Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175011,
        author = {J. Mahathi and K. Aryasri Reddy and T. Surya Sangeeth Chandra and CH. Joshi Paul and Dr. G. Aparna},
        title = {Deep Learning For Knee Osteoarthritis Severity Classification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {2574-2579},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175011},
        abstract = {Knee osteoarthritis (KOA) is a degenerative joint disease that affects mobility and quality of life. Early and accurate severity classification is essential for effective treatment planning. In this study, a deep learning-based approach is used to classify KOA severity using the EfficientNet-B3 model. The model analyzes primary characteristics of knee joint images to distinguish between different severity levels. A Convolutional Neural Network (CNN) with Rectified Linear Units (ReLU) is employed to extract meaningful features and improve classification performance. The proposed method was evaluated on standard datasets, including the Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST). Experimental results demonstrate that the EfficientNet-B3 model achieves an accuracy of 88%, providing a reliable and efficient solution for automated KOA severity classification. This approach enhances the potential for real-time implementation in computer-aided diagnosis (CAD) systems.},
        keywords = {Knee Osteoarthritis (KOA), Deep Learning, EfficientNet-B3, Convolutional Neural Network (CNN), Rectified Linear Unit (ReLU), Computer-Aided Diagnosis (CAD), Medical Image Analysis.},
        month = {April},
        }