Block based texture analysis approach for knee osteoarthritis identification using SVM

This Osteoarthritis (OA) is an inflammatory disease causing pain, swelling, stiffness, and loss of function in joints; it is difficult to diagnose in early stages. An early diagnosis and treatment can delay the onset of severe disability. X-ray imaging offers a potential approach to detect changes in degree of inflammation. X-ray images of knee joints were collected from 20 normal subjects and 20 patients diagnosed with Osteoarthritis (OA). These images were divided into blocks and texture analysis algorithm was applied for statistical feature extraction. Finally classification is done using Support Vector Machine (SVM) Classifier for decision making. Results indicate that: (i) X-ray images can be useful for detecting patients with the disease, (ii) The extracted texture features are good to describe image information about Osteoarthritis, (iii) the the extracted features and classifier used have assisted us to differentiate between normal subjects and patients with OA are the Skewness, Kurtosis Standard Deviation and Energy.