Cargando…

Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets

Ultrasound (US) is widely used in the clinical diagnosis and treatment of musculoskeletal diseases. However, the low efficiency and non-uniformity of artificial recognition hinder the application and popularization of US for this purpose. Herein, we developed an automatic muscle boundary segmentatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Xin, Chen, Li, Baoxu, Wang, Dezheng, Chen, Wei, Yue, Shouwei, Meng, Dong, Qiao, Xu, Zhang, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10374344/
https://www.ncbi.nlm.nih.gov/pubmed/37520832
http://dx.doi.org/10.3389/fphys.2023.1166061
_version_ 1785078754618376192
author Xin, Chen
Li, Baoxu
Wang, Dezheng
Chen, Wei
Yue, Shouwei
Meng, Dong
Qiao, Xu
Zhang, Yang
author_facet Xin, Chen
Li, Baoxu
Wang, Dezheng
Chen, Wei
Yue, Shouwei
Meng, Dong
Qiao, Xu
Zhang, Yang
author_sort Xin, Chen
collection PubMed
description Ultrasound (US) is widely used in the clinical diagnosis and treatment of musculoskeletal diseases. However, the low efficiency and non-uniformity of artificial recognition hinder the application and popularization of US for this purpose. Herein, we developed an automatic muscle boundary segmentation tool for US image recognition and tested its accuracy and clinical applicability. Our dataset was constructed from a total of 465 US images of the flexor digitorum superficialis (FDS) from 19 participants (10 men and 9 women, age 27.4 ± 6.3 years). We used the U-net model for US image segmentation. The U-net output often includes several disconnected regions. Anatomically, the target muscle usually only has one connected region. Based on this principle, we designed an algorithm written in C++ to eliminate redundantly connected regions of outputs. The muscle boundary images generated by the tool were compared with those obtained by professionals and junior physicians to analyze their accuracy and clinical applicability. The dataset was divided into five groups for experimentation, and the average Dice coefficient, recall, and accuracy, as well as the intersection over union (IoU) of the prediction set in each group were all about 90%. Furthermore, we propose a new standard to judge the segmentation results. Under this standard, 99% of the total 150 predicted images by U-net are excellent, which is very close to the segmentation result obtained by professional doctors. In this study, we developed an automatic muscle segmentation tool for US-guided muscle injections. The accuracy of the recognition of the muscle boundary was similar to that of manual labeling by a specialist sonographer, providing a reliable auxiliary tool for clinicians to shorten the US learning cycle, reduce the clinical workload, and improve injection safety.
format Online
Article
Text
id pubmed-10374344
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103743442023-07-28 Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets Xin, Chen Li, Baoxu Wang, Dezheng Chen, Wei Yue, Shouwei Meng, Dong Qiao, Xu Zhang, Yang Front Physiol Physiology Ultrasound (US) is widely used in the clinical diagnosis and treatment of musculoskeletal diseases. However, the low efficiency and non-uniformity of artificial recognition hinder the application and popularization of US for this purpose. Herein, we developed an automatic muscle boundary segmentation tool for US image recognition and tested its accuracy and clinical applicability. Our dataset was constructed from a total of 465 US images of the flexor digitorum superficialis (FDS) from 19 participants (10 men and 9 women, age 27.4 ± 6.3 years). We used the U-net model for US image segmentation. The U-net output often includes several disconnected regions. Anatomically, the target muscle usually only has one connected region. Based on this principle, we designed an algorithm written in C++ to eliminate redundantly connected regions of outputs. The muscle boundary images generated by the tool were compared with those obtained by professionals and junior physicians to analyze their accuracy and clinical applicability. The dataset was divided into five groups for experimentation, and the average Dice coefficient, recall, and accuracy, as well as the intersection over union (IoU) of the prediction set in each group were all about 90%. Furthermore, we propose a new standard to judge the segmentation results. Under this standard, 99% of the total 150 predicted images by U-net are excellent, which is very close to the segmentation result obtained by professional doctors. In this study, we developed an automatic muscle segmentation tool for US-guided muscle injections. The accuracy of the recognition of the muscle boundary was similar to that of manual labeling by a specialist sonographer, providing a reliable auxiliary tool for clinicians to shorten the US learning cycle, reduce the clinical workload, and improve injection safety. Frontiers Media S.A. 2023-07-13 /pmc/articles/PMC10374344/ /pubmed/37520832 http://dx.doi.org/10.3389/fphys.2023.1166061 Text en Copyright © 2023 Xin, Li, Wang, Chen, Yue, Meng, Qiao and Zhang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Physiology
Xin, Chen
Li, Baoxu
Wang, Dezheng
Chen, Wei
Yue, Shouwei
Meng, Dong
Qiao, Xu
Zhang, Yang
Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title_full Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title_fullStr Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title_full_unstemmed Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title_short Deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
title_sort deep learning for the rapid automatic segmentation of forearm muscle boundaries from ultrasound datasets
topic Physiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10374344/
https://www.ncbi.nlm.nih.gov/pubmed/37520832
http://dx.doi.org/10.3389/fphys.2023.1166061
work_keys_str_mv AT xinchen deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT libaoxu deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT wangdezheng deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT chenwei deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT yueshouwei deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT mengdong deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT qiaoxu deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets
AT zhangyang deeplearningfortherapidautomaticsegmentationofforearmmuscleboundariesfromultrasounddatasets