Lumen segmentation of atherosclerotic carotid arteries in CTA

Lumen segmentation is relevant for quantification of the degree of stenoses and as preprocessing step for the analysis of the vessel wall, and for the simulation and planing of interventions. Although lumen segmentation in CTA has received considerable interest, it remains a challenge for atherosclerotic vessels. In this paper we propose a semi-automatic lumen segmentation method using a levelset approach, which utilizes both boundary information and regional intensity information to accurately segment the lumen of atherosclerotic vessels. The method was trained and evaluated on a publicly available database of 56 carotid arteries. The average Dice similarity coefficient was 88.9 %, the mean absolute surface distance was 0.31 mm. Compared to using only boundary information, this method yields better segmentation in severely atheroslerotic vessels.