Segmentation of artery wall in coronary IVUS images: a probabilistic approach

Intravascular ultrasound (IVUS) images represent a unique tool to analyze the morphology of arteries and vessels (plaques, etc). The poor quality of these images makes traditional segmentation algorithms (such as edge detection) fail to achieve the expected results. We present a probabilistic flexible template to separate different regions in the image. In particular, we use elliptic templates to model and detect the shape of the vessel inner wall in IVUS images. The use of elliptic templates forces a global probabilistic approach, that makes use of image statistics inside regions. We present the results of successful segmentation obtained from 12 patients undergoing stent treatment. A physician team has validated these results