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{186894,
        author = {Radhika Shetty D S and Abhishekh and Krishna Kumar and Lohith P K and Madanmohan Holisagar},
        title = {Knee Osteoarthritis Classification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {2936-2943},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186894},
        abstract = {Knee Osteoarthritis (KOA) is a degenerative joint disease that affects millions worldwide and is a leading cause of pain, reduced mobility, and decreased quality of life in elderly populations. Timely diagnosis and accurate grading of KOA are essential for preventing further joint deterioration and for guiding treatment decisions. The widely used Kellgren–Lawrence (KL) grading system provides a standardized framework but suffers from high subjectivity and variability across clinicians. To address this challenge, automated diagnostic systems based on deep learning have been developed. In this paper, we propose an enhanced framework that combines DenseNet201 with a custom multi-path CNN augmented by squeeze-and-excitation and spatial attention modules. The hybrid model captures subtle differences between adjacent KOA grades, offering both improved accuracy and interpretability. Our experiments on preprocessed knee X-ray datasets confirm the robustness of the proposed method, demonstrating its potential as a clinical decision-support tool.},
        keywords = {Index Terms—Knee Osteoarthritis; Convolution neural network; classification; Knee radiograph images;},
        month = {November},
        }