Detection of Rheumatoid Arthritis using Image Processing Techniques

Rheumatoid Arthritis (RA) is a kind of inflammatory disease.Main symptoms of RA are inflammation, swollen and joint pain especially early hours of the day. Inflammation starts at smaller joints of the body, in later stages inflammation spread to heart and other organs of the body. Therefore, detection of RA in early stages is very much essential.Different modalities are being used for the purpose of RA diagnosis notably radiography, ultrasound and Magnetic Resonance Imaging (MRI), even though X-ray is the best and effective tool in the assessment of joint damage and position changes. The gap between phalangeal bones in the hand finger is a vital parameter in the detection of RA using X-ray images, especially the metacarpal joint and proximal joint involved in the early stage of the RA. This work deals with development of the image processing technique which is helpful for RA detection. The image processing steps involves median filtering, background extraction, images subtraction, canny edge detection for segmentation and finally features extraction. The extracted feature reveals the significant difference between normal and abnormal (RA) image. Dataset include both normal and RA affected images.