A Modified Spatial Fuzzy Clustering Method Based on Texture Analysis for Ultrasound Image Segmentation

Ultrasound image segmentation is challenging due to the interference from speckle noise and fuzziness of boundaries. In this paper, we propose a segmentation scheme using fuzzy c-means (FCM) clustering incorporating spatial information based on intensity and texture of images. Firstly, the nonlinear structure tensor, which helps to refine the edges detected by intensity, is used to extract speckle texture. And then, a spatial FCM clustering method is applied on the image feature space for segmentation. In the experiments with simulated and clinical ultrasound images, the proposed method can get more accurate results than the conventional FCM and other segmentation methods.