Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises

Abstract Stroke rehabilitation movements are significantly influenced by patient subjectivity, leading to challenges in capturing subtle differences and temporal characteristics of patient motions. Existing methods typically focus on adjacent joint movements, overlooking the intricate interdependenc...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaohui Zhang, Qiuying Han, Peng Wang, Junjie Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-12020-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332839187742720
author Shaohui Zhang
Qiuying Han
Peng Wang
Junjie Li
author_facet Shaohui Zhang
Qiuying Han
Peng Wang
Junjie Li
author_sort Shaohui Zhang
collection DOAJ
description Abstract Stroke rehabilitation movements are significantly influenced by patient subjectivity, leading to challenges in capturing subtle differences and temporal characteristics of patient motions. Existing methods typically focus on adjacent joint movements, overlooking the intricate interdependencies among body joints. Moreover, they lack the capacity to assess motion quality based on diverse temporal characteristics. To address these challenges, we propose a Frame Topology Fusion Hierarchical Graph Convolution Network (FTF-HGCN). This method aims to provide a more precise assessment of rehabilitation movement quality by effectively modeling both spatial and temporal features. First, this method combines nearby and distant keypoints to construct a fused topology structure for obtaining the enhanced motion representation. This allows the network to focus on joints with larger motion amplitudes. Second, based on the fused topology structure, a learnable topological matrix is established for each action frame to capture subtle differences between patient movements. Finally, a hierarchical temporal convolution attention module is employed to integrate motion feature information across different time sequences. Subsequently, a fully connected layer is used to output the predicted quality score of rehabilitation movements. Extensive experiments were conducted on KIMORE and UI-PRMD datasets, achieving best performance on relevant evaluation metrics (MAD: 13.4 $$\% \downarrow$$ , RMSE: 39.8 $$\% \downarrow$$ , MAPE: 7.6 $$\% \downarrow$$ ). This shows that the proposed FTF-HGCN method is capable of delivering accurate evaluations and offering superior support for the home-based rehabilitation of stroke patients.
format Article
id doaj-art-be5a99fb324b4a518dbd5ea5d88d1012
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-be5a99fb324b4a518dbd5ea5d88d10122025-08-20T03:46:05ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-12020-8Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercisesShaohui Zhang0Qiuying Han1Peng Wang2Junjie Li3School of Artificial Intelligence, Zhoukou Normal UniversitySchool of Computer Science and Technology, Zhoukou Normal UniversitySchool of Artificial Intelligence, Zhoukou Normal UniversitySchool of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical UniversityAbstract Stroke rehabilitation movements are significantly influenced by patient subjectivity, leading to challenges in capturing subtle differences and temporal characteristics of patient motions. Existing methods typically focus on adjacent joint movements, overlooking the intricate interdependencies among body joints. Moreover, they lack the capacity to assess motion quality based on diverse temporal characteristics. To address these challenges, we propose a Frame Topology Fusion Hierarchical Graph Convolution Network (FTF-HGCN). This method aims to provide a more precise assessment of rehabilitation movement quality by effectively modeling both spatial and temporal features. First, this method combines nearby and distant keypoints to construct a fused topology structure for obtaining the enhanced motion representation. This allows the network to focus on joints with larger motion amplitudes. Second, based on the fused topology structure, a learnable topological matrix is established for each action frame to capture subtle differences between patient movements. Finally, a hierarchical temporal convolution attention module is employed to integrate motion feature information across different time sequences. Subsequently, a fully connected layer is used to output the predicted quality score of rehabilitation movements. Extensive experiments were conducted on KIMORE and UI-PRMD datasets, achieving best performance on relevant evaluation metrics (MAD: 13.4 $$\% \downarrow$$ , RMSE: 39.8 $$\% \downarrow$$ , MAPE: 7.6 $$\% \downarrow$$ ). This shows that the proposed FTF-HGCN method is capable of delivering accurate evaluations and offering superior support for the home-based rehabilitation of stroke patients.https://doi.org/10.1038/s41598-025-12020-8
spellingShingle Shaohui Zhang
Qiuying Han
Peng Wang
Junjie Li
Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
Scientific Reports
title Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
title_full Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
title_fullStr Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
title_full_unstemmed Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
title_short Frame topology fusion-based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
title_sort frame topology fusion based hierarchical graph convolution for automatic assessment of physical rehabilitation exercises
url https://doi.org/10.1038/s41598-025-12020-8
work_keys_str_mv AT shaohuizhang frametopologyfusionbasedhierarchicalgraphconvolutionforautomaticassessmentofphysicalrehabilitationexercises
AT qiuyinghan frametopologyfusionbasedhierarchicalgraphconvolutionforautomaticassessmentofphysicalrehabilitationexercises
AT pengwang frametopologyfusionbasedhierarchicalgraphconvolutionforautomaticassessmentofphysicalrehabilitationexercises
AT junjieli frametopologyfusionbasedhierarchicalgraphconvolutionforautomaticassessmentofphysicalrehabilitationexercises