Osteoarthritis Classification Using Self Organizing Map Based on Gabor Kernel and Contrast-Limited Adaptive Histogram Equalization

Abstract

Localization is the first step in osteoarthritis (OA) classification. Manual classification, however, is time-consuming, tedious, and expensive. The proposed system is designed as decision support system for medical doctors to classify the severity of knee OA. A method has been proposed here to localize a joint space area for OA and then classify it in 4 steps to classify OA into KL-Grade 0, KL-Grade 1, KL-Grade 2, KL-Grade 3 and KL-Grade 4, which are preprocessing, segmentation, feature extraction, and classification. In this proposed system, right and left knee detection was performed by employing the Contrast-Limited Adaptive Histogram Equalization (CLAHE) and the template matching. The Gabor kernel, row sum graph and moment methods were used to localize the junction space area of knee. CLAHE is used for preprocessing step, i.e.to normalize the varied intensities. The segmentation process was conducted using the Gabor kernel, template matching, row sum graph and gray level center of mass method. Here GLCM (contrast, correlation, energy, and homogeinity) features were employed as training data. Overall, 50 data were evaluated for training and 258 data for testing. Experimental results showed the best performance by using gabor kernel with parameters α=8, θ=0, Ψ=[0 π/2], γ=0,8, N=4 and with number of iterations being 5000, momentum value 0.5 and α0=0.6 for the classification process. The run gave classification accuracy rate of 93.8% for KL-Grade 0, 70% for KL-Grade 1, 4% for KL-Grade 2, 10% for KL-Grade 3 and 88.9% for KL-Grade 4.

Fully automated shape analysis for detection of Osteoarthritis from lateral knee radiographs

“…They used a RFCLM on a 74 points model and extracted features of tibial texture. Other approaches are [7] and [8], where image processing techniques are applied to PA knee radiographs: in the former the authors extracted image content descriptors and image transforms to use as features in a Nearest Neighbor setting; the latter applied the unsupervised self organizing maps based on Gabor filter to classify the K-L grades. In [9], the authors used medical infrared thermography of the PA view to extract features on which train a SVM classifier.…”

Automatic Grading of Knee Osteoarthritis from Plain Radiographs Using Densely Connected Convolutional Networks

“…One of the simplest methods is given in [ 17 ]—localization of the knee joint area there is performed by calculating the center of mass of the histogram, calculated by the sum of intensities of image rows. Similar histograms are also used in [ 12 ].…”

DeepKneeExplainer: Explainable Knee Osteoarthritis Diagnosis From Radiographs and Magnetic Resonance Imaging

“…53 Several approaches for feature extraction are pre- [29]. Anifah et al [30] applied the gray-level co-occurrence matrix (GLCM) with Gabor kernel, giving an accuracy of 53.34%. However, only 4% of the radiographs could correctly be classified as KL grade 2.…”