An automated technique for carotid far wall classification using grayscale features and wall thickness variability
PurposeTo test a computer-aided diagnostic method for differentiating symptomatic from asymptomatic carotid B-mode ultrasonographic images. MethodsOur system (called Atheromatic) automatically computed the intima-media thickness (IMT) of the carotid far wall using AtheroEdge, calculated nonlinear fe...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Published: |
Wiley Black
2015
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/15750/ http://www.ncbi.nlm.nih.gov/pubmed/24909942 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaya |
id |
my.um.eprints.15750 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.157502016-04-08T02:29:12Z http://eprints.um.edu.my/15750/ An automated technique for carotid far wall classification using grayscale features and wall thickness variability Acharya, U.R. Sree, S.V. Molinari, F. Saba, L. Nicolaides, A. Suri, J.S. T Technology (General) TA Engineering (General). Civil engineering (General) PurposeTo test a computer-aided diagnostic method for differentiating symptomatic from asymptomatic carotid B-mode ultrasonographic images. MethodsOur system (called Atheromatic) automatically computed the intima-media thickness (IMT) of the carotid far wall using AtheroEdge, calculated nonlinear features based on higher order spectra, and used these features and IMT and IMT variability (IMTVpoly) to associate each image to a feature vector that was then labeled as symptomatic or asymptomatic (Sym/Asym) by a multiclassifiers system. We tested this method on a database of 118 carotid artery images from 37 symptomatic and 22 asymptomatic patients ResultsThe highest accuracy (99.1) was obtained by the support vector machine classifier using seven features. These features, relevant to discriminate Sym/Asym, included IMT and IMTVpoly, along with the bispectral entropies of the distal wall image at 77 degrees, 78 degrees, and 79 degrees angles. ConclusionsClassification in Sym/Asym of the far carotid wall is feasible and accurate and could be useful for the early detection of atherosclerosis and to identify patients with higher cardiovascular risk. (c) 2014 Wiley Periodicals, Inc. J Clin Ultrasound 43:302-311, 2015 Wiley Black 2015-06 Article PeerReviewed Acharya, U.R. and Sree, S.V. and Molinari, F. and Saba, L. and Nicolaides, A. and Suri, J.S. (2015) An automated technique for carotid far wall classification using grayscale features and wall thickness variability. Journal of Clinical Ultrasound, 43 (5). pp. 302-311. ISSN 0091-2751 http://www.ncbi.nlm.nih.gov/pubmed/24909942 10.1002/jcu.22183 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
T Technology (General) TA Engineering (General). Civil engineering (General) |
spellingShingle |
T Technology (General) TA Engineering (General). Civil engineering (General) Acharya, U.R. Sree, S.V. Molinari, F. Saba, L. Nicolaides, A. Suri, J.S. An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
description |
PurposeTo test a computer-aided diagnostic method for differentiating symptomatic from asymptomatic carotid B-mode ultrasonographic images. MethodsOur system (called Atheromatic) automatically computed the intima-media thickness (IMT) of the carotid far wall using AtheroEdge, calculated nonlinear features based on higher order spectra, and used these features and IMT and IMT variability (IMTVpoly) to associate each image to a feature vector that was then labeled as symptomatic or asymptomatic (Sym/Asym) by a multiclassifiers system. We tested this method on a database of 118 carotid artery images from 37 symptomatic and 22 asymptomatic patients ResultsThe highest accuracy (99.1) was obtained by the support vector machine classifier using seven features. These features, relevant to discriminate Sym/Asym, included IMT and IMTVpoly, along with the bispectral entropies of the distal wall image at 77 degrees, 78 degrees, and 79 degrees angles. ConclusionsClassification in Sym/Asym of the far carotid wall is feasible and accurate and could be useful for the early detection of atherosclerosis and to identify patients with higher cardiovascular risk. (c) 2014 Wiley Periodicals, Inc. J Clin Ultrasound 43:302-311, 2015 |
format |
Article |
author |
Acharya, U.R. Sree, S.V. Molinari, F. Saba, L. Nicolaides, A. Suri, J.S. |
author_facet |
Acharya, U.R. Sree, S.V. Molinari, F. Saba, L. Nicolaides, A. Suri, J.S. |
author_sort |
Acharya, U.R. |
title |
An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
title_short |
An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
title_full |
An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
title_fullStr |
An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
title_full_unstemmed |
An automated technique for carotid far wall classification using grayscale features and wall thickness variability |
title_sort |
automated technique for carotid far wall classification using grayscale features and wall thickness variability |
publisher |
Wiley Black |
publishDate |
2015 |
url |
http://eprints.um.edu.my/15750/ http://www.ncbi.nlm.nih.gov/pubmed/24909942 |
_version_ |
1643690125915324416 |