Ultrasound Image Segmentation Based On Probability Distance and Maximum Likelihood

In this paper, a novel geometric active contour model for segmenting ultrasound image is presented. A partial differential equation is designed to minimize the dif-ference between the actual and the esti-mated intensity probability distributions of the image regions. The Rayleigh dis-tribution and maximum likelihood method are applied for the estimation of the intensity distributions of the regions. The approximation of the flow is based on finite difference with a non re-initialization strategy. The experimental results demonstrate that the proposed ap-proach can segment images accurately and effectively