Automated Knee Osteoarthritis Severity Grading in X-ray Images Using Transfer Learning

Authors

  • Mohammad Mojtaba Rohani Department of Radiology, Poursina Hospital, Guilan University of Medical Sciences, Rasht, Iran Author

Keywords:

Transfer Learning, Knee Osteoarthritis

Abstract

Knee osteoarthritis (OA) is a chronic degenerative joint disease that leads to cartilage breakdown, joint space narrowing, and osteophyte formation, significantly impacting mobility and quality of life. Early and accurate grading of OA severity is crucial for effective treatment and disease management. X-ray imaging is the most widely used diagnostic tool for knee OA, providing a cost-effective and non-invasive method to assess structural changes in the knee joint. However, manual interpretation of X-rays is subjective and prone to inter-observer variability, necessitating the development of automated AI-based diagnostic systems. This study proposes a deep learning-based approach for knee OA severity grading using transfer learning with MobileNet and ResNet models. The results indicate that ResNet significantly outperformed MobileNet, achieving 83.5% accuracy, 83.0% precision, and 83.1% recall, compared to 74.1%, 71.5%, and 71.0%, respectively, for MobileNet. Statistical analysis using ANOVA confirmed significant differences (p < 0.05) in classification performance between the models.

 

References

[1] Sharma L. Osteoarthritis of the knee. New England Journal of Medicine. 2021 Jan 7;384(1):51-9.

[2] Hussain SM, Neilly DW, Baliga S, Patil S, Meek RM. Knee osteoarthritis: a review of management options. Scottish medical journal. 2016 Feb;61(1):7-16.

[3] Chen P. Knee osteoarthritis severity grading dataset. Mendeley Data. 2018 Jan;1(10.17632):30784984.

[4] Cozzi D, Albanesi M, Cavigli E, Moroni C, Bindi A, Luvarà S, Lucarini S, Busoni S, Mazzoni LN, Miele V. Chest X-ray in new Coronavirus Disease 2019 (COVID-19) infection: findings and correlation with clinical outcome. La radiologia medica. 2020 Aug;125:730-7.

[5] Rad AE, Rahim MS, Rehman A, Saba T. Digital dental X-ray database for caries screening. 3D Research. 2016 Jun 11;7(2):18.

[6] Sharifi S, Donyadadi A. Detection and Diagnosis of Congenital Heart Disease from Chest X-Rays with Deep Learning Models. International Journal of Applied Data Science in Engineering and Health. 2025 Jan 2;1(1):1-9.

[7] Saleem M, Farid MS, Saleem S, Khan MH. X-ray image analysis for automated knee osteoarthritis detection. Signal, Image and Video Processing. 2020 Sep;14(6):1079-87.

[8] Tariq T, Suhail Z, Nawaz Z. Knee osteoarthritis detection and classification using x-rays. IEEE Access. 2023 May 16;11:48292-303.

[9] Suganyadevi S, Seethalakshmi V, Balasamy K. A review on deep learning in medical image analysis. International Journal of Multimedia Information Retrieval. 2022 Mar;11(1):19-38.

[10] Yeoh PS, Lai KW, Goh SL, Hasikin K, Hum YC, Tee YK, Dhanalakshmi S. Emergence of deep learning in knee osteoarthritis diagnosis. Computational intelligence and neuroscience. 2021;2021(1):4931437.

[11] Tiulpin A, Thevenot J, Rahtu E, Lehenkari P, Saarakkala S. Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Scientific reports. 2018 Jan 29;8(1):1727.

[12] Kijowski R, Fritz J, Deniz CM. Deep learning applications in osteoarthritis imaging. Skeletal radiology. 2023 Nov;52(11):2225-38.

 

Published

2025-03-19