Computerized Texture Analysis of Carotid Plaque Ultrasonic Images Can Identify Unstable Plaques Associated With Ipsilateral Neurological Symptoms (original) (raw)
Related papers
2011
Abstract Carotid plaques have been associated with ipsilateral neurological symptoms. High-resolution ultrasound can provide information not only on the degree of carotid artery stenosis but also on the characteristics of the arterial wall including the size and consistency of atherosclerotic plaques. The aim of this study was to determine cerebrovascular risk stratification based on ultrasonic plaque texture features and clinical features in patients with asymptomatic internal carotid artery (ICA) stenosis.
There are indications that the texture of certain components of atherosclerotic carotid plaques in the common carotid artery (CCA), obtained by high resolution ultrasound imaging, may have additional prognostic implication for the risk of stroke. The objective of this study was to perform texture analysis of the middle component of atherosclerotic carotid plaques in 230 CCA plaque ultrasound images (115 asymptomatic and 115 symptomatic). These were manually delineated by a neurovascular expert after normalization and despeckle filtering using the linear despeckle filter (DsFlsmv). Texture features were extracted from the middle plaque component. We found statistical significant differences for some of the texture features extracted, between asymptomatic and symptomatic subjects. The results showed that it may be possible to identify a group of patients at risk of stroke (asymptomatic versus symptomatic) based on texture features extracted from the middle component of the atheroscler...
Electrical Engineering & Applied Signal Processing Series, 2005
There are indications that the texture of certain components of atherosclerotic carotid plaques in the common carotid artery (CCA), obtained by high resolution ultrasound imaging, may have additional prognostic implication for the risk of stroke. The objective of this study was to perform texture analysis of the middle component of atherosclerotic carotid plaques in 230 CCA plaque ultrasound images (115 asymptomatic and 115 symptomatic). These were manually delineated by a neurovascular expert after normalization and despeckle filtering using the linear despeckle filter (DsFlsmv). Texture features were extracted from the middle plaque component. We found statistical significant differences for some of the texture features extracted, between asymptomatic and symptomatic subjects. The results showed that it may be possible to identify a group of patients at risk of stroke (asymptomatic versus symptomatic) based on texture features extracted from the middle component of the atherosclerotic carotid plaque in ultrasound images of the CCA.
Selection of parameters for texture analysis for the classification of carotid plaques
IEEE Trans Med Imaging, 2003
Abstract: Texture features extracted from high-resolution ultrasound images of carotid plaques can be used for the identification of patients at risk of stroke. This work explores the selection of the parameters for the computation of the texture features, which will yield the best class separation between symptomatic and asymptomatic subjects. The following texture algorithms were investigated on 230 carotid plaque images (recorded from 115 symptomatic and 115 asymptomatic subjects): Spatial Gray Level Dependence Matrices ( ...
Prediction of High-Risk Asymptomatic Carotid Plaques Based on Ultrasonic Image Features
IEEE Transactions on Information Technology in Biomedicine, 2012
Carotid plaques have been associated with ipsilateral neurological symptoms. High-resolution ultrasound can provide information not only on the degree of carotid artery stenosis but also on the characteristics of the arterial wall including the size and consistency of atherosclerotic plaques. The aim of this study is to determine whether the addition of ultrasonic plaque texture features to clinical features in patients with asymptomatic internal carotid artery stenosis (ACS) improves the ability to identify plaques that will produce stroke. 1121 patients with ACS have been scanned with ultrasound and followed for a mean of 4 years. It is shown that the combination of texture features based on secondorder statistics spatial gray level dependence matrices (SGLDM) and clinical factors improves stroke prediction (by correctly predicting 89 out of the 108 cases that were symptomatic). Here, the best classification results of 77 ± 1.8% were obtained from the use of the SGLDM texture features with support vector machine classifiers. The combination of morphological features with clinical features gave slightly worse classification results of 76 ± 2.6%. These findings need to be further validated in additional prospective studies. Index Terms-Assessment of stroke risk, plaque imaging, ultrasound image analysis. I. INTRODUCTION A therosclerosis of the internal carotid artery (ICA) is an important risk factor for stroke. Using the North American symptomatic carotid endarterectomy trial method [1] for the determination of stenosis the risk of stroke has been shown to range between 0.1-1.6% per year for asymptomatic individuals with ICA stenosis <75-80%. The risk rises to 2-3%
Computer based analysis of ultrasound images for assessing carotid artery plaque risk
2003
To design and implement a computer based image analysis system, employing pattern recognition methods on ultrasound images, for assessing carotid plaque risk of causing brain infarcts. Materials and methods: Sixty-one ultrasound images displaying carotid artery stenosis were selected by an HDI-3000 ATL digital ultrasound system. Plaques were categorized on the basis of the gray scale median (GSM) as echolucent (GSMSSO gray level), with high risk of causing brain infarcts, and echogenic (GSM>SO gray level) and in accordance with the physician's assessment and final clinical outcome. Thirty-eight textural features were calculated ?om the carotid plaque's image, 4 ?om the image histogram, 28 j?om the co-occurrence matrix, and I O ?om the run-length matrix. Two classi$er.v. the least squares minimum distance (LSMDI and the support vector machines (SVM) were employed for comparison reasons. Textural features were employed as input to the class$ers. which were trained to characterize plaques as either high risk or low risk of causing brain infarcts. Results: SVM classr$cation accuracy was 96.7% employing the following twa textural features: (a) mean gray-level and (b) image contrast, a measure of local variations present in the image, from !he co-occurrence matrix. Comparatively, LSMD classification precision, employing the same textural feature combination, was 86.9%. Conclusion: The proposed image analysis system, employing textural features and the SVM classifier, may be indicative of carotid plaque risk of causing brain infarcts and may be of value to patient management.
Journal of Neuroimaging, 2009
BACKGROUND AND PURPOSE To determine the correlation between carotid plaque morphology, assessed by two different ultrasonographic methods, and presence of cerebrovascular events and/or lesions on magnetic resonance imaging (MRI). PATIENTS AND METHODS Visual analysis of plaque echogenicity using a five-type classification was performed. Further, a semi-automated gray-scale-based color mapping of the whole plaque and of its surface was achieved. RESULTS There were 31 (35%) symptomatic (23 strokes and 8 transitory ischemic attacks [TIAs]) and 58 (65%) asymptomatic carotid stenoses. MRI lesions related to the carotid stenosis if located in the ipsilateral cortical, subcortical, or watershed area, were present in 27 cases (30%). In a multivariate logistic regression model, degree of stenosis (P = .03) and a predominant red color on the surface (P = .04) were independent factors associated with the presence of cerebrovascular events and/or lesions on MRI. Sensitivity and specificity were, respectively, 80% and 63% by combining degree of stenosis and color mapping of plaque surface. CONCLUSION Degree of stenosis and a predominant red color on plaque surface were independent factors associated with the presence of cerebrovascular events and/or lesions on MRI. No correlation was observed with any particular type of plaque based on visual analysis alone.
Texture Analysis for the Classification of Carotid Plaques
1998
Abstract The objective of this work is to develop a computer aided system which will facilitate the automated characterization of carotid plaques recorded from high resolution ultrasound images for the identification of individuals with asymptomatic carotid stenosis at risk of stroke. The system consists of the following four modules:(i) image standardization,(ii) image segmentation,(iii) feature extraction and selection,(iv) plaque classification.