TRANSFER LEARNING‐BASED CLASSIFICATION OF KNEE OSTEOARTHRITIS SEVERITY FROM X-RAY IMAGES

Öz

Knee osteoarthritis (KOA) a degenerative, long-term joint condition that, more often than not, affects the elderly and is characterized by articular cartilage degradation. Appropriate treatment and early analysis are essential for sickness control. However, traditional diagnostic methods for classifying KOA from X-ray images require laborious expertise and, unfortunately, have a large margin of error. This study presents an image processing-based solution for multi-classification KOA severity from X-ray images using the Bilateral filter, contrast-limited adaptive histogram equalization (CLAHE), and transfer learning models. The CLAHE method improved image quality, while the Bilateral filter enhanced details and minimized blurriness in X-ray images. KOA image dataset consists of 9786 knee images and five class labels. The performances of transfer learning models including AlexNet, ResNet101, DenseNet201, and VGG19 were compared. The ResNet101 model emerged as the most effective, achieving a kappa statistic of 0.970, weighted F1-score of 0.978, and an overall accuracy of 97.85%. This model’s high accuracy and precision make it a dependable and objective diagnostic solution.

Anahtar Kelimeler

• Deep Learning
• Image Processing
• Transfer Learning
• ResNet101
• Knee Osteoarthritis.

DIZ OSTEOARTRITI ŞIDDETININ X-RAY GÖRÜNTÜLERINDEN TRANSFER ÖĞRENME TABANLI SINIFLANDIRILMASI

Öz

Diz osteoartriti (KOA), çoğunlukla yaşlıları etkileyen ve eklem kıkırdağı bozulmasıyla karakterize dejeneratif, uzun vadeli bir eklem durumudur. Hastalık kontrolü için uygun tedavi ve erken analiz kritiktir. Bununla birlikte, X-ray görüntülerinden KOA sınıflandırması için geleneksel tanı yöntemleri uzmanlık gerektirmektedir, yorucudur ve maalesef büyük bir hata payına sahiptir. Bu çalışma, Bilateral filtresi, kontrast sınırlı adaptif histogram eşitleme (CLAHE) ve transfer öğrenme modelleri kullanarak X-ray görüntülerinden KOA şiddetini sınıflandırmak için görüntü işleme tabanlı bir çözüm sunmaktadır. CLAHE yöntemi görüntü kalitesini iyileştirirken, Bilateral filtresi X-ray görüntülerindeki ayrıntıları iyileştirerek bulanıklığı en aza indirmiştir. KOA görüntü veri seti 9786 diz görüntüsü ve beş sınıf etiketinden oluşmaktadır. AlexNet, ResNet101, DenseNet201 ve VGG19 dahil olmak üzere transfer öğrenme modellerinin performansları karşılaştırıldı. ResNet101 modeli 0,970 kappa istatistiği, 0,978 ağırlıklı F1-skoru ve %97,85 genel doğruluk elde ederek en etkili model olarak ortaya çıkmıştır. Bu modelin yüksek doğruluğu ve kesinliği onu güvenilir ve objektif bir tanı çözümü olduğunu göstermektedir.

Anahtar Kelimeler

• Derin Öğrenme
• Görüntü İşleme
• Transfer Öğrenme
• ResNet101
• Diz Osteoartriti

