Christina I. Christodoulou

Texture-based classification of atherosclerotic carotid plaques

There are indications that the morphology of atherosclerotic carotid plaques, obtained by high-resolution ultrasound imaging, has prognostic implications. The objective of this study was to develop a computer-aided system that will facilitate the characterization of carotid plaques for the identification of individuals with asymptomatic carotid stenosis at risk of stroke. A total of 230 plaque images were collected which were classified into two types: symptomatic because of ipsilateral hemispheric symptoms, or asymptomatic because they were not connected with ipsilateral hemispheric events. Ten different texture feature sets were extracted from the manually segmented plaque images using the following algorithms: first-order statistics, spatial gray level dependence matrices, gray level difference statistics, neighborhood gray tone difference matrix, statistical feature matrix, Laws texture energy measures, fractal dimension texture analysis, Fourier power spectrum and shape parameters. For the classification task a modular neural network composed of self-organizing map (SOM) classifiers, and combining techniques based on a confidence measure were used. Combining the classification results of the ten SOM classifiers inputted with the ten feature sets improved the classification rate of the individual classifiers, reaching an average diagnostic yield (DY) of 73.1%. The same modular system was implemented using the statistical k-nearest neighbor (KNN) classifier. The combined DY for the KNN system was 68.8%. The results of this paper show that it is possible to identify a group of patients at risk of stroke based on texture features extracted from ultrasound images of carotid plaques. This group of patients may benefit from a carotid endarterectomy whereas other patients may be spared from an unnecessary operation.

Classification of atherosclerotic carotid plaques using morphological analysis on ultrasound images

Abstract The aim of this study was to investigate the usefulness of multilevel binary and gray scale morphological analysis in the assessment of atherosclerotic carotid plaques. Ultrasound images were recorded from 137 asymptomatic and 137 symptomatic plaques (Stroke, Transient Ischaemic Attack (TIA), Amaurosis Fugax (AF)). We carefully develop the clinical motivation behind our approach. We do this by relating the proposed L-images, M-images and H-images in terms of the clinically established hypoechoic, isoechoic and hyperechoic classification. Normalized pattern spectra were computed for both a structural, multilevel binary morphological model, and a direct gray scale morphology model. From the plots of the average pattern spectra, it is clear that we have significant differences between the symptomatic and asymptomatic spectra. Here, we note that the morphological measurements appear to be in agreement with the clinical assertion that symptomatic plaques tend to have large lipid cores while the asymptomatic plaques tend to have small lipid cores. The derived pattern spectra were used as classification features with two different classifiers, the Probabilistic Neural Network (PNN) and the Support Vector Machine (SVM). Both classifiers were used for classifying the pattern spectra into either a symptomatic or an asymptomatic class. The highest percentage of correct classifications score was 73.7% for multilevel binary morphological image analysis and 66.8% for gray scale morphological analysis. Both were achieved using the SVM classifier. Among all features, the L-image pattern spectra, that also measure the distributions of the lipid core components (and some non-lipid components) gave the best classification results.

Speckle reduction in ultrasound images of atherosclerotic carotid plaque

The objective of this work was to develop six speckle reduction-filtering techniques and evaluate them together with texture analysis in the assessment of 240 ultrasound images of the carotid artery. The de-speckled filters are based on anisotropic diffusion, local statistics with higher moments, and geometric filtering. Results showed that some improvement in class separation (between symptomatic and asymptomatic plaques) of the images was evident after de-speckle filtering.

De-speckle filtering in ultrasound imaging of the carotid artery

The main objective of this paper is to evaluate the classification performance of de-speckle filtering on ultrasound imaging of the carotid atherosclerotic plaque. The following procedure was investigated on 230 images (recorded from 115 symptomatic, and 115 asymptomatic subjects): (i) six different de-speckle filters were used based on first order and higher order local statistics, anisotropic diffusion, and geometric properties; (ii) nine different texture feature sets were extracted, and (iii) the k-nearest neighbor classifier was used to classify a plaque as symptomatic or asymptomatic. The despeckle filters based on higher order statistics, anisotropic speckle diffusion, and geometric properties gave a slightly higher percentage of correct classifications score than the original images.

Multi-feature texture analysis for the classification of carotid plaques

We develop a computer aided system which will facilitate the automated characterisation of carotid plaques recorded from high resolution ultrasound images for the identification of individuals with asymptomatic carotid stenosis at risk of stroke. The plaques were classified into: symptomatic or asymptomatic. Ten different texture feature sets were extracted from the segmented plaque image. Although the statistics of all features extracted for the two classes indicated a high degree of overlap, a classification of the plaques was possible using the unsupervised self-organizing feature map (SOFM) classifier and combining techniques. The classification results of the different feature sets were combined using the majority voting and weighted averaging based on a confidence measure derived from the SOFM. Combining the classification results of the ten different feature sets improved significantly the classification results obtained by the individual feature sets, reaching an average diagnostic yield of 75%.

