Region Growing Based on Window Frame Difference for Segmenting Ultrasonic Contrast Images of Arteries

The arterial wall position has impacts on the accuracy of wall shear stress calculation. In this paper, a novel region growing algorithm based on window frame difference is proposed for extracting the arterial boundaries in ultrasound contrast images. Firstly, window frame difference is constructed by the intensity difference of two consecutive frames according to the flow characteristics of ultrasound contrast agents in blood. Region growing is proceeded by the improved growing principle combined with window frame difference and neighborhood intensity. Then the close operator of morphology is used to fill the holes generated in region growing and a customized method is developed to smooth the irregular boundaries. Finally, the experimental results verify the efficiency and feasibility of the proposed algorithm in segmenting ultrasound contrast images of rat carotid arteries. The proposed algorithm is able to extract the obscure arterial boundaries and has low time complexity.