Kaynakça

1. Abedin, J., Antony, J., McGuinness, K., Moran, K., O’Connor, N. E., Rebholz-Schuhmann, D., & Newell, J. 2019. Predicting knee osteoarthritis severity: comparative modeling based on patient’s data and plain X-ray images. Scientific Reports, 9(1), 5761.
2. Ahmed, H. A., & Mohammed, E. A. (2022). Detection and classification of the osteoarthritis in knee joint using transfer learning with convolutional neural networks (CNNs). Iraqi Journal of Science, 5058-5071.
3. Alshamrani, H. A., Rashid, M., Alshamrani, S. S., & Alshehri, A. H. (2023). Osteo-net: An automated system for predicting knee osteoarthritis from x-ray images using transfer-learning-based neural networks approach. Healthcare. 11 (9), 1-30.
4. Brahim, A., Jennane, R., Riad, R., Janvier, T., Khedher, L., Toumi, H., & Lespessailles, E. 2019. A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative. Computerized Medical Imaging and Graphics, 73, 11-18.
5. Cantor, A. B. (1996). Sample-size calculations for Cohen's kappa. Psychological Methods, 1(2), 150-151. doi: 10.1037/1082-989X.1.2.150
6. Çelik, Y., Dengiz, B., & Güney, S. (2023). Ahşap ham maddelerde yüzey hatasını belirlemek için görüntü işleme tabanlı kalite kontrol sistemi. Mühendislik Bilimleri ve Tasarım Dergisi, 11(4), 1365-1382.
7. Geng, R., Li, J., Yu, C., Zhang, C., Chen, F., Chen, J., Haonan, N., Wang, J., Kang, K., Wei, Z., Xu, Y., & Jin, T. (2023). Knee osteoarthritis: Current status and research progress in treatment. Experimental and therapeutic medicine, 26(4), 1-11.
8. Goswami, A. D. (2023). Automatic classification of the severity of knee osteoarthritis using enhanced image sharpening and CNN. Applied Sciences, 13(3), 1658.

