Machine Learning Method for Knee Osteoarthritis Detection from Magnetic Resonance Imaging: A 3-D Independent Component Analysis-Based Approach

Marco Oyarzo Huichaqueo¹

Section:Research Paper, Product Type: Journal-Paper
Vol.8 , Issue.4 , pp.1-4, Dec-2021

Online published on Dec 31, 2021

Copyright © Marco Oyarzo Huichaqueo . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
Osteoarthritis (OA) is a global disease that still does not have a treatment for its process and that impacts people`s quality of life. Nowadays, medical images such as magnetic resonance (MR) images are widely used for the OA diagnosis. For this, a medical specialist analyzes medical images by measuring the changes and in particular for knee OA, the changes in the compartment of the tibio-femoral cartilage. In this work, we describe a novel knee OA diagnostic method, which use a Support Vector Machine (SVM) algorithm and is capable of detecting the disease from MR images. Our proposed approach is based on the application of the Independent Component Analysis (ICA) technique to 3-D information from MR images of a real cohort. The experimental results showed that our ICA-SVM machine learning model achieved 86% of testing accuracy with both 72% of specificity and 100% of sensitivity, once trained with a small MR image dataset.

Key-Words / Index Term :
Osteoarthritis, Magnetic Resonance Imaging, Independent Component Analysis, Support Vector Machine

References :
[1] J. Kellgren and J. Lawrence, “Radiological assessment of osteo-arthrosis”, Annals of the Rheumatic Diseases, Vol. 16, No. 4, pp. 494-502, 1957.
[2] H. Park, S. Soo, S. Lee, N. Park, J. Park, Y. Choi, H. Jeon, “A practical MRI grading system for osteoarthritis of the knee: Association with Kellgren-Lawrence radiographic scores”, European Journal of Radiology, Vol. 82, No. 1, pp. 112-117, 2013.
[3] V. Joshi, R. Singh, N. Kohli, U. Parashari, A. Kumar, V. Singh, “Evaluation of osteoarthritis of the knee with magnetic resonance imaging and correlating it with radiological findings in the indian population”, The Internet Journal of Orthopedic Surgery, Vol. 14, No. 1, pp. 01-09, 2008.
[4] Y. Du, R. Almajalid, J. Shan, M. Zhang, “A novel method to predict knee osteoarthritis progression on MRI using machine learning methods”, IEEE Transactions on Nanobioscience, Vol. 17, No. 3, pp. 228-236, 2018.
[5] S. Moustakidis, E. Christodoulou, E. Papageorgiou, C. Kokkotis, N. Papandrianos, D. Tsaopoulos, “Application of machine intelligence for osteoarthritis classification: a classical implementation and a quantum perspective”, Quantum Machine Intelligence, Vol. 1, No. 1, pp. 73-86, 2019.
[6] F. Sultana, A. Sufian, P. Dutta, “Advancements in image classification using convolutional neural network”, Fourth IEEE International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN 2018), Kolkata, India, pp. 122-129, 2018.
[7] F. Ambellan, A. Tack, M. Ehlke, S. Zachow, “Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks”, Medical Image Analysis, Vol. 52, No. 2, pp. 109-118, 2019.
[8] G. Chang, D. Felson, S. Qiu, A. Guermazi, T. Capellini, V. Kolachalama, “Assessment of knee pain from MR imaging using a convolutional siamese network”, European Radiology, Vol. 30, No. 6, pp. 3538-3548, 2020.
[9] C. Guida, M. Zhang, J. Shan, “Knee osteoarthritis classification using 3D CNN and MRI”, Applied Sciences, Vol. 11, No. 11, pp. 5196-5207 , 2021.
[10] F. Eckstein, M. Hudelmaier, W. Wirth, B. Kiefer, R. Jackson, J. Yu, C. Eaton, E. Schneider, “Double echo steady state magnetic resonance imaging of knee articular cartilage at 3 Tesla: A pilot study for the osteoarthritis initiative”, Annals of the Rheumatic Diseases, Vol. 65, No. 4, pp. 433-441, 2006.