A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries

The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tea...

Full description

Saved in:
Bibliographic Details
Main Authors: Biyong Deng, Jiashan Pan, Xiaoyu Tang, Haitao Fu, Shushan Hu
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-01-01
Series:Cognitive Robotics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667241325000138
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267990420881408
author Biyong Deng
Jiashan Pan
Xiaoyu Tang
Haitao Fu
Shushan Hu
author_facet Biyong Deng
Jiashan Pan
Xiaoyu Tang
Haitao Fu
Shushan Hu
author_sort Biyong Deng
collection DOAJ
description The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tears, due to its efficiency and accuracy in medical imaging. However, the interpretation and understanding of knee MRI images are time-consuming, laborious, require sufficient expertise, and are also prone to diagnostic errors. Thus, it is imperative to devise a computational method employing knee MRI for intelligent diagnosis of knee injuries, as this could expedite medical assessments by physicians, reduce costs, and substantially reduce the risk of misdiagnosis. Although several computational methods have been proposed to diagnose knee injuries, most rely heavily on local features in MRI images and exhibit low prediction accuracy. In this paper, we proposed a novel multi-view graph neural network, abbreviated as MVGNN, to identify knee injuries (specifically ACL tears and meniscal tears) by leveraging graph representations derived from multiple MRI views. Comprehensive experiments demonstrate that MVGNN achieves state-of-the-art results for diagnosing knee injuries, with a 5.9% improvement in accuracy on ACL data and a 6.5% improvement on Men data, compared to the second-best method, MVCNN.
format Article
id doaj-art-e10fa8cd05e94e40958305e22ce11a9f
institution OA Journals
issn 2667-2413
language English
publishDate 2025-01-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Cognitive Robotics
spelling doaj-art-e10fa8cd05e94e40958305e22ce11a9f2025-08-20T01:53:34ZengKeAi Communications Co. Ltd.Cognitive Robotics2667-24132025-01-01520121010.1016/j.cogr.2025.05.001A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuriesBiyong Deng0Jiashan Pan1Xiaoyu Tang2Haitao Fu3Shushan Hu4School of Artificial Intelligence, Hubei University, Wuhan, 430062, China; Department of Orthopedic Surgery, Beijing Jishuitan Hospital Guizhou Hospital, Guiyang, 550014, ChinaSchool of Artificial Intelligence, Hubei University, Wuhan, 430062, ChinaSchool of Artificial Intelligence, Hubei University, Wuhan, 430062, ChinaCorresponding authors.; School of Artificial Intelligence, Hubei University, Wuhan, 430062, China; Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education, Wuhan, 430062, ChinaCorresponding authors.; School of Artificial Intelligence, Hubei University, Wuhan, 430062, ChinaThe knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tears, due to its efficiency and accuracy in medical imaging. However, the interpretation and understanding of knee MRI images are time-consuming, laborious, require sufficient expertise, and are also prone to diagnostic errors. Thus, it is imperative to devise a computational method employing knee MRI for intelligent diagnosis of knee injuries, as this could expedite medical assessments by physicians, reduce costs, and substantially reduce the risk of misdiagnosis. Although several computational methods have been proposed to diagnose knee injuries, most rely heavily on local features in MRI images and exhibit low prediction accuracy. In this paper, we proposed a novel multi-view graph neural network, abbreviated as MVGNN, to identify knee injuries (specifically ACL tears and meniscal tears) by leveraging graph representations derived from multiple MRI views. Comprehensive experiments demonstrate that MVGNN achieves state-of-the-art results for diagnosing knee injuries, with a 5.9% improvement in accuracy on ACL data and a 6.5% improvement on Men data, compared to the second-best method, MVCNN.http://www.sciencedirect.com/science/article/pii/S2667241325000138Meniscal tearKneeDeep learningGraph neural networkMagnetic resonance imaging
spellingShingle Biyong Deng
Jiashan Pan
Xiaoyu Tang
Haitao Fu
Shushan Hu
A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
Cognitive Robotics
Meniscal tear
Knee
Deep learning
Graph neural network
Magnetic resonance imaging
title A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
title_full A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
title_fullStr A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
title_full_unstemmed A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
title_short A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries
title_sort multi view graph neural network approach for magnetic resonance imaging based diagnosis of knee injuries
topic Meniscal tear
Knee
Deep learning
Graph neural network
Magnetic resonance imaging
url http://www.sciencedirect.com/science/article/pii/S2667241325000138
work_keys_str_mv AT biyongdeng amultiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT jiashanpan amultiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT xiaoyutang amultiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT haitaofu amultiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT shushanhu amultiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT biyongdeng multiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT jiashanpan multiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT xiaoyutang multiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT haitaofu multiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries
AT shushanhu multiviewgraphneuralnetworkapproachformagneticresonanceimagingbaseddiagnosisofkneeinjuries