Sci-Fri AM: Imaging - 07: Semi-Automated Segmentation of Carotid Artery Lumen and Wall from Three-Dimensional Ultrasound Images Using Level Sets

Abstract

Three-dimensional (3D) carotid ultrasound (US) phenotypes are increasingly being investigated for quantifying carotid arthrosclerosis for monitoring and assessment of patients who are at a greater risk of stroke. Vessel wall volume (VWV), which is the 3D measurement of vessel wall thickness plus plaque within the carotid artery, provides a high measurement sensitivity and reproducibility for carotid arthrosclerosis. VWV computation requires lumen and media-adventitia boundaries of the carotid arteries to be outlined. Its use in current clinical practice is limited by the requirement for manual segmentation which is extremely time consuming and operator-dependent. Therefore the objective of this study is to develop and validate a semiautomatic segmentation algorithm for delineating the media-adventitia and lumen boundaries of carotid arteries for patients with asymptomatic carotid stenosis. Due to the presence of plaque, poor definition of the vessel boundaries, intensity heterogeneity, image speckle, and shadowing, the carotid arteries are extremely challenging to segment using image information alone. Therefore, we combine various image cues with domain knowledge of the vessel geometry and some user interaction into the segmentation framework. We adopted an energy minimization approach based on the level sets formulation to segment the vessel wall and lumen using edge-based and region-based objective functions respectively. The proposed segmentation method was evaluated with respect to manually outlined boundaries using several similarity measures on 60 2D US slices from ten patients. The realization of semi-automated methods will accelerate the translation of 3DUS to real-time clinical research and clinical care.