Automatic Joint detection Hand Radiographs in Rheumatoid Arthritis

Abstract

Although radiographic evaluation of joint space measurement is essential in characterizing disease progression and prediction in patients with rheumatoid arthritis (RA), it is often difficult even for trained radiologists to find radiographic changes on hand radiographs because lesion changes are often subtle. Therefore, an effective system analysis is necessary for the identification and detection of rheumatoid arthritis by hand, especially during its development or pre-diagnostic stages. First symptom of this disease is seen in joints of hand finger and wrist joints thus making hand radiograph analysis extremely important. Lately Reading hand X-ray radiographic image to measure joint space width is very tedious and time consuming task for the radiologist since there are 14 joints in hand and also the structure of hand is complicated to carry out joint space width measurement and analysis. In this paper a quantitative method is proposed for automatically detection of hand joints of RA patients. The proposed system is designed to develop an intelligent system to detect rheumatoid arthritis of the hand using image processing techniques and a neural network of convolution.The system comprises of two main phases. The image processing phase is the first stage in which images are processed using image processing. These techniques include pre-processing, image segmentation and feature extraction using gabor filter. We have experimented 21 digital hand X-ray radiograph of resolution 2000 pixels×2000 pixels and automatically detected all finger joints successfully.