Universiti Teknologi Malaysia Institutional Repository

K-means clustering in knee cartilage classification: Data from the OAI

Sia, Joyce Sin Yin and Tan, Tian Swee and Tiong, Matthias Foh Thye and Leong, Kah Meng and Ling, Kelvin Chia Hiik and Malik, Sameen Ahmed and Sia, Jeremy Yik Xian (2020) K-means clustering in knee cartilage classification: Data from the OAI. Indonesian Journal of Electrical Engineering and Informatics, 8 (2). pp. 320-330. ISSN 2089-3272

[img]
Preview
PDF
634kB

Official URL: http://dx.doi.org/10.11591/ijeei.v8i2.1649

Abstract

Knee osteoarthritis is a degenerative joint disease which affects people mostly from elderly population. Knee cartilage segmentation is still a driving force in managing early symptoms of knee pain and its consequences of physical disability. However, manual delineation of the tissue of interest by single trained operator is very time consuming. This project utilized a fully-automated segmentation that combined a series of image processing methods to process sagittal knee images. MRI scans undergo Bi-Bezier curve contrast enhancement which increase the distinctiveness of cartilage tissue. Bone-cartilage complex is extracted with dilation of mask resulted from region growing at distal femoral bone. Later, the processed image is clustered with k = 2, into two groups, including coarse cartilage group and background. The thin layer of cartilage is successfully clustered with satisfactory accuracy of 0.987±0.004, sensitivity 0.685±0.065 of and specificity of 0.994±0.004. The results obtained are promising and potentially replace the manual labelling process of training set in convolutional neural network model.

Item Type:Article
Uncontrolled Keywords:image processing, cartilage segmentation
Subjects:Q Science > QM Human anatomy
Divisions:Biosciences and Medical Engineering
ID Code:93632
Deposited By: Widya Wahid
Deposited On:31 Dec 2021 08:45
Last Modified:31 Dec 2021 08:45

Repository Staff Only: item control page