Constantinos S. Pattichis

Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery

It is well-known that speckle is a multiplicative noise that degrades the visual evaluation in ultrasound imaging. The recent advancements in ultrasound instrumentation and portable ultrasound devices necessitate the need of more robust despeckling techniques for enhanced ultrasound medical imaging for both routine clinical practice and teleconsultation. The objective of this work was to carry out a comparative evaluation of despeckle filtering based on texture analysis, image quality evaluation metrics, and visual evaluation by medical experts in the assessment of 440 (220 asymptomatic and 220 symptomatic) ultrasound images of the carotid artery bifurcation. In this paper a total of 10 despeckle filters were evaluated based on local statistics, median filtering, pixel homogeneity, geometric filtering, homomorphic filtering, anisotropic diffusion, nonlinear coherence diffusion, and wavelet filtering. The results of this study suggest that the first order statistics filter lsmv, gave the best performance, followed by the geometric filter gf4d, and the homogeneous mask area filter lsminsc. These filters improved the class separation between the asymptomatic and the symptomatic classes based on the statistics of the extracted texture features, gave only a marginal improvement in the classification success rate, and improved the visual assessment carried out by the two experts. More specifically, filters lsmv or gf4d can be used for despeckling asymptomatic images in which the expert is interested mainly in the plaque composition and texture analysis; and filters lsmv, gf4d, or lsminsc can be used for the despeckling of symptomatic images in which the expert is interested in identifying the degree of stenosis and the plaque borders. The proper selection of a despeckle filter is very important in the enhancement of ultrasonic imaging of the carotid artery. Further work is needed to evaluate at a larger scale and in clinical practice the performance of the proposed despeckle filters in the automated segmentation, texture analysis, and classification of carotid ultrasound imaging.

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.

Snakes based segmentation of the common carotid artery intima media

Ultrasound measurements of the human carotid artery walls are conventionally obtained by manually tracing interfaces between tissue layers. In this study we present a snakes segmentation technique for detecting the intima-media layer of the far wall of the common carotid artery (CCA) in longitudinal ultrasound images, by applying snakes, after normalization, speckle reduction, and normalization and speckle reduction. The proposed technique utilizes an improved snake initialization method, and an improved validation of the segmentation method. We have tested and clinically validated the segmentation technique on 100 longitudinal ultrasound images of the carotid artery based on manual measurements by two vascular experts, and a set of different evaluation criteria based on statistical measures and univariate statistical analysis. The results showed that there was no significant difference between all the snakes segmentation measurements and the manual measurements. For the normalized despeckled images, better snakes segmentation results with an intra-observer error of 0.08, a coefficient of variation of 12.5%, best Bland–Altman plot with smaller differences between experts (0.01, 0.09 for Expert1 and Expert 2, respectively), and a Hausdorff distance of 5.2, were obtained. Therefore, the pre-processing of ultrasound images of the carotid artery with normalization and speckle reduction, followed by the snakes segmentation algorithm can be used successfully in the measurement of IMT complementing the manual measurements. The present results are an expansion of data published earlier as an extended abstract in IFMBE Proceedings (Loizou et al. IEEE Int X Mediterr Conf Medicon Med Biol Eng POS-03 499:1–4, 2004).

Unsupervised pattern recognition for the classification of EMG signals

The shapes and firing rates of motor unit action potentials (MUAPs) in an electromyographic (EMG) signal provide an important source of information for the diagnosis of neuromuscular disorders. In order to extract this information from EMG signals recorded at low to moderate force levels, it is required: i) to identify the MUAPs composing the EMG signal, ii) to classify MUAPs with similar shape, and iii) to decompose the superimposed MUAP waveforms into their constituent MUAPs. For the classification of MUAPs two different pattern recognition techniques are presented: i) an artificial neural network (ANN) technique based on unsupervised learning, using a modified version of the self-organizing feature maps (SOFM) algorithm and learning vector quantization (LVQ) and ii) a statistical pattern recognition technique based on the Euclidean distance. A total of 1213 MUAPs obtained from 12 normal subjects, 13 subjects suffering from myopathy, and 15 subjects suffering from motor neuron disease were analyzed. The success rate for the ANN technique was 97.6% and for the statistical technique 95.3%. For the decomposition of the superimposed waveforms, a technique using crosscorrelation for MUAPs alignment, and a combination of Euclidean distance and area measures in order to classify the decomposed waveforms is presented. The success rate for the decomposition procedure was 90%.

