Automated detection of unimpaired joint space for knee osteoarthritis assessment

This paper introduces a machine vision system for osteoarthritis (OA) assessment. The system is designed to help medical doctors to determine the region of interest of visual characteristics found in knee OA, and to provide exact measurement of unimpaired joint space width. In this proposed system, ROI detection is performed using edge based segmentation method. The feature to be extracted is the distance between femur and tibia bone, which associates with the grade of the disease. Normal and narrowing joint is classified using neural network. Compared with the predetermined diagnosis, this system shows 50% sensitivity, 100% specificity, 100% positive predictive value, and 91.84% negative predictive value.