Ultrasonic renal-stone detection and identification for extracorporeal lithotripsy.

The efficacy of extracorporeal shock wave lithotripsy (ESWL) depends greatly on the capability to focus shock waves on renal stone in real time. To achieve automatic focusing on moving targets, target detection, identification and tracking are required functions. An algorithm for renal stone detection and identification based on ultrasound images is proposed. Two types of image features (contrast and target shape) are selected for stone detection and identification. A feature extraction algorithm is proposed and tested. Statistical characteristics of these features are studied based on the images of kidney recorded during ESWL treatment. The results demonstrate the feasibility of automatic detection and identification of renal stone based on ultrasound images.