3-D deformable model for abdominal aortic aneurysm segmentation from CT images

Abstract

In this paper we propose a technique for 3-D segmentation of abdominal aorta computed tomography (CT) images. Output data of the proposed algorithm are a 3-D model of the aorta that can be used for measurement of aorta dimensions. This information is very important in minimal invasive treatment of an abdominal aortic aneurysm. The technique is based on a deformable model. The deformable model is implemented using a level-set algorithm. The level set algorithm has several advantages over classical "snake" algorithms. Experiments have been performed using real patient CT angiography images and show good results.