John Stoitsis

Automated detection of the carotid artery wall in B-mode ultrasound images using active contours initialized by the Hough transform

Automatic segmentation of the arterial lumen from ultrasound images is an important and often challenging task in clinical diagnosis. We previously used the Hough Transform (HT) to automatically extract circles from sequences of B-mode ultrasound images of transverse sections of the carotid artery. In this paper, an active-contour-based methodology is suggested, initialized by the HT circle, in an attempt to extend previous findings and to accurately detect the arterial wall boundary. The methodology is based on the generation of a gradient vector flow field, an approach attempting to overcome conventional active contours constraints. Contour estimation is then achieved by deforming the initial curve (circle) based on the gradient vector flow field. In ten normal subjects, the specificity and accuracy of the segmentation were on average higher than 0.98, whereas the sensitivity was higher than 0.82. The methodology was also applied to four subjects with atherosclerosis, in which sensitivity, specificity and accuracy were comparable to those of normal subjects. In conclusion, the HT-initialized active contours methodology provides a reliable tool to detect the carotid artery wall in ultrasound images and can be used in clinical practice.

Comparison of Kalman-filter-based approaches for block matching in arterial wall motion analysis from B-mode ultrasound

Block matching (BM) has been previously used to estimate motion of the carotid artery from B-mode ultrasound image sequences. In this paper, Kalman filtering (KF) was incorporated in this conventional method in two distinct scenarios: (a) as an adaptive strategy, by renewing the reference block and (b) by renewing the displacements estimated by BM or adaptive BM. All methods resulting from combinations of BM and KF with the two scenarios were evaluated on synthetic image sequences by computing the warping index, defined as the mean squared error between the real and estimated displacements. Adaptive BM, followed by an update through the second scenario at the end of tracking, ABM_KF-K2, minimized the warping index and yielded average displacement error reductions of 24% with respect to BM. The same method decreased estimation bias and jitter over varying center frequencies by 30% and 64%, respectively, with respect to BM. These results demonstrated the increased accuracy and robustness of ABM_KF-K2 in motion tracking of the arterial wall from B-mode ultrasound images, which is crucial in the study of mechanical properties of normal and diseased arterial segments.

Carotid artery wall motion analysis from B-mode ultrasound using adaptive block matching: in silico evaluation and in vivo application.

Valid risk stratification for carotid atherosclerotic plaques represents a crucial public health issue toward preventing fatal cerebrovascular events. Although motion analysis (MA) provides useful information about arterial wall dynamics, the identification of motion-based risk markers remains a significant challenge. Considering that the ability of a motion estimator (ME) to handle changes in the appearance of motion targets has a major effect on accuracy in MA, we investigated the potential of adaptive block matching (ABM) MEs, which consider changes in image intensities over time. To assure the validity in MA, we optimized and evaluated the ABM MEs in the context of a specially designed in silico framework. ABM(FIRF2), which takes advantage of the periodicity characterizing the arterial wall motion, was the most effective ABM algorithm, yielding a 47% accuracy increase with respect to the conventional block matching. The in vivo application of ABM(FIRF2) revealed five potential risk markers: low movement amplitude of the normal part of the wall adjacent to the plaques in the radial (RMA(PWL)) and longitudinal (LMA(PWL)) directions, high radial motion amplitude of the plaque top surface (RMA(PTS)), and high relative movement, expressed in terms of radial strain (RSI(PL)) and longitudinal shear strain (LSSI(PL)), between plaque top and bottom surfaces. The in vivo results were reproduced by OF(LK(WLS)) and ABM(KF-K2), MEs previously proposed by the authors and with remarkable in silico performances, thereby reinforcing the clinical values of the markers and the potential of those MEs. Future in vivo studies will elucidate with confidence the full potential of the markers.

Assessment of carotid atherosclerosis from B-mode ultrasound images using directional multiscale texture features

In this paper, three multiscale transforms with directional character, namely the dual-tree complex wavelet (DTCWT), the finite ridgelet (FRIT) and the fast discrete curvelet (FDCT) transforms, were comparatively assessed with respect to their ability to characterize carotid atherosclerotic plaque from B-mode ultrasound and discriminate between symptomatic and asymptomatic cases. The standard deviation and entropy of the detail subimages produced for each decomposition scheme were used as texture features. Feature selection included ranking the features according to their highest separability value and the minimum correlation among them. Due to the rather limited size of the sample population, the selected features were resampled 100 times by the bootstrap technique and divided into training and test sets. For each pair of sets, a support vector machine classifier was trained on the training set and evaluated on the test set. The average overall classification performance for systole (diastole) was 70% (65.2%), 72.6% (70.4%) and 84.9% (73.6%) for the DTCWT, FRIT and FDCT, respectively. These preliminary results showed the superiority of the curvelet transform, in terms of classification accuracy, being of great importance for the diagnosis and management of plaque instability in carotid atheromatous stenosis.

Carotid Artery Motion Estimation From Sequences of B-Mode Ultrasound Images: Effect of Scanner Settings and Image Normalization

The motion of the carotid artery wall can quantitatively be estimated from sequences of B-mode ultrasound images. In this paper, the effects of dynamic range (DR) and persistence, along with that of image normalization, were studied, in an attempt to suggest optimal values for reliable motion analysis. Image sequences were recorded using four different values for DR, i.e., 0, 48, 66, and 90 dB, and three different values for persistence, i.e., 0, 5.6, and 50. Radial and axial displacements, as well as the correlation coefficients (CCs), were estimated using block matching from recordings with durations of about 3 s. The variances of radial and axial displacements were not significantly affected by changes in DR and persistence. The mean value of the CC, which is an index of the reliability of motion analysis, was also not significantly affected by these settings. However, an increase in persistence increased the delays between peak radial displacements and cardiac systole. Image normalization did not affect the results of motion analysis. It is suggested that high values of DR (66 or 90 dB) and low values of persistence (0 or 5.6) are used for motion analysis based on block matching.

