Revolutionizing Knee Osteoarthritis Diagnosis: Unleashing the Potential of Vision Transformers

Year : 2024 | Volume :11 | Issue : 01 | Page : 24-31

Suman Rani

Minakshi Memoria

  1. Associate Professor Computer science, Uttaranchal University Uttarakhand India
  2. Research Scholar Computer science, Uttaranchal University Uttarakhand


Osteoarthritis (OA) is the most common kind of arthritis. By analysing data from both sides of the knee joints, radiologists use the Kellgren–Lawrence (KL) grading system to determine the severity of osteoarthritis (OA). The need for knee arthroplasties has increased as a result of this. Recently, there have been proposals for computer-assisted techniques to improve the precision of OA diagnosis. Choosing between conservative and surgical treatment options for knee osteoarthritis (OA) requires an accurate diagnosis and classification of the condition. Consequently, standard weight- bearing knee X-rays are heavily relied upon by many orthopaedic surgeons. Enhancing these tests’ consistency and repeatability can have major benefits. Recent developments in artificial intelligence (AI) have shown promise, especially in the area of deep learning. Earlier, the diagnosis of knee osteoarthritis was done using deep learning and DNN. But in the future, in the diagnosis of knees, it will use computer vision techniques. The purpose of this research is to evaluate how well artificial intelligence (AI) can classify the degree of osteoarthritis M(OA) in the knee by taking into account entire image sets and taking common visual anomalies like casts, implants, and non-degenerative diseases into account. In this study, we present an architectural model—based on the ViT transformer—for categorising osteoarthritis in the knee. We will use ViT to classify knee osteoarthritis in the future and gather information from multiple sources. In this study discuss the how ViT used in knee osteoarthritis diagnosis

Keywords: Knee Osteoarthritis classification, Deep learning, KL Grade, AI, Image Processing, Vision Transformer

[This article belongs to Journal of Mechatronics and Automation(joma)]

How to cite this article: Suman Rani, Minakshi Memoria. Revolutionizing Knee Osteoarthritis Diagnosis: Unleashing the Potential of Vision Transformers. Journal of Mechatronics and Automation. 2024; 11(01):24-31.
How to cite this URL: Suman Rani, Minakshi Memoria. Revolutionizing Knee Osteoarthritis Diagnosis: Unleashing the Potential of Vision Transformers. Journal of Mechatronics and Automation. 2024; 11(01):24-31. Available from:

Browse Figures


  1. D. Kohn, A. A. Sassoon, and N. D. Fernando, “Classifications in Brief: Kellgren-Lawrence Classification of Osteoarthritis,” Clin. Orthop. Relat. Res., vol. 474, no. 8, pp. 1886–1893, 2016, doi: 10.1007/s11999-016-4732-4.
  2. Saini, D., Khosla, A., Chand, T., Chouhan, D. K., & Prakash, M. (2023). Automated knee osteoarthritis severity classification using three‐stage preprocessing method and VGG16 architecture. International Journal of Imaging Systems and Technology, 33(3), 1028-1047.
  3. Vaishya, G. B. Pariyo, A. K. Agarwal, and V. Vijay, “Non-operative management of osteoarthritis of the knee joint,” J. Clin. Orthop. Trauma, vol. 7, no. 3, pp. 170–176, 2016, doi: 10.1016/j.jcot.2016.05.005.
  4. Leung et al., “Prediction of total knee replacement and diagnosis of osteoarthritis by using deep learning on knee radiographs: Data from the osteoarthritis initiative,” Radiology, vol. 296, no. 3, pp. 584–593, Sep. 2020, doi: 10.1148/radiol.2020192091.
  5. B. Schiratti et al., “A deep learning method for predicting knee osteoarthritis radiographic progression from MRI,” Arthritis Res. Ther., vol. 23, no. 1, pp. 1–10, 2021, doi: 10.1186/s13075- 021-02634-4.
  6. Guangyi. et al., “Subchondral bone in osteoarthritis: Insight into risk factors and microstructural changes,” Arthritis Res. Ther., vol. 15, p. 223, 2013, [Online]. Available: http://arthritis- D=emed11&NEWS=N&AN=2013776791
  7. S. Cruz, H. C. Lins, R. V. A. Medeiros, J. M. F. Filho, and S. G. Silva, “Artificial intelligence on the identification of risk groups for osteoporosis, a general review,” Biomed. Eng. Online, vol. 17, no. 1, pp. 1–17, 2018, doi: 10.1186/s12938-018-0436- 1.
  8. Kokkotis, S. Moustakidis, E. Papageorgiou, G. Giakas, and D. E. Tsaopoulos, “Machine learning in knee osteoarthritis: A review,” Osteoarthr. Cartil. Open, vol. 2, no. 3, p. 100069, Sep. 2020, doi: 10.1016/j.ocarto.2020.100069.
  9. Vos et al., “Years lived with disability (YLDs) for 1160 sequelae of 289 diseases and injuries 1990-2010: A systematic analysis for the Global Burden of Disease Study 2010,” The Lancet, vol. 380, no. 9859. pp. 2163–2196, 2012. doi: 10.1016/S0140-6736(12)61729-2.
  10. Binvignat et al., “Use of machine learning in osteoarthritis research: A systematic literature review,” RMD Open, vol. 8, no. 1, pp. 1–10, 2022, doi: 10.1136/rmdopen-2021-001998.
  11. Kokkotis, S. Moustakidis, D. Tsaopoulos, V. Baltzopoulos, and G. Giakas, “Identifying robust risk factors for knee osteoarthritis progression: An evolutionary machine learning approach,” Healthc., vol. 9, no. 3, Mar. 2021, doi: 10.3390/healthcare9030260.
  12. S. Gornale, P. U. Patravali, and R. R. Manza, “Detection of Osteoarthritis using Knee X-Ray Image Analyses: A Machine Vision based Approach,” Int. J. Comput. Appl., vol. 145, no. 1, pp. 975–8887, 2016.
  13. A. El-Ghany, M. Elmogy, and A. A. A. El-Aziz, “A fully automatic fine tuned deep learning model for knee osteoarthritis detection and progression analysis,” Egypt. Informatics J., vol. 24, no. 2, pp. 229–240, Jul. 2023, doi: 10.1016/j.eij.2023.03.005.
  14. T. Wahyuningrum, A. Lilik, and P. I, “11_ICAwST.2019.8923284.pdf,” 2019 IEEE 10th Int. Conf. Aware. Sci. Technol., pp. 1–6.
  15. S. Lee et al., “Artificial intelligence in diagnosis of knee osteoarthritis and prediction of arthroplasty outcomes: a review,” Arthroplasty, vol. 4, no. 1. BioMed Central Ltd, Dec. 01, 2022. doi: 10.1186/s42836-022-00118-7.
  16. S. Q. Yeoh et al., “Emergence of Deep Learning in Knee Osteoarthritis Diagnosis,” Computational Intelligence and Neuroscience, vol. 2021. Hindawi Limited, 2021. doi: 10.1155/2021/4931437.
  17. Guida, M. Zhang, and J. Shan, “Knee osteoarthritis classification using 3D CNN and MRI,” Appl. Sci., vol. 11, no. 11, Jun. 2021, doi: 10.3390/app11115196.
  18. Wang, X. Wang, T. Gao, L. Du, and W. Liu, “An Automatic Knee Osteoarthritis Diagnosis Method Based on Deep Learning: Data from the Osteoarthritis Initiative,” J. Healthc. Eng., vol. 2021, 2021, doi: 10.1155/2021/5586529.
  19. Dur, “FINAL MASTER THESIS Area of Medicine,” no. January, 2022.
  20. Irshad, M. Yasmin, M. I. Sharif, M. Rashid, M. Sharif, and S. Kadry, “A Novel Light U-Net Model for Left Ventricle Segmentation Using MRI,” Mathematics, vol. 11, no. 14, 2023, doi: 10.3390/math11143245.
  21. Ma, C., Chao, Y., Zhu, J., Wang, Y., Liu, W., & Han, Z. (2022, November). Chip Surface Defect Recognition based on Improved Faster R-CNN. In 2022 28th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (pp. 1-6). IEEE.
  22. Rani, S., M. Memoria, T. Choudhury, and A. Sar. “A Comprehensive Review of Machine Learning’s Role Within KOA”. EAI Endorsed Transactions on Internet of Things, vol. 10, Mar. 2024, doi:10.4108/eetiot.5329.
  23. Ekram R, Nazer MS. Hospital Admission Profile Due to Osteoarthritis: An Ecological Study. Cureus. 2023 May 2;15(5):e38435. doi: 10.7759/cureus.38435. PMID: 37273367; PMCID: PMC10234140

Regular Issue Subscription Original Research
Volume 11
Issue 01
Received April 9, 2024
Accepted April 22, 2024
Published May 15, 2024