Neural network models in EMG diagnosis

In previous years, several computer-aided quantitative motor unit action potential (MUAP) techniques were reported. It is now possible to add to these techniques the capability of automated medical diagnosis so that all data can be processed in an integrated environment. In this study, the parametric pattern recognition (PPR) algorithm that facilitates automatic MUAP feature extraction and Artificial Neural Network (ANN) models are combined for providing an integrated system for the diagnosis of neuromuscular disorders. Two paradigms of learning for training ANN models were investigated, supervised, and unsupervised. For supervised learning, the back-propagation algorithm and for unsupervised learning, the Kohonens self-organizing feature maps algorithm were used. The diagnostic yield for models trained with both procedures was similar and on the order of 80%. However, back propagation models required considerably more computational effort compared to the Kohonens self-organizing feature map models. Poorer diagnostic performance was obtained when the K-means nearest neighbor clustering algorithm was applied on the same set of data. >

Assessment of the Risk Factors of Coronary Heart Events Based on Data Mining With Decision Trees

Coronary heart disease (CHD) is one of the major causes of disability in adults as well as one of the main causes of death in the developed countries. Although significant progress has been made in the diagnosis and treatment of CHD, further investigation is still needed. The objective of this study was to develop a data-mining system for the assessment of heart event-related risk factors targeting in the reduction of CHD events. The risk factors investigated were: 1) before the event: a) nonmodifiable-age, sex, and family history for premature CHD, b) modifiable-smoking before the event, history of hypertension, and history of diabetes; and 2) after the event: modifiable-smoking after the event, systolic blood pressure, diastolic blood pressure, total cholesterol, high-density lipoprotein, low-density lipoprotein, triglycerides, and glucose. The events investigated were: myocardial infarction (MI), percutaneous coronary intervention (PCI), and coronary artery bypass graft surgery (CABG). A total of 528 cases were collected from the Paphos district in Cyprus, most of them with more than one event. Data-mining analysis was carried out using the C4.5 decision tree algorithm for the aforementioned three events using five different splitting criteria. The most important risk factors, as extracted from the classification rules analysis were: 1) for MI, age, smoking, and history of hypertension; 2) for PCI, family history, history of hypertension, and history of diabetes; and 3) for CABG, age, history of hypertension, and smoking. Most of these risk factors were also extracted by other investigators. The highest percentages of correct classifications achieved were 66%, 75%, and 75% for the MI, PCI, and CABG models, respectively. It is anticipated that data mining could help in the identification of high and low risk subgroups of subjects, a decisive factor for the selection of therapy, i.e., medical or surgical. However, further investigation with larger datasets is still needed.

Time-scale analysis of motor unit action potentials

Quantitative analysis in clinical electromyography (EMG) is very desirable because it allows a more standardized, sensitive and specific evaluation of the neurophysiological findings, especially for the assessment of neuromuscular disorders. Following the recent development of computer-aided EMC equipment, different methodologies in the time domain and frequency domain have been followed for quantitative analysis. In this study, the usefulness of the wavelet transform (WT), that provides a linear time-scale representation is investigated, for describing motor unit action potential (MUAP) morphology. The motivation behind the use of the WT is that it provides localized statistical measures (the scalogram) for nonstationary signal analysis. The following four WTs were investigated in analyzing a total of 800 MUAPs recorded from 12 normal subjects, 15 subjects suffering with motor neuron disease, and 13 from myopathy: Daubechies with four and 20 coefficients, Chui (CH), and Battle-Lemarie (BL). The results are summarized as follows: 1) most of the energy of the MUAP signal is distributed among a small number of well-localized (in time) WT coefficients in the region of the main spike, 2) for MUAP signals, the authors look to the low-frequency coefficients for capturing the average waveshape of the MUAP signal over long durations, and the authors look to the high-frequency coefficients for locating MUAP spike changes, 3) the Daubechies 4 wavelet, is effective in tracking the transient components of the MUAP signal, 4) the linear spline CH (semiorthogonal) wavelet provides the best MUAP signal approximation by capturing most of the energy in the lowest resolution approximation coefficients, and 5) neural network BY (DY) of Daubechies 4 and BL WT coefficients was in the region of 66%, whereas BY for the empirically determined time domain feature set was 78%. In conclusion, wavelet analysis provides a new way in describing MUAP morphology in the time-frequency plane. This method allows for the fast extraction of localized frequency components, which when combined with time domain analysis into a modular neural network decision support system enhances further the BY to 82.5% aiding the neurophysiologist in the early and accurate diagnosis of neuromuscular disorders.

