Share Email Print

Proceedings Paper

Three dimensional level set based semiautomatic segmentation of atherosclerotic carotid artery wall volume using 3D ultrasound imaging
Author(s): Md. Murad Hossain; Khalid AlMuhanna; Limin Zhao; Brajesh K. Lal; Siddhartha Sikdar
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

3D segmentation of carotid plaque from ultrasound (US) images is challenging due to image artifacts and poor boundary definition. Semiautomatic segmentation algorithms for calculating vessel wall volume (VWV) have been proposed for the common carotid artery (CCA) but they have not been applied on plaques in the internal carotid artery (ICA). In this work, we describe a 3D segmentation algorithm that is robust to shadowing and missing boundaries. Our algorithm uses distance regularized level set method with edge and region based energy to segment the adventitial wall boundary (AWB) and lumen-intima boundary (LIB) of plaques in the CCA, ICA and external carotid artery (ECA). The algorithm is initialized by manually placing points on the boundary of a subset of transverse slices with an interslice distance of 4mm. We propose a novel user defined stopping surface based energy to prevent leaking of evolving surface across poorly defined boundaries. Validation was performed against manual segmentation using 3D US volumes acquired from five asymptomatic patients with carotid stenosis using a linear 4D probe. A pseudo gold-standard boundary was formed from manual segmentation by three observers. The Dice similarity coefficient (DSC), Hausdor distance (HD) and modified HD (MHD) were used to compare the algorithm results against the pseudo gold-standard on 1205 cross sectional slices of 5 3D US image sets. The algorithm showed good agreement with the pseudo gold standard boundary with mean DSC of 93.3% (AWB) and 89.82% (LIB); mean MHD of 0.34 mm (AWB) and 0.24 mm (LIB); mean HD of 1.27 mm (AWB) and 0.72 mm (LIB). The proposed 3D semiautomatic segmentation is the first step towards full characterization of 3D plaque progression and longitudinal monitoring.

Paper Details

Date Published: 21 March 2014
PDF: 8 pages
Proc. SPIE 9034, Medical Imaging 2014: Image Processing, 90344B (21 March 2014); doi: 10.1117/12.2043975
Show Author Affiliations
Md. Murad Hossain, George Mason Univ. (United States)
Khalid AlMuhanna, George Mason Univ. (United States)
Limin Zhao, Univ. of Maryland (United States)
Brajesh K. Lal, Univ. of Maryland (United States)
Veterans Affairs Maryland Health Care System (United States)
Siddhartha Sikdar, George Mason Univ. (United States)

Published in SPIE Proceedings Vol. 9034:
Medical Imaging 2014: Image Processing
Sebastien Ourselin; Martin A. Styner, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?