A Modular Neural Network Decision Support System in EMG Diagnosis

Motor unit action potentials (MUAPs) recorded during routine electromyographic (EMG) examination provide important information for the assessment of neuromuscular disorders. The objective of this study was to design, develop, and test a decision support system which mimics the decision making process carried out by the expert neurophysiologist in MUAP analysis where: (i) the statistics of MUAP features are compared to normal reference values, and (ii) the individual MUAP waveforms are visually evaluated in sequence. The system consisted of the following two modular neural network subsystems. In the first subsystem, the statistics for each subject of multiple features extracted from the MUAP waveforms were fed into multiple classifiers, and the classification results were combined in order to improve the diagnostic yield. The feature sets computed, were: (i) the time domain parameters, (ii) the frequency domain parameters, (iii) the autoregressive coefficients, (iv) the cepstral coefficients and (v) the wavelet transform coefficients. The classifiers implemented were: (i) the back-propagation (BP), (ii) the radial basis function (RBF) network and (iii) the self-organising feature map

Classification of Atherosclerotic Carotid Plaques Using Gray Level Morphological Analysis on Ultrasound images

The aim of this study was to investigate the usefulness of gray scale morphological analysis in the assessment of atherosclerotic carotid plagues. Ultrasound images were recorded from 137 asymptomatic and 137 symptomatic plaques (Stroke, Transient Ischaemic Attack -TLA, Amaurosis Fugax-AF). The morphological pattern spectra of gray scale images were computed and two different classifiers named the Probabilistic Neural Network (PNN) and the Support Vector Machine (SVM) were evaluated for classifying these spectra into two classes: asymptomatic or symptomatic. The highest percentage of correct classifications score was 66,8% and was achieved using the SVM classifier. This score is slightly lower than texture analysis carried out on the same data set.

Multi-scale AM–FM analysis for the classification of surface electromyographic signals

Abstract In this work, multi-scale amplitude modulation–frequency modulation (AM–FM) features are extracted from surface electromyographic (SEMG) signals and they are used for the classification of neuromuscular disorders. The method is validated on SEMG signals recorded from a total of 40 subjects: 20 normal and 20 abnormal cases (11 myopathy, and 9 neuropathy cases), at 10%, 30%, 50%, 70% and 100% of maximum voluntary contraction (MVC), from the biceps brachii muscle. For the classification, three classifiers are used: (i) the statistical K-nearest neighbor (KNN), (ii) the self-organizing map (SOM) and (iii) the support vector machine (SVM). For all classifiers, the leave-one-out methodology is used to validate the classification of the SEMG signals into normal or abnormal (myopathy or neuropathy). A classification success rate of 78% for the AM–FM features and SVM models was achieved. These results also show that SEMG can be used as a non-invasive alternative to needle EMG for differentiating between normal and abnormal (myopathy, or neuropathy) cases.

A Comparative Study of Morphological and Other Texture Features for the Characterization of Atherosclerotic Carotid Plaques

The extraction of features characterizing the structure of atherosclerotic carotid plaques, obtained by high-resolution ultrasound imaging is important for the correct plaque classification and the estimation of the risk of stroke. In this study morphological features were extracted and compared with the well-known texture features spatial gray level dependence matrices (SGLDM), gray level difference statistics (GLDS) and the first order statistics (FOS) for the classification of 330 carotid plaques. For the classification the neural self-organizing map (SOM) classifier and the statistical k-nearest neighbor (KNN) classifier were used. The results showed that morphological and other texture features are comparable, with the morphological and the GLDS feature sets to perform slightly better than the SGLDM and the FOS features. The highest diagnostic yield was achieved with the GLDS feature set and it was about 70%.

Image Retrieval and Classification of Carotid Plaque Ultrasound Images

The extraction of multiple features from high-resolution ultrasound images of atherosclerotic carotid plaques, characterizing the plaque morphology and structure can be used for the classification and retrieval of similar plaques and the identification of individuals with asymptomatic carotid stenosis at risk of stroke. The objective of this work was to de- velop an automated image retrieval and classification system for the retrieval of similar carotid plaque ultrasound images, which will assist the physician in making his diagnostic decision based on similar previous cases. The neural self- organizing map (SOM) and the statistical K-nearest neighbor (KNN) classifiers were used for the retrieval and the classi- fication of the carotid plaques into symptomatic or asymptomatic. Twenty different feature sets including texture, shape, morphological, histogram and correlogram features were extracted from the carotid plaque images and the classification results were further combined in order to improve the success rate. The results on a dataset of 274 carotid plaque ultra- sound images show that image retrieval and classification for carotid plaque image are feasible and that features like multi-region histogram or texture can be used successfully for the identification of cases with similar symptoms output.