IMPROVING KNEE OSTEOARTHRITIS CLASSIFICATION USING CNNS ON IMBALANCED DATA
Main Article Content
Abstract
This study investigates the effectiveness of convolutional neural networks (CNNs) for classifying knee osteoarthritis severity from X-ray images under class-imbalanced conditions. Transfer learning is applied to several representative CNNs, including VGG16, ResNet50, and EfficientNet-B0, using the public Osteoarthritis Initiative (OAI) dataset. To address class imbalance, a class-weighted training strategy is incorporated to improve recognition of moderate and severe osteoarthritis cases. Experimental results demonstrate that imbalance handling significantly enhances classification performance. These findings highlight the potential of CNN-based approaches for supporting clinical assessment of knee osteoarthritis severity.
Keywords
CNN, Knee Osteoarthritis, imbalanced data.
Article Details
References
[2] M. Fransen, S. McConnell, A. R. Harmer, M. Van der Esch, M. Simic, and K. L. Bennell (2015), “Exercise for osteoarthritis of the knee: a Cochrane systematic review,” Br. J. Sports Med., vol. 49, no. 24, pp. 1554–1557.
[3] D. T. Felson, A. Naimark, J. Anderson, L. Kazis, W. Castelli, and R. F. Meenan (1987), “The prevalence of knee osteoarthritis in the elderly. The Framingham Osteoarthritis Study,” Arthritis Rheum. Off. J. Am. Coll. Rheumatol., vol. 30, no. 8, pp. 914–918.
[4] G. Jones, C. Ding, F. Scott, M. Glisson, and F. Cicuttini (2004), “Early radiographic osteoarthritis is associated with substantial changes in cartilage volume and tibial bone surface area in both males and females,” Osteoarthritis Cartilage, vol. 12, no. 2, pp. 169–174.
[5] D. Bhatia, T. Bejarano, and M. Novo (2013), “Current interventions in the management of knee osteoarthritis,” J. Pharm. Bioallied Sci., vol. 5, no. 1, pp. 30–38.
[6] S. Rani et al. (2024), “Deep learning to combat knee osteoarthritis and severity assessment by using CNN-based classification,” BMC Musculoskelet. Disord., vol. 25, no. 1, p. 817.
[7] S. Iqbal, D. Ali, S. Rafique, K. Bagga, A. U. Rahman, and S. Khan (2025), “Comparative Analysis of Automated Knee Osteoarthritis Severity Classification from X-Ray Images Using CNNs and VGG16 Architecture,” ICCK Trans. Sens. Commun. Control, vol. 2, no. 1, pp. 36–47.
[8] J. H. Kellgren and J. Lawrence (1957), “Radiological assessment of osteo-arthrosis,” Ann Rheum Dis, vol. 16, no. 4, pp. 494–502.
[9] A. S. Mohammed, A. A. Hasanaath, G. Latif, and A. Bashar (2023), “Knee osteoarthritis detection and severity classification using residual neural networks on preprocessed x-ray images,” Diagnostics, vol. 13, no. 8, p. 1380.
[10] A. Rachmad, F. Sonata, J. Hutagalung, D. Hapsari, M. Fuad, and E. M. Sari Rochman (2023), “An Automated System for Osteoarthritis Severity Scoring Using Residual Neural Networks.,” Math. Model. Eng. Probl., vol. 10, no. 5.
[11] T. Tariq, Z. Suhail, and Z. Nawaz (2023), “Knee osteoarthritis detection and classification using x-rays,” IEEE Access, vol. 11, pp. 48292–48303.
[12] Y. Wang, X. Wang, T. Gao, L. Du, and W. Liu (2021), “An automatic knee osteoarthritis diagnosis method based on deep learning: data from the osteoarthritis initiative,” J. Healthc. Eng., vol. 2021, no. 1, p. 5586529.
[13] P. S. Q. Yeoh et al. (2021), “Emergence of deep learning in knee osteoarthritis diagnosis,” Comput. Intell. Neurosci., vol. 2021, no. 1, p. 4931437.
[14] J. Byrd and Z. Lipton (2019), “What is the effect of importance weighting in deep learning?,” in International conference on machine learning, pp. 872–881.
[15] J. M. Johnson and T. M. Khoshgoftaar (2019), “Survey on deep learning with class imbalance,” J. Big Data, vol. 6, no. 1, p. 27.
[16] K. Simonyan and A. Zisserman (2014), “Very deep convolutional networks for large-scale image recognition,” ArXiv Prepr. ArXiv14091556.
[17] K. He, X. Zhang, S. Ren, and J. Sun (2016), “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778.
[18] M. Tan and Q. Le (2019), “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International conference on machine learning, pp. 6105–6114.