Automated detection of the carotid artery wall in longitudinal B-mode images using active contours initialized by the Hough transform

Matsakou, AI; Golemati, S; Stoitsis, JS; Nikita, KS

dc.contributor.author	Matsakou, AI	en
dc.contributor.author	Golemati, S	en
dc.contributor.author	Stoitsis, JS	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T02:47:17Z
dc.date.available	2014-03-01T02:47:17Z
dc.date.issued	2011	en
dc.identifier.issn	1557170X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33057
dc.subject	B-mode ultrasound	en
dc.subject	Carotid artery wall	en
dc.subject	Gradient vector flow snake	en
dc.subject	Hough transform	en
dc.subject	Segmentation	en
dc.subject.other	Active contours	en
dc.subject.other	Arterial wall	en
dc.subject.other	Automated detection	en
dc.subject.other	Automated segmentation	en
dc.subject.other	B-mode images	en
dc.subject.other	B-mode ultrasound images	en
dc.subject.other	Carotid artery	en
dc.subject.other	Contour detection	en
dc.subject.other	Diameter Measurement	en
dc.subject.other	Gradient vector flow	en
dc.subject.other	Gradient vector flow snakes	en
dc.subject.other	Image edge	en
dc.subject.other	Segmentation methods	en
dc.subject.other	Ultrasound images	en
dc.subject.other	Deformation	en
dc.subject.other	Hough transforms	en
dc.subject.other	Ultrasonic applications	en
dc.subject.other	Ultrasonics	en
dc.subject.other	Image segmentation	en
dc.title	Automated detection of the carotid artery wall in longitudinal B-mode images using active contours initialized by the Hough transform	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2011.6090106	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2011.6090106	en
heal.identifier.secondary	6090106	en
heal.publicationDate	2011	en
heal.abstract	In this paper, a fully automatic active-contour-based segmentation method is presented, for detecting the carotid artery wall in longitudinal B-mode ultrasound images. A Hough-transform-based methodology is used for the definition of the initial snake, followed by a gradient vector flow (GVF) snake deformation for the final contour detection. The GVF snake is based on the calculation of the image edge map and the calculation of GVF field which guides its deformation for the estimation of the real arterial wall boundaries. In twenty cases there was no significant difference between the automated segmentation and the manual diameter measurements. The sensitivity, specificity and accuracy were 0.97, 0.99 and 0.98, respectively, for both diastolic and systolic cases. In conclusion, the proposed methodology provides an accurate and reliable way to segment ultrasound images of the carotid artery. © 2011 IEEE.	en
heal.journalName	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS	en
dc.identifier.doi	10.1109/IEMBS.2011.6090106	en
dc.identifier.volume	2011	en
dc.identifier.spage	571	en
dc.identifier.epage	574	en