Large Separable Kernel Attention–Driven Multidimensional Feature Cross-Level Fusion Classification Network of Knee Cartilage Injury: Algorithm Development and Validation
JMIR Medical Informatics · 17.12.2025 · 13 · e79748-e79748
DOI: 10.2196/79748 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift JMIR Medical Informatics, online erschienen am 17.12.2025. Verfasst von Lirong Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: The School of Digital Art and Design, Dalian Neusoft University of Information, No. 8 Software Park Road, Ganjingzi District, Dalian, Liaoning, 11602…. Hauptthemen laut MEDLINE: Knee Injuries, Algorithms, Cartilage, Articular. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Knee cartilage injury (KCI) poses significant challenges in the early clinical diagnosis process, primarily due to its high incidence, the complexity of healing, and the limited sensitivity of initial imaging modalities.
Objective
This study aims to employ magnetic resonance imaging and machine learning methods to enhance the classification accuracy of the classifier for KCI, improve the existing network structure, and demonstrate important clinical application value.
Methods
The proposed methodology is a multidimensional feature cross-level fusion classification network driven by the large separable kernel attention, which enables high-precision hierarchical diagnosis of KCI through deep learning. The network first fuses shallow high-resolution features with deep semantic features via the cross-level fusion module. Then, the large separable kernel attention module is embedded in the YOLOv8 network. This network utilizes the combined optimization of depth-separable and point-by-point convolutions to enhance features at multiple scales, thereby dramatically improving the hierarchical characterization of cartilage damage. Finally, five classifications of knee cartilage injuries are performed by classifiers.
Results
To overcome the limitations of network models trained with single-plane images, this study presents the first hospital-based multidimensional magnetic resonance imaging real dataset for KCI, on which the classification accuracy is 99.7%, the Kappa statistic is 99.6%, the F -measure is 99.7%, the sensitivity is 99.7%, and the specificity is 99.9%. The experimental results validate the feasibility of the proposed method.
Conclusions
The experimental outcomes confirm that the proposed methodology not only achieves exceptional performance in classifying knee cartilage injuries but also offers substantial improvements over existing techniques. This underscores its potential for clinical deployment in enhancing diagnostic precision and efficiency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The School of Digital Art and Design, Dalian Neusoft University of Information, No. 8 Software Park Road, Ganjingzi District, Dalian, Liaoning, 116023, China, 86 13478427287.
ORCID-Profile: Lirong Zhang, Hang Yu, Yating Yang
Zitieren
APA
Zhang, L., Yu, H., & Yang, Y. (2025). Large Separable Kernel Attention–Driven Multidimensional Feature Cross-Level Fusion Classification Network of Knee Cartilage Injury: Algorithm Development and Validation. JMIR Medical Informatics, 13, e79748-e79748. https://doi.org/10.2196/79748
Vancouver
Zhang L, Yu H, Yang Y. Large Separable Kernel Attention–Driven Multidimensional Feature Cross-Level Fusion Classification Network of Knee Cartilage Injury: Algorithm Development and Validation. JMIR Medical Informatics. 2025;13:e79748-e79748. doi:10.2196/79748
BibTeX
@article{Zhang2025,
author = {Zhang, Lirong and Yu, Hang and Yang, Yating},
title = {Large Separable Kernel Attention–Driven Multidimensional Feature Cross-Level Fusion Classification Network of Knee Cartilage Injury: Algorithm Development and Validation},
journal = {JMIR Medical Informatics},
year = {2025},
volume = {13},
pages = {e79748--e79748},
doi = {10.2196/79748}
}
EUVIMED