Premium
Semiautomatic segmentation and stenosis quantification of 3D contrast‐enhanced MR angiograms of the internal carotid artery
Author(s) -
van Bemmel Cornelis M.,
Viergever Max A.,
Niessen Wiro J.
Publication year - 2004
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.20020
Subject(s) - segmentation , contrast (vision) , stenosis , initialization , magnetic resonance angiography , medicine , internal carotid artery , carotid arteries , angiography , radiology , nuclear medicine , magnetic resonance imaging , computer science , artificial intelligence , cardiology , programming language
Abstract A technique is presented for the segmentation and quantification of stenosed internal carotid arteries (ICAs) in 3D contrast‐enhanced MR angiography (CE‐MRA). Segmentation with sub‐pixel accuracy of the ICA is achieved via level‐set techniques in which the central axis serves as the initialization. The central axis is determined between two user‐defined points, and minimal user interaction is required. For quantification, the cross‐sectional area is measured in the stenosis and at a reference segment in planes perpendicular to the central axis. The technique was applied to 20 ICAs. The variation in measurements obtained by this method in comparison with manual observations was 8.7%, which is smaller than the interobserver variability among three experts (11.0%). Magn Reson Med 51:753–760, 2004. © 2004 Wiley‐Liss, Inc.