Automatic segmentation of the vessel lumen from 3D CTA images of aortic dissection

Abstract

Acute aortic dissection is a life-threatening condition and must be diagnosed and treated promptly. For treatment planning the reliable identification of the true and false lumen is crucial. However, a fully automatic Computer Aided Diagnosing system capable to display the different lumens in an easily comprehensible and timely manner is still not available. In this paper we present the first step towards such a system, namely a method that segments the entire aorta without any user interaction. The method is robust against inhomogeneous distribution of the contrast agent generally seen in dissected aortas, high-density artifacts, and the dissection membrane separating the true and the false lumen.