Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort

Sarcopenia is characterized by a degeneration of muscle mass and strength that incurs impaired mobility, posing grievous impacts on the quality of life and well-being of older adults worldwide. In 2018, a new international consensus was formulated to incorporate ultrasound imaging of the rectus femo...

Full description

Saved in:
Bibliographic Details
Main Authors: Dawei Zhang, Hongyu Kang, Yu Sun, Justina Yat Wa Liu, Ka-Shing Lee, Zhen Song, Jien Vei Khaw, Jackie Yeung, Tao Peng, Sai-kit Lam, Yongping Zheng
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/12/1291
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105790470946816
author Dawei Zhang
Hongyu Kang
Yu Sun
Justina Yat Wa Liu
Ka-Shing Lee
Zhen Song
Jien Vei Khaw
Jackie Yeung
Tao Peng
Sai-kit Lam
Yongping Zheng
author_facet Dawei Zhang
Hongyu Kang
Yu Sun
Justina Yat Wa Liu
Ka-Shing Lee
Zhen Song
Jien Vei Khaw
Jackie Yeung
Tao Peng
Sai-kit Lam
Yongping Zheng
author_sort Dawei Zhang
collection DOAJ
description Sarcopenia is characterized by a degeneration of muscle mass and strength that incurs impaired mobility, posing grievous impacts on the quality of life and well-being of older adults worldwide. In 2018, a new international consensus was formulated to incorporate ultrasound imaging of the rectus femoris (RF) muscle for early sarcopenia assessment. Nonetheless, current clinical RF muscle identification and delineation procedures are manual, subjective, inaccurate, and challenging. Thus, developing an effective AI-empowered RF segmentation model to streamline downstream sarcopenia assessment is highly desirable. Yet, this area of research readily goes unnoticed compared to other disciplines, and relevant research is desperately wanted, especially in comparison among traditional, classic, and cutting-edge segmentation networks. This study evaluated an emerging Automatic Segment Anything Model (AutoSAM) compared to the U-Net and nnU-Net models for RF segmentation on ultrasound images. We prospectively analyzed ultrasound images of 257 older adults (aged > 65) in a community setting from Hong Kong’s District Elderly Community Centers. Three models were developed on a training set (<i>n</i> = 219) and independently evaluated on a testing set (<i>n</i> = 38) in aspects of DICE, Intersection-over-Union, Hausdorff Distance (HD), accuracy, precision, recall, as well as stability. The results indicated that the AutoSAM achieved the best segmentation agreement in all the evaluating metrics, consistently outperforming the U-Net and nnU-Net models. The results offered an effective state-of-the-art RF muscle segmentation tool for sarcopenia assessment in the future.
format Article
id doaj-art-bf2bae40c2df4ad69dd73ebf34a61f13
institution Kabale University
issn 2306-5354
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-bf2bae40c2df4ad69dd73ebf34a61f132024-12-27T14:11:45ZengMDPI AGBioengineering2306-53542024-12-011112129110.3390/bioengineering11121291Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community CohortDawei Zhang0Hongyu Kang1Yu Sun2Justina Yat Wa Liu3Ka-Shing Lee4Zhen Song5Jien Vei Khaw6Jackie Yeung7Tao Peng8Sai-kit Lam9Yongping Zheng10Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaSchool of Nursing, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaSchool of Nursing, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaSchool of Future Science and Engineering, Soochow University, Suzhou 215222, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaDepartment of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, ChinaSarcopenia is characterized by a degeneration of muscle mass and strength that incurs impaired mobility, posing grievous impacts on the quality of life and well-being of older adults worldwide. In 2018, a new international consensus was formulated to incorporate ultrasound imaging of the rectus femoris (RF) muscle for early sarcopenia assessment. Nonetheless, current clinical RF muscle identification and delineation procedures are manual, subjective, inaccurate, and challenging. Thus, developing an effective AI-empowered RF segmentation model to streamline downstream sarcopenia assessment is highly desirable. Yet, this area of research readily goes unnoticed compared to other disciplines, and relevant research is desperately wanted, especially in comparison among traditional, classic, and cutting-edge segmentation networks. This study evaluated an emerging Automatic Segment Anything Model (AutoSAM) compared to the U-Net and nnU-Net models for RF segmentation on ultrasound images. We prospectively analyzed ultrasound images of 257 older adults (aged > 65) in a community setting from Hong Kong’s District Elderly Community Centers. Three models were developed on a training set (<i>n</i> = 219) and independently evaluated on a testing set (<i>n</i> = 38) in aspects of DICE, Intersection-over-Union, Hausdorff Distance (HD), accuracy, precision, recall, as well as stability. The results indicated that the AutoSAM achieved the best segmentation agreement in all the evaluating metrics, consistently outperforming the U-Net and nnU-Net models. The results offered an effective state-of-the-art RF muscle segmentation tool for sarcopenia assessment in the future.https://www.mdpi.com/2306-5354/11/12/1291deep learningmedical segment anything modelrectus femoris muscleSarcopenia UltrasoundU-Net
spellingShingle Dawei Zhang
Hongyu Kang
Yu Sun
Justina Yat Wa Liu
Ka-Shing Lee
Zhen Song
Jien Vei Khaw
Jackie Yeung
Tao Peng
Sai-kit Lam
Yongping Zheng
Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
Bioengineering
deep learning
medical segment anything model
rectus femoris muscle
Sarcopenia Ultrasound
U-Net
title Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
title_full Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
title_fullStr Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
title_full_unstemmed Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
title_short Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort
title_sort rectus femoris muscle segmentation on ultrasound images of older adults using automatic segment anything model nnu net and u net a prospective study of hong kong community cohort
topic deep learning
medical segment anything model
rectus femoris muscle
Sarcopenia Ultrasound
U-Net
url https://www.mdpi.com/2306-5354/11/12/1291
work_keys_str_mv AT daweizhang rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT hongyukang rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT yusun rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT justinayatwaliu rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT kashinglee rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT zhensong rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT jienveikhaw rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT jackieyeung rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT taopeng rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT saikitlam rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort
AT yongpingzheng rectusfemorismusclesegmentationonultrasoundimagesofolderadultsusingautomaticsegmentanythingmodelnnunetandunetaprospectivestudyofhongkongcommunitycohort