Literature DB >> 34365038

Deep neural network for automatic volumetric segmentation of whole-body CT images for body composition assessment.

Yoon Seong Lee1, Namki Hong2, Joseph Nathanael Witanto3, Ye Ra Choi4, Junghoan Park1, Pierre Decazes5, Florian Eude5, Chang Oh Kim6, Hyeon Chang Kim7, Jin Mo Goo8, Yumie Rhee9, Soon Ho Yoon10.   

Abstract

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 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).
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.
Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Entities:  

Keywords:  Body composition; Computed tomography; Deep learning; Sarcopenia; Segmentation

Mesh:

Substances:

Year:  2021        PMID: 34365038     DOI: 10.1016/j.clnu.2021.06.025

Source DB:  PubMed          Journal:  Clin Nutr        ISSN: 0261-5614            Impact factor:   7.324


  7 in total

Review 1.  [Potential of radiomics and artificial intelligence in myeloma imaging : Development of automatic, comprehensive, objective skeletal analyses from whole-body imaging data].

Authors:  Markus Wennmann; Jacob M Murray
Journal:  Radiologe       Date:  2021-12-10       Impact factor: 0.635

Review 2.  Measurement of Sarcopenia in Head and Neck Cancer Patients and Its Association With Frailty.

Authors:  Remco de Bree; Christiaan D A Meerkerk; Gyorgy B Halmos; Antti A Mäkitie; Akihiro Homma; Juan P Rodrigo; Fernando López; Robert P Takes; Jan B Vermorken; Alfio Ferlito
Journal:  Front Oncol       Date:  2022-05-12       Impact factor: 5.738

3.  Computed Tomography-Derived Skeletal Muscle Radiodensity Is an Early, Sensitive Marker of Age-Related Musculoskeletal Changes in Healthy Adults.

Authors:  Yeon Woo Jung; Namki Hong; Joon Chae Na; Woong Kyu Han; Yumie Rhee
Journal:  Endocrinol Metab (Seoul)       Date:  2021-12-13

4.  Adrenal Morphology as an Indicator of Long-Term Disease Control in Adults with Classic 21-Hydroxylase Deficiency.

Authors:  Taek Min Kim; Jung Hee Kim; Han Na Jang; Man Ho Choi; Jeong Yeon Cho; Sang Youn Kim
Journal:  Endocrinol Metab (Seoul)       Date:  2022-02-08

5.  Prognostic role of computed tomography-based, artificial intelligence-driven waist skeletal muscle volume in uterine endometrial carcinoma.

Authors:  Se Ik Kim; Joo Yeon Chung; Haerin Paik; Aeran Seol; Soon Ho Yoon; Taek Min Kim; Hee Seung Kim; Hyun Hoon Chung; Jeong Yeon Cho; Jae-Weon Kim; Maria Lee
Journal:  Insights Imaging       Date:  2021-12-20

6.  Impacts of body composition parameters and liver cirrhosis on the severity of alcoholic acute pancreatitis.

Authors:  Dong Kee Jang; Dong-Won Ahn; Kook Lae Lee; Byeong Gwan Kim; Ji Won Kim; Su Hwan Kim; Hyoun Woo Kang; Dong Seok Lee; Soon Ho Yoon; Sang Joon Park; Ji Bong Jeong
Journal:  PLoS One       Date:  2021-11-22       Impact factor: 3.240

7.  Remotely shared CT-derived presurgical understanding of lung cancer: A randomized trial.

Authors:  Soon Ho Yoon; Kwon Joong Na; Chang Hyun Kang; In Kyu Park; Samina Park; Jin Mo Goo; Young Tae Kim
Journal:  Thorac Cancer       Date:  2022-09-02       Impact factor: 3.223

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.