Use of textural and statistical features for analyzing severity of radio-graphic osteoarthritis of knee joint

Osteoarthritis (abbreviated as OA) is chronic disease, most commonly appeared in the knee joint. The defects in cartilage are found due to increasing age of person. OA can be result in any of joint in body like spines, hips, fingers etc, but it is most common and severe in knee. Most of the population over the age of 65 is suffering from this disease. The aim of this paper is to analyze the severity of OA in knee joint by using radio graphs. The simpler methodology depending upon the feature extractions like entropy, standard deviation, coarseness, contrast etc. has been explored in this paper. The grades are then assigned to knee joint images according to their severity. The experimental results shows that developed method can detect and classify OA of knee joint with sufficient accuracy. Maximum accuracy of 92% is achieved for grade 3 images.