An Integrated System for the Segmentation of Atherosclerotic Carotid Plaque

The robust border identification of atherosclerotic carotid plaque, the corresponding degree of stenosis of the common carotid artery (CCA), and also the characteristics of the arterial wall, including plaque size, composition, and elasticity, have significant clinical relevance for the assessment of future cardiovascular events. To facilitate the follow-up and analysis of the carotid stenosis in serial clinical investigations, we propose and evaluate an integrated system for the segmentation of atherosclerotic carotid plaque in ultrasound videos of the CCA based on video frame normalization, speckle reduction filtering, M-mode state-based identification, parametric active contours, and snake segmentation. Initially, the cardiac cycle in each video is identified and the video M-mode is generated, thus identifying systolic and diastolic states. The video is then segmented for a time period of at least one full cardiac cycle. The algorithm is initialized in the first video frame of the cardiac cycle, with human assistance if needed, and the moving atherosclerotic plaque borders are tracked and segmented in the subsequent frames. Two different initialization methods are investigated in which initial contours are estimated every 20 video frames. In the first initialization method, the initial snake contour is estimated using morphology operators; in the second initialization method, the Chan-Vese active contour model is used. The performance of the algorithm is evaluated on 43 real CCA digitized videos from B-mode longitudinal ultrasound segments and is compared with the manual segmentations of an expert, available every 20 frames in a time span of 3 to 5 s, covering, in general, 2 cardiac cycles. The segmentation results were very satisfactory, according to the expert objective evaluation, for the two different methods investigated, with true-negative fractions (TNF-specificity) of 83.7 ± 7.6% and 84.3 ± 7.5%; true-positive fractions (TPF-sensitivity) of 85.42 ± 8.1% and 86.1 ± 8.0%; and between the ground truth and the proposed segmentation method, kappa indices (KI) of 84.6% and 85.3% and overlap indices of 74.7% and 75.4%. The segmentation contours were also used to compute the cardiac state identification and radial, longitudinal, and shear strain indices for the CCA wall and plaque between the asymptomatic and symptomatic groups were investigated. The results of this study show that the integrated system investigated in this study can be successfully used for the automated video segmentation of the CCA plaque in ultrasound videos.

Despeckle Filtering Algorithms and Software for Ultrasound Imaging

Abstract It is well-known that speckle is a multiplicative noise that degrades image quality and the visual evaluation in ultrasound imaging. This necessitates the need for robust despeckling techniques for both routine clinical practice and teleconsultation. The goal for this book is to introduce the theoretical background (equations), the algorithmic steps, and the MATLAB™ code for the following group of despeckle filters: linear filtering, nonlinear filtering, anisotropic diffusion filtering and wavelet filtering. The book proposes a comparative evaluation framework of these despeckle filters based on texture analysis, image quality evaluation metrics, and visual evaluation by medical experts, in the assessment of cardiovascular ultrasound images recorded from the carotid artery. The results of our work presented in this book, suggest that the linear local statistics filter DsFlsmv, gave the best performance, followed by the nonlinear geometric filter DsFgf4d, and the linear homogeneous mask area filte...

Quality evaluation of ultrasound imaging in the carotid artery based on normalization and speckle reduction filtering

Image quality is important when evaluating ultrasound images of the carotid for the assessment of the degree of atherosclerotic disease, or when transferring images through a telemedicine channel, and/or in other image processing tasks. The objective of this study was to investigate the usefulness of image quality evaluation based on image quality metrics and visual perception, in ultrasound imaging of the carotid artery after normalization and speckle reduction filtering. Image quality was evaluated based on statistical and texture features, image quality evaluation metrics, and visual perception evaluation made by two experts. These were computed on 80 longitudinal ultrasound images of the carotid bifurcation recorded from two different ultrasound scanners, the HDI ATL-3000 and the HDI ATL-5000 scanner, before (NF) and after (DS) speckle reduction filtering, after normalization (N), and after normalization and speckle reduction filtering (NDS). The results of this study showed that: (1) the normalized speckle reduction, NDS, images were rated visually better on both scanners; (2) the NDS images showed better statistical and texture analysis results on both scanners; (3) better image quality evaluation results were obtained between the original (NF) and normalized (N) images, i.e. NF–N, for both scanners, followed by the NF–DS images for the ATL HDI-5000 scanner and the NF–DS on the HDI ATL-3000 scanner; (4) the ATL HDI-5000 scanner images have considerable higher entropy than the ATL HDI-3000 scanner and thus more information content. However, based on the visual evaluation by the two experts, both scanners were rated similarly. The above findings are also in agreement with the visual perception evaluation, carried out by the two vascular experts. The results of this study showed that ultrasound image normalization and speckle reduction filtering are important preprocessing steps favoring image quality, and should be further investigated.