Multicue PDE-based segmentation of ultrasound carotid artery using flooding technique

摘要

One of the successful applications of image processing techniques is in the area of medical imaging. There exists no general segmentation algorithm in image processing which can work efficiently for all images. A technique for the segmentation of an ultrasound carotid artery is presented in this paper. This paper solves the segmentation problem of carotid artery by attempting to incorporate cues such as intensity contrast, region size and texture in the segmentation procedure and derive improved results compared to using individual cues separately. It proposes efficient simplification operators and feature extraction schemes, capable of quantifying important characteristics like geometrical complexity, rate of change in local contrast variations and orientation. This helps the final segmentation result. The main technique used in this project is the modelling and partial differential equation (PDE) formulation of watershed transform in order to satisfy various flooding criteria.