Detection of Shoulder Rotator Cuff Tears from X-Ray Image by Using Convolutional Neural Network

Shoulder rotator cuff tears are common disabilities of the shoulder joint caused by daily activities, sports injuries, and aging. Magnetic resonance imaging is widely used to diagnose tears, but radiography a more rapid popular technique. In this study, we proposed detection method using convolutional neural networks (CNN) on X-ray images for simpler diagnosis tears. 139 subjects, classified into two classes according severity tear, were compared in terms accuracy between five regions interest combinations CNN models, with maximum 79.3% accuracy.