A novel segmentation technique for carotid ultrasound images

Ultrasound provides a non-invasive means for visualizing various tissues within the human body. However, these visualizations tend to be filled with speckle noise and other artifacts, due to the sporadic nature of sound waves. The paper presents a novel segmentation technique for use on noisy B-mode ultrasound images of the carotid artery. This scheme is based on histogram equalization, Canny edge detection and morphology methods. The proposed scheme provides various degrees of customizability, for a wide range of ultrasound images. The experimental results show that this scheme is accurate enough to segment the different textures in ultrasound images. These automatically segmented regions may alleviate the need for a practitioner´s time-consuming manual segmentation of wanted regions.