In order to fulfil the contour extraction of left atrial appendage (LAA) from the low resolution, low contrast and noisy transesophageal ultrasound images automatically, a new method was proposed, which combines the anatomical knowledge of LAA and the information of intensity and phase in ultrasound images. Firstly, to locate the effective initial contour with the characteristic of intensity and geometry from LAA ultrasound images, the anatomy location of LAA in the standard section is taken as the priori-knowledge based on the physicians’ collecting habit. Then, to improve the convergence performance of classical Vector Filed Convolution (VFC) model, a new external force term was proposed by combing phase and gradient information in the linear weighting method. According to the test results conducted from 300 frames, it shows that, this method can reach the accuracy of 0.8969 0.0494, sensitivity of 0.9058 0.0762 and specificity of 0.9645 0.1687 by regarding the contours outlined by physicians as “golden standard”. Comparing with traditional VFC model, this method owns better segmentation performance by determining a more suitable initial contour and is more robust to weak edge.
