Segmentation of Ultrasonic Images Based on Modified Chan-Vese algorithm

Abstract

Abstract. The primary ultrasonic image segmentation goal is to partition a given ultrasonic image into different regions representing anatomical structures. Ultrasonic image segmentation is very important because the accurate representation of object and background fluid provides a way to identify many disease. In this paper, a modified Chan-Vese model is proposed for image segmentation, which is based on the similarity between each point and center point in the neighborhood. This model can capture the details of local region to realize the image segmentation in gray-level heterogeneous area. Experimental results show that this method can segment the ultrasonic image with high accuracy, adapt ability and more stable performance compared with the traditional Chan-Vese model.