CAROTID - A web-based platform for optimal personalized management of atherosclerotic patients

Carotid atherosclerosis is the main cause of fatal cerebral ischemic events, thereby posing a major burden for public health and state economies. We propose a web-based platform named CAROTID to address the need for optimal management of patients with carotid atherosclerosis in a twofold sense: (a) objective selection of patients who need carotid-revascularization (i.e., high-risk patients), using a multifaceted description of the disease consisting of ultrasound imaging, biochemical and clinical markers, and (b) effective storage and retrieval of patient data to facilitate frequent follow-ups and direct comparisons with related cases. These two services are achieved by two interconnected modules, namely the computer-aided diagnosis (CAD) tool and the intelligent archival system, in a unified, remotely accessible system. We present the design of the platform and we describe three main usage scenarios to demonstrate the CAROTID utilization in clinical practice. Additionally, the platform was evaluated in a real clinical environment in terms of CAD performance, end-user satisfaction and time spent on different functionalities. CAROTID classification of high- and low-risk cases was 87%; the corresponding stenosis-degree-based classification would have been 61%. Questionnaire-based user satisfaction showed encouraging results in terms of ease-of-use, clinical usefulness and patient data protection. Times for different CAROTID functionalities were generally short; as an example, the time spent for generating the diagnostic decision was 5min in case of 4-s ultrasound video. Large datasets and future evaluation sessions in multiple medical institutions are still necessary to reveal with confidence the full potential of the platform.

Kalman-filter-based block matching for arterial wall motion estimation from B-mode ultrasound

The motion of the carotid artery wall has been previously estimated from ultrasound image sequences using block matching. In this paper, this conventional method was extended through its combination with Kalman filtering in two distinct scenarios; (a) by renewing the reference block and (b) by updating the estimate of the conventional algorithm. Both procedures were evaluated on synthetic image sequences through the estimation of the warping index. The results showed that incorporation of the Kalman filter in conventional block matching slightly improved the accuracy in arterial wall motion estimation. Updating the estimate of the conventional algorithm using Kalman filtering was the most efficient procedure and could be used to study further the displacements of the arterial wall in an attempt to obtain useful knowledge about arterial biomechanics.

Characterization of carotid atherosclerotic plaques using frequency-based texture analysis and bootstrap.

Texture analysis of B-mode ultrasound images of carotid atheromatous plaque can be valuable for the accurate diagnosis of atherosclerosis. In this paper, two frequency-based texture analysis methods based on the Fourier Power Spectrum and the Wavelet Transform were used to characterize atheromatous plaques. B-mode ultrasound images of 10 symptomatic and 9 asymptomatic plaques were interrogated. A total of 109 texture features were estimated for each plaque. The bootstrap method was used to compare the mean values of the texture features extracted from the two groups. After bootstrapping, three features were found to be significantly different between the two types of plaques: the average value of the angular distribution corresponding to the wedge centered at 90deg, the standard deviation at scale 1 derived from the horizontal detail image, and the standard deviation at scale 2 derived from the horizontal detail image. It is concluded that frequency-based texture analysis in combination with a powerful statistical technique, such as bootstrapping, may provide valuable information about the plaque tissue type

Texture characterization of carotid atherosclerotic plaque from B-mode ultrasound using gabor filters

Texture analysis of B-mode ultrasound images of carotid atheromatous plaque can be valuable for the accurate diagnosis of atherosclerosis. In this paper, Gabor filters were used to characterize the texture of carotid artery atherosclerotic tissue. B-mode ultrasound images of 10 symptomatic and 9 asymptomatic plaques were interrogated. A total of 40 texture features were estimated for each plaque. The bootstrap method was used to compare the mean values of the texture features extracted from the two groups. After bootstrapping, the mean value and the standard deviation of the energy estimated using the Gabor filters was found to be significantly different between symptomatic and asymptomatic plaques in the first scale of analysis and for all orientations. In addition, a number of texture features that correspond to larger resolution scales were found to be significantly different between the two types of plaques. It is concluded that Gabor-filter-based texture analysis in combination with a powerful statistical technique, such as bootstrapping, may provide valuable information about the plaque tissue type.

Discrete wavelet transform vs. wavelet packets for texture analysis of ultrasound images of carotid atherosclerosis

In this paper, a scale/frequency approach, based on the wavelet transform, was used in an attempt to characterize carotid atherosclerotic plaque from B-mode ultrasound. Two wavelet decomposition schemes, namely the discrete wavelet transform (DWT) and wavelet packets (WP), and three basis functions, namely Haar, symlet3 and biorthogonal3.1, were investigated in terms of their ability to discriminate between symptomatic and asymptomatic cases. A total of 12 detail sub-images were extracted using the DWT and 255 using the WP decomposition schemes. It was shown that WP analysis by the use of Haar filter and the l-1 norm as texture descriptor could reveal differences not only in high but also in low frequencies, and therefore characterize efficiently the atheromatous tissue. Additional studies applying and further extending the above methodology are required to ensure the usefulness of wavelet-based texture analysis of carotid atherosclerosis.