9. Göker, H. (2024). Detection of cervical cancer from uterine cervix images using transfer learning architectures. Eskişehir Technical University Journal of Science and Technology A-Applied Sciences and Engineering, 25(2), 222-239.
10. Guan, B., Liu, F., Mizaian, A. H., Demehri, S., Samsonov, A., Guermazi, A., & Kijowski, R. (2022). Deep learning approach to predict pain progression in knee osteoarthritis. Skeletal Radiology, 1-11.
11. Islam, M. S., & Rony, M. A. T. (2024). CDK: A novel high-performance transfer feature technique for early detection of osteoarthritis. Journal of Pathology Informatics, 15, 100382.
12. Jain, R. K., Sharma, P. K., Gaj, S., Sur, A., & Ghosh, P. 2024. Knee osteoarthritis severity prediction using an attentive multi-scale deep convolutional neural network. Multimedia Tools and Applications, 83(3), 6925-6942.
13. Jung, J., Han, J., Han, J. M., Ko, J., Yoon, J., Hwang, J. S., Park, J. I., Hwang, G., Jung, J. H. & Hwang, D. D. J. (2024). Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network. Scientific Reports, 14(1), 5854. 1-12.
14. Karim, A. M., Kaya, H., Alcan, V., Sen, B., & Hadimlioglu, I. A. (2022). New optimized deep learning application for COVID-19 detection in chest X-ray images. Symmetry. 14 (5): 1003.
15. Karlik, B., & Olgac, A. V. (2011). Performance analysis of various activation functions in generalized MLP architectures of neural networks. International Journal of Artificial Intelligence and Expert Systems, 1(4), 111-122.
16. Khattar, A., & Quadri, S. M. K. (2022). Generalization of convolutional network to domain adaptation network for classification of disaster images on twitter. Multimedia Tools and Applications, 81(21), 30437-30464.
17. Kim, H. E., Cosa-Linan, A., Santhanam, N., Jannesari, M., Maros, M. E., & Ganslandt, T. (2022). Transfer learning for medical image classification: a literature review. BMC medical imaging, 22(1), 69.
18. Kishore, V. V., Kalpana, V., & Dosapati, U. B. (2024, April). Interpretation of KOA by KL Grading System using Deep Learning. In 2024 10th International Conference on Communication and Signal Processing (ICCSP) (pp. 109-114). IEEE.
19. Kokkotis, C., Moustakidis, S., Giakas, G., & Tsaopoulos, D. 2020. Identification of risk factors and machine learning-based prediction models for knee osteoarthritis patients. Applied Sciences, 10(19), 6797.
20. Kumar, H., Virmani, A., Tripathi, S., Agrawal, R., & Kumar, S. (2021). Transfer learning and supervised machine learning approach for detection of skin cancer: performance analysis and comparison. Drugs and Cell Therapies in Hematology, 10(1). 1-16
21. Langworthy, M., Dasa, V., & Spitzer, A. I. (2024). Knee osteoarthritis: disease burden, available treatments, and emerging options. Therapeutic Advances in Musculoskeletal Disease, 16, 1759720X241273009.
22. Li, H., & Duan, X. L. (2022). SAR ship image speckle noise suppression algorithm based on adaptive bilateral filter. Wireless Communications and Mobile Computing, 2022(1), 9392648.
23. Mahmoud, M., Kasem, M. S., & Kang, H. S. (2024). A Comprehensive Survey of Masked Faces: Recognition, Detection, and Unmasking. arXiv preprint arXiv:2405.05900.
24. Mohammed, A. S., Hasanaath, A. A., Latif, G., & Bashar, A. (2023). Knee osteoarthritis detection and severity classification using residual neural networks on preprocessed x-ray images. Diagnostics, 13(8), 1380.
25. Nurmirinta, T. A., Turunen, M. J., Korhonen, R. K., Tohka, J., Liukkonen, M. K., & Mononen, M. E. (2024). Two-stage Classification of future knee osteoarthritis severity after 8 Years using MRI: data from the osteoarthritis initiative. Annals of Biomedical Engineering, 1-12.
26. Qali, A., Selek, M., & Abbas, S. S. (2021). Termal görüntü işleme ile diz osteoartritinin tespit edilmesi. Avrupa Bilim ve Teknoloji Dergisi, (30), 69-72.
27. Rehman, S. U., & Gruhn, V. (2024). A Sequential VGG16+ CNN based Automated Approach with Adaptive Input for Efficient Detection of Knee Osteoarthritis Stages. IEEE Access.
28. Solak, F. Z. 2024. Classification of knee osteoarthritis severity by transfer learning from X-ray images. Karaelmas Science and Engineering Journal, 14(2), 119-133.
29. Tang, W., Sun, J., Wang, S., & Zhang, Y. (2023). Review of alexnet for medical image classification. EAI Endorsed Transactions on E-Learning, 9. 1-13. https://doi.org/10.4108/eetel.4389
30. Tiwari, A., Poduval, M., & Bagaria, V. (2022). Evaluation of artificial intelligence models for osteoarthritis of the knee using deep learning algorithms for orthopedic radiographs. World Journal of Orthopedics, 13(6), 603.
31. Tong, Y., Lu, W., Deng, Q. Q., Chen, C., & Shen, Y. (2020). Automated identification of retinopathy of prematurity by image-based deep learning. Eye and Vision, 7, 1-12.
32. Wahyuningrum, R. T., Yasid, A., & Jacob Verkerke, G. (2020, December). Deep neural networks for automatic classification of knee osteoarthritis severity based on X-ray images. In Proceedings of the 2020 8th International Conference on Information Technology: IoT and Smart City (pp. 110-114).
33. Wang, Y., Wang, X., Gao, T., Du, L., & Liu, W. (2021). An automatic knee osteoarthritis diagnosis method based on deep learning: data from the osteoarthritis initiative. Journal of Healthcare Engineering, 2021(1), 5586529.
34. Yang, Z., Nashik, S., Huang, C., Aibin, M., & Coria, L. (2024). Next-Gen Remote Airport Maintenance: UAV-Guided Inspection and Maintenance Using Computer Vision. Drones, 8(6), 225.
35. Zeng, L., Zhou, G., Yang, W., & Liu, J. (2023). Guidelines for the diagnosis and treatment of knee osteoarthritis with integrative medicine based on traditional Chinese medicine. Frontiers in medicine, 10, 1260943.