Cargando…

A deep learning method for foot-type classification using plantar pressure images

Background: Flat foot deformity is a prevalent and challenging condition often leading to various clinical complications. Accurate identification of abnormal foot types is essential for appropriate interventions. Method: A dataset consisting of 1573 plantar pressure images from 125 individuals was c...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Yangyang, Zhou, Jiali, Qiu, Fei, Liao, Xuying, Jiang, Jianhua, Chen, Heqing, Lin, Xiaomei, Hu, Yiqun, He, Jianquan, Chen, Jian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10519788/
https://www.ncbi.nlm.nih.gov/pubmed/37767108
http://dx.doi.org/10.3389/fbioe.2023.1239246
_version_ 1785109769970778112
author Zhao, Yangyang
Zhou, Jiali
Qiu, Fei
Liao, Xuying
Jiang, Jianhua
Chen, Heqing
Lin, Xiaomei
Hu, Yiqun
He, Jianquan
Chen, Jian
author_facet Zhao, Yangyang
Zhou, Jiali
Qiu, Fei
Liao, Xuying
Jiang, Jianhua
Chen, Heqing
Lin, Xiaomei
Hu, Yiqun
He, Jianquan
Chen, Jian
author_sort Zhao, Yangyang
collection PubMed
description Background: Flat foot deformity is a prevalent and challenging condition often leading to various clinical complications. Accurate identification of abnormal foot types is essential for appropriate interventions. Method: A dataset consisting of 1573 plantar pressure images from 125 individuals was collected. The performance of the You Only Look Once v5 (YOLO-v5) model, improved YOLO-v5 model, and multi-label classification model was evaluated for foot type identification using the collected images. A new dataset was also collected to verify and compare the models. Results: The multi-label classification algorithm based on ResNet-50 outperformed other algorithms. The improved YOLO-v5 model with Squeeze-and-Excitation (SE), the improved YOLO-v5 model with Convolutional Block Attention Module (CBAM), and the multilabel classification model based on ResNet-50 achieved an accuracy of 0.652, 0.717, and 0.826, respectively, which is significantly higher than those obtained using the ordinary plantar-pressure system and the standard YOLO-v5 model. Conclusion: These results indicate that the proposed DL-based multilabel classification model based on ResNet-50 is superior in flat foot type detection and can be used to evaluate the clinical rehabilitation status of patients with abnormal foot types and various foot pathologies when more data on patients with various diseases are available for training.
format Online
Article
Text
id pubmed-10519788
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-105197882023-09-27 A deep learning method for foot-type classification using plantar pressure images Zhao, Yangyang Zhou, Jiali Qiu, Fei Liao, Xuying Jiang, Jianhua Chen, Heqing Lin, Xiaomei Hu, Yiqun He, Jianquan Chen, Jian Front Bioeng Biotechnol Bioengineering and Biotechnology Background: Flat foot deformity is a prevalent and challenging condition often leading to various clinical complications. Accurate identification of abnormal foot types is essential for appropriate interventions. Method: A dataset consisting of 1573 plantar pressure images from 125 individuals was collected. The performance of the You Only Look Once v5 (YOLO-v5) model, improved YOLO-v5 model, and multi-label classification model was evaluated for foot type identification using the collected images. A new dataset was also collected to verify and compare the models. Results: The multi-label classification algorithm based on ResNet-50 outperformed other algorithms. The improved YOLO-v5 model with Squeeze-and-Excitation (SE), the improved YOLO-v5 model with Convolutional Block Attention Module (CBAM), and the multilabel classification model based on ResNet-50 achieved an accuracy of 0.652, 0.717, and 0.826, respectively, which is significantly higher than those obtained using the ordinary plantar-pressure system and the standard YOLO-v5 model. Conclusion: These results indicate that the proposed DL-based multilabel classification model based on ResNet-50 is superior in flat foot type detection and can be used to evaluate the clinical rehabilitation status of patients with abnormal foot types and various foot pathologies when more data on patients with various diseases are available for training. Frontiers Media S.A. 2023-09-11 /pmc/articles/PMC10519788/ /pubmed/37767108 http://dx.doi.org/10.3389/fbioe.2023.1239246 Text en Copyright © 2023 Zhao, Zhou, Qiu, Liao, Jiang, Chen, Lin, Hu, He and Chen. 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 Bioengineering and Biotechnology
Zhao, Yangyang
Zhou, Jiali
Qiu, Fei
Liao, Xuying
Jiang, Jianhua
Chen, Heqing
Lin, Xiaomei
Hu, Yiqun
He, Jianquan
Chen, Jian
A deep learning method for foot-type classification using plantar pressure images
title A deep learning method for foot-type classification using plantar pressure images
title_full A deep learning method for foot-type classification using plantar pressure images
title_fullStr A deep learning method for foot-type classification using plantar pressure images
title_full_unstemmed A deep learning method for foot-type classification using plantar pressure images
title_short A deep learning method for foot-type classification using plantar pressure images
title_sort deep learning method for foot-type classification using plantar pressure images
topic Bioengineering and Biotechnology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10519788/
https://www.ncbi.nlm.nih.gov/pubmed/37767108
http://dx.doi.org/10.3389/fbioe.2023.1239246
work_keys_str_mv AT zhaoyangyang adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT zhoujiali adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT qiufei adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT liaoxuying adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT jiangjianhua adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT chenheqing adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT linxiaomei adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT huyiqun adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT hejianquan adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT chenjian adeeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT zhaoyangyang deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT zhoujiali deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT qiufei deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT liaoxuying deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT jiangjianhua deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT chenheqing deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT linxiaomei deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT huyiqun deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT hejianquan deeplearningmethodforfoottypeclassificationusingplantarpressureimages
AT chenjian deeplearningmethodforfoottypeclassificationusingplantarpressureimages