu.2021.06.025
pii:
doi:
Substances chimiques
Radiopharmaceuticals
0
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Journal Article
Multicenter Study
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
5038-5046Informations de copyright
Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.
Déclaration de conflit d'intérêts
Conflict of interest S.H.Y. joined the MEDICAL IP, Co. Ltd. as a chief medical officer since November 2020. J.N.W. is an employer and machine learning researcher of MEDICAL IP, Co. Ltd. Other authors have no conflicts of interest to declare.