Abstract
Osteoarthritis (OA) is a type of chronic bone joint disorder. Patients may suffer from heavy pain while performing day to day activities. By confirming the description of the Osteoarthritis Initiative (OAI) nowadays, not only older but also younger people are also suffering from knee OA. The early diagnosis and prognosis of OA are necessary to reduce the pains. Manual detection and accurate severity level identification from an X-ray image is a complicated and requires experienced knowledgeable person. Radiographer and expert orthopedic surgeons spend a lot of time to decide the exact OA grade. To reduce expert’s effects and to predict exact OA severity grade we have developed a deep neural network (DNN) based Computer-aided detection (CAD) system for knee OA classification which precisely identifies the severity level.
The proposed CAD system works in stages. Initially, an innovative column sum-based histogram modeling function is devised to separate the left and right knee from X-ray image. Later DNN-based five-class classification is applied to identify the severity grade. To achieve this, we have developed our own convolutional neural network named OACnet (Osteoarthritis classification network) which follows Kellgren & Lawrence (K&L) knee OA grading system. On OAI database (9,492 knee X-ray images of various severity grades) our system yields 81.41% result.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brandt, K.D., Dieppe, P., Radin, E.L.: Etiopathogenesis of osteoarthritis. Rheum. Dis. Clin. North Am. 34(3), 531–559 (2008)
Felson, D.T., Anderson, J.J., Naimark, A., Walker, A.M., Meenan, R.F.: Obesity and knee osteoarthritis: the Framingham study. Ann. Internal Med. 109(1), 18–24 (1988)
Stammberger, T., Eckstein, F., Michaelis, M., Englmeier, K.-H., Reiser, M.: Interobserver reproducibility of quantitative cartilage measurements: comparison of b-spline snakes and manual segmentation. Magn. Reson. Imaging 17(7), 1033–1042 (1999)
Antony, J., McGuinness, K., Moran, K., O’Connor, N.E.: Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. In: Perner, P. (ed.) MLDM 2017. LNCS (LNAI), vol. 10358, pp. 376–390. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-62416-7_27
Navale, D.I., Hegadi, R.S., Mendgudli, N.: Block based texture analysis approach for knee osteoarthritis identification using SVM. In: 2015 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), pp. 338–341. IEEE (2015)
Hegadi, R.S., Navale, D.I., Pawar, T.D., Ruikar, D.D.: Osteoarthritis detection and classification from knee X-ray images based on artificial neural network. In: Santosh, K.C., Hegadi, R.S. (eds.) RTIP2R 2018. CCIS, vol. 1036, pp. 97–105. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-9184-2_8
Hegadi, R.S., Navale, D.I., Pawar, T.D., Ruikar, D.D.: Multi feature-based classification of osteoarthritis in knee joint X-ray images. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, p. 75 (2019)
Suresha, S., Kidziński, L., Halilaj, E., Gold, G.E., Delp, S.L.: Automated staging of knee osteoarthritis severity using deep neural networks. Osteoarthritis Cartilage 26, S441 (2018)
Kamble, P.M., Hegadi, R.S.: Comparative study of handwritten Marathi characters recognition based on KNN and SVM classifier. In: Santosh, K.C., Hangarge, M., Bevilacqua, V., Negi, A. (eds.) RTIP2R 2016. CCIS, vol. 709, pp. 93–101. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-4859-3_9
Kawathekar, P.P., Karande, K.J.: Use of textural and statistical features for analyzing severity of radio-graphic osteoarthritis of knee joint. In: 2015 International Conference on Information Processing (ICIP), pp. 1–4. IEEE (2015)
Tiulpin, A., Thevenot, J., Rahtu, E., Lehenkari, P., Saarakkala, S.: Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci. Rep. 8(1), 1727 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Navale, D.I., Ruikar, D.D., Sawat, D.D., Kamble, P., Houde, K.V., Hegadi, R.S. (2022). Automatic Knee Osteoarthritis Stages Identification. In: Santosh, K., Hegadi, R., Pal, U. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2021. Communications in Computer and Information Science, vol 1576. Springer, Cham. https://doi.org/10.1007/978-3-031-07005-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-07005-1_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-07004-4
Online ISBN: 978-3-031-07005-1
eBook Packages: Computer ScienceComputer Science (R0)