Multiscale geometric texture analysis of ultrasound images of carotid atherosclerosis

Tsiaparas, N; Golemati, S; Andreadis, I; Stoitsis, J; Nikita, KS

dc.contributor.author	Tsiaparas, N	en
dc.contributor.author	Golemati, S	en
dc.contributor.author	Andreadis, I	en
dc.contributor.author	Stoitsis, J	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T02:46:53Z
dc.date.available	2014-03-01T02:46:53Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32916
dc.subject	Carotid Artery	en
dc.subject	Classification Accuracy	en
dc.subject	Feature Selection	en
dc.subject	Standard Deviation	en
dc.subject	Support Vector Machine	en
dc.subject	Texture Analysis	en
dc.subject	Texture Features	en
dc.subject	Ultrasound	en
dc.subject	Ultrasound Imaging	en
dc.subject.other	Atherosclerotic plaque	en
dc.subject.other	Carotid artery	en
dc.subject.other	Classification accuracy	en
dc.subject.other	Classification performance	en
dc.subject.other	Curvelet transforms	en
dc.subject.other	Curvelets	en
dc.subject.other	Decomposition scheme	en
dc.subject.other	Feature selection	en
dc.subject.other	Geometric texture	en
dc.subject.other	Multiscales	en
dc.subject.other	Ridgelets	en
dc.subject.other	Sample population	en
dc.subject.other	Standard deviation	en
dc.subject.other	Subimages	en
dc.subject.other	Texture features	en
dc.subject.other	Ultrasound images	en
dc.subject.other	Discrete wavelet transforms	en
dc.subject.other	Information technology	en
dc.subject.other	Textures	en
dc.subject.other	Ultrasonics	en
dc.subject.other	Feature extraction	en
dc.title	Multiscale geometric texture analysis of ultrasound images of carotid atherosclerosis	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ITAB.2010.5687632	en
heal.identifier.secondary	5687632	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ITAB.2010.5687632	en
heal.publicationDate	2010	en
heal.abstract	In this paper two wavelet extension methods, the ridge let (DR1) and the fast discrete curvelet (FDC1) transforms, were used in an attempt to characterize carotid atherosclerotic plaque from B-mode ultrasound and discriminate between symptomatic and asymptomatic cases. The mean and standard deviation of the detail subimages produced for each decomposition scheme were used as texture features. Feature selection included ranking the features in terms of their divergence values. The selected features were subsequently input to a classifier using support vector machines. Both transforms produced an 82.5% overall classification performance (75% and 85% for systole and 90% and 80% for diastole for DRT and FDCT, respectively). Those preliminary results in a somewhat limited sample population showed that, in terms of classification accuracy of ultrasound images of the carotid artery, ridgelet and curvelet transforms are equivalent. The faster and most sensitive FDCT algorithm might be a reasonable choice. © 2010 IEEE.	en
heal.journalName	Proceedings of the IEEE/EMBS Region 8 International Conference on Information Technology Applications in Biomedicine, ITAB	en
dc.identifier.doi	10.1109/ITAB.2010.5687632	en