Segmentation of finger joint synovitis in ultrasound images

摘要

The arthritis disease may result from the long-lasting inflammation of the joint. The medical diagnosis assumes visual inspection of the joint ultrasonographic (USG) image, before any medical treatment takes place. Nowadays, the annotation of USG data is prepared manually by an expert physician, which is time-consuming and tiresome work. Therefore, in this work a system for automatic joint synovitis region detection for USG images of finger joints is introduced. The system enables accurate localization of skin border, detection of bones regions, calculation of joint center coordinates. All these information are indispensable for the procedure of automatic finger joint synovitis area localization. The accuracy of specific region detection was verified by comparison with manual annotations and proved high correlation, giving satisfactory result.