Abstract :

Knee Osteoarthritis (OA) Is A Progressive Joint Disorder That Leads To Cartilage Degradation, Causing Pain And Reduced Mobility. Early Detection And Accurate Classification Of OA Severity Using Radiographic Images Are Crucial For Timely Intervention And Treatment Planning. In This Study, We Develop A Deep Learningbased Approach For Automatic Classification Of Knee OA Severity From X-ray Images Using The Kellgren Lawrence (KL) Grading System. We Proposed Preprocessing X-ray Images Through Contrast Enhancement, Bone Segmentation, And Data Augmentation To Improve Model Robustness. Convolutional Neural Networks (CNNs) Such As ResNet50, Efficient Net, And Vision Transformers (ViT) For Feature Extraction And Multi-class Classification. To Address Class Imbalance, We Implement Focal Loss And Weighted Sampling Strategies. The Model Is Trained And Evaluated Using Publicly Available Datasets Such As The Osteoarthritis Initiative (OAI) And KneeKL Dataset, Achieving High Accuracy And A Strong Agreement With Clinical Assessments, As Measured By The Quadratic Weighted Kappa (QWK) Score. Keywords: Knee Osteoarthritis, Deep Learning, X-ray Classification, Convolutional Neural Networks, Vision Transformers, Medical Imaging.

Published:

29-6-2025

Issue:

Vol. 25 No. 6 (2025)

Page Nos:

970-978

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite