A review of noninvasive ultrasound image processing methods in the analysis of carotid plaque morphology for the assessment of stroke risk

Assessing the impact of ultrasound image standardization in deep learning-based segmentation of carotid plaque types

BACKGROUND AND OBJECTIVE

Carotid B-mode ultrasound (CBUS) imaging is often used to detect and assess atherosclerotic plaques. Doctors often need to segment plaques in the CBUS images to further examine them. Multiple studies have proposed two-dimensional CBUS plaque segmentation deep learning (DL)-based solutions, achieving promising results. In most of these studies, image standardization is not reported, while not all plaque types are represented. However, prior multiple studies have highlighted the importance of data standardization in computerized CBUS plaque classification or segmentation solutions. In this study, we propose and separately evaluate three progressive preprocessing schemes, to discover the most optimal to standardize CBUS images for DL-based carotid plaque segmentation, while we also assess the effect of each preprocessing in the segmentation performance per echodensity-based plaque type (I, II, III, IV and V).

METHODS

We included three CBUS image datasets (276 CBUS images, from three medical centres), with which we produced 3 data folds (with the best possible equal inclusion of images from all centers per fold), to perform 3-fold cross validation-based training and evaluation of the pre-released Channel-wise Feature Pyramid Network for Medicine (CFPNet-M) model, in carotid plaque type segmentation. We included the three data folds in their original version (O), generating also three preprocessed versions of them, namely, the resolution-normalized (R), the resolution- and intensity-normalized (RN), and the resolution- and intensity-normalized combined with despeckling (RND) versions. The samples were cropped to the plaque level, and the intersection over union (IoU) and the Dice Similarity Coefficient (DSC), along with other metrics, were used to measure the model's performance. In each training round, 12 % of the images in the 2 training folds was used for internal validation (last fold was used in evaluation). Two experienced ultrasonographers manually delineated plaques in the dataset, to provide us with ground truths, while the plaque types (I to V) were extracted according to the Gray-Weale and Geroulakos classification system. We measured the mean±standard deviation of DSC within and across the three evaluated folds, per preprocessing scheme and per plaque type.

RESULTS

CFPNet-M segmented the plaques in the CBUS images in all the data preprocessing versions, yielding progressively improved performances (mean DSC at 81.9 ± 9.1 %, 83.6 ± 9.0 %, 84.1 ± 8.3 %, and 84.4 ± 8.1 % for the O, R, RN and RND 3-fold cross validation processes, respectively), irrespective of the plaque type. Interestingly, CFPNet_M yielded improved performances, for all plaque types (I, II, III, IV and V), when trained and tested with the RND data versus the O version, achieving an 80.6 ± 11 % versus 77.6 ± 17 % DSC for type I, an 84.3 ± 8 % versus 81.2 ± 9 % DSC for type II, an 84.9 ± 7 % versus 82.6 ± 7 % for type III, an 85.3 ± 8 % versus 83.9 ± 7 % for type IV, and a 84.8 ± 8 % versus 81.8 ± 2 % for type V. The best increase in DSC, from the O to the RND CBUS images, was found for the plaque type I (3.86 % increase), with types II and V, following.

CONCLUSIONS

In this study, we investigated the impact of CBUS standardization in DL-based carotid plaque type segmentation and showed that indeed normalization of the image resolution and intensity, combined with speckle noise removal, prior to model training and testing, enhances the DL model's performance, across all plaque types. Based on the findings in this study, CBUS images should be standardized when destined for DL-based segmentation tasks, while all plaque types should be considered, as in a plethora of existing relevant studies, uniformly echolucent plaques or heavily calcified plaques with acoustic shadow are notably underrepresented.

Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data

BACKGROUND

The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms.

METHODOLOGY

500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0HDL was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge™ 3.0HDL was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data.

RESULTS

The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0HDL showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards.

CONCLUSIONS

The hypothesis for AtheroEdge™ 3.0HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.

Predictive stroke risk model with vision transformer-based Doppler features

BACKGROUND

Acute stroke is the leading cause of death and disability globally, with an estimated 16 million cases each year. The progression of carotid stenosis reduces blood flow to the intracranial vasculature, causing stroke. Early recognition of ischemic stroke is crucial for disease treatment and management.

PURPOSE

A computer-aided diagnosis (CAD) system was proposed in this study to rapidly evaluate ischemic stroke in carotid color Doppler (CCD).

METHODS

Based on the ground truth from the clinical examination report, the vision transformer (ViT) features extracted from all CCD images (513 stroke and 458 normal images) were combined in machine learning classifiers to generate the likelihood of ischemic stroke for each image. The pretrained weights from ImageNet reduced the time-consuming training process. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were calculated to evaluate the stroke prediction model. The chi-square test, DeLong test, and Bonferroni correction for multiple comparisons were applied to deal with the type-I error. Only p values equal to or less than 0.00125 were considered to be statistically significant.

RESULTS

The proposed CAD system achieved an accuracy of 89%, a sensitivity of 94%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.95, outperforming the convolutional neural networks AlexNet (82%, p < 0.001), Inception-v3 (78%, p < 0.001), ResNet101 (84%, p < 0.001), and DenseNet201 (85%, p < 0.01). The computational time in model training was only 30 s, which would be efficient and practical in clinical use.

CONCLUSIONS

The experiment shows the promising use of CCD images in stroke estimation. Using the pretrained ViT architecture, the image features can be automatically and efficiently generated without human intervention. The proposed CAD system provides a rapid and reliable suggestion for diagnosing ischemic stroke.

Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer

BACKGROUND

Numerous features are commonly generated in radiomics applications as applied to medical imaging, and identification of robust radiomics features (RFs) can be an important step to derivation of reliable, reproducible solutions. In this work, we utilize a tensor radiomics (TR) framework, where numerous fusions are explored, to generate different flavours of RFs, and we aimed to identify RFs that are robust to fusion techniques in head and neck cancer. Overall, we aimed to predict progression-free survival (PFS) using Hybrid Machine Learning Systems (HMLS) and reproducible RFs.

METHODS

The study was performed on 408 patients with head and neck cancer from The Cancer Imaging Archive. After image preprocessing, 15 fusion techniques were employed to combine Positron Emission Tomography (PET) and Computed Tomography (CT) images. Subsequently, 215 RFs were extracted through a standardized radiomics software, with 17 'flavours' generated using PET-only, CT-only, and 15 fused PET&CT images. The variability of RFs across flavours was studied using the Intraclass Correlation Coefficient (ICC). Furthermore, the features were categorized into seven reliability groups, 106 reproducible RFs with ICC>0.75 were selected, highly correlated flavours were removed, Principal Component Analysis was used to convert 17 flavours to 1 attribute, the polynomial function was utilized to increase RFs, and Analysis of variance (ANOVA) was used to select the relevant attributes. Finally, 3 classifiers including Random Forest (RFC), Logistic regression (LR), and Multi-layer perceptron were applied to the preselected relevant attributes to predict binary PFS. In 5-fold cross-validation, 80% of 4 divisions were utilized to train the model, and the remaining 20% was utilized to evaluate the model. Further, the remaining fold was used for external nested testing.

RESULTS

Reliability analysis indicated that most morphological features belong to the high-reliability category. By contrast, local intensity and statistical features extracted from images belong to the low-reliability category. In the tensor framework, the highest 5-fold cross-validation accuracy of 76.7%±3.3% with an external nested testing of 70.6%±6.7% resulted from the reproducible TR+polynomial function+ANOVA+LR algorithm while the accuracy of 70.0%±4.2% with the external nested testing of 67.7%±4.9% was achieved through the PCA fusion+RFC (non-tensor paradigm).

CONCLUSIONS

This study demonstrated that using reproducible RFs as utilized within a tensor fusion radiomics framework, linked with ANOVA and LR, added value to prediction of progression-free survival outcome in head and neck cancer patients.

The latest application progress of radiomics in prediction and diagnosis of liver diseases

INTRODUCTION

Early detection and individualized treatment of patients with liver disease is the key to survival. Radiomics can extract high-throughput quantitative features by multimode imaging, which has good application prospects for the diagnosis, staging and prognosis of benign and malignant liver diseases. Therefore, this paper summarizes the current research status in the field of liver disease, in order to help these patients achieve personalized and precision medical care.

AREAS COVERED

This paper uses several keywords on the PubMed database to search the references, and reviews the workflow of traditional radiomics, as well as the characteristics and influencing factors of different imaging modes. At the same time, the references on the application of imaging in different benign and malignant liver diseases were also summarized.

EXPERT OPINION

For patients with liver disease, the traditional imaging evaluation can only provide limited information. Radiomics exploits the characteristics of high-throughput and high-dimensional extraction, enabling liver imaging capabilities far beyond the scope of traditional visual image analysis. Recent studies have demonstrated the prospect of this technology in personalized diagnosis and treatment decision in various fields of the liver. However, further clinical validation is needed in its application and practice.

Plaque Evaluation by Ultrasound and Transcriptomics Reveals BCLAF1 as a Regulator of Smooth Muscle Cell Lipid Transdifferentiation in Atherosclerosis

BACKGROUND

Understanding the processes behind carotid plaque instability is necessary to develop methods for identification of patients and lesions with stroke risk. Here, we investigated molecular signatures in human plaques stratified by echogenicity as assessed by duplex ultrasound.

METHODS

Lesion echogenicity was correlated to microarray gene expression profiles from carotid endarterectomies (n=96). The findings were extended into studies of human and mouse atherosclerotic lesions in situ, followed by functional investigations in vitro in human carotid smooth muscle cells (SMCs).

RESULTS

Pathway analyses highlighted muscle differentiation, iron homeostasis, calcification, matrix organization, cell survival balance, and BCLAF1 (BCL2 [B-cell lymphoma 2]-associated transcription factor 1) as the most significant signatures. BCLAF1 was downregulated in echolucent plaques, positively correlated to proliferation and negatively to apoptosis. By immunohistochemistry, BCLAF1 was found in normal medial SMCs. It was repressed early during atherogenesis but reappeared in CD68+ cells in advanced plaques and interacted with BCL2 by proximity ligation assay. In cultured SMCs, BCLAF1 was induced by differentiation factors and mitogens and suppressed by macrophage-conditioned medium. BCLAF1 silencing led to downregulation of BCL2 and SMC markers, reduced proliferation, and increased apoptosis. Transdifferentiation of SMCs by oxLDL (oxidized low-denisty lipoprotein) was accompanied by upregulation of BCLAF1, CD36, and CD68, while oxLDL exposure with BCLAF1 silencing preserved MYH (myosin heavy chain) 11 expression and prevented transdifferentiation. BCLAF1 was associated with expression of cell differentiation, contractility, viability, and inflammatory genes, as well as the scavenger receptors CD36 and CD68. BCLAF1 expression in CD68+/BCL2+ cells of SMC origin was verified in plaques from MYH11 lineage-tracing atherosclerotic mice. Moreover, BCLAF1 downregulation associated with vulnerability parameters and cardiovascular risk in patients with carotid atherosclerosis.

CONCLUSIONS

Plaque echogenicity correlated with enrichment of distinct molecular pathways and identified BCLAF1, previously not described in atherosclerosis, as the most significant gene. Functionally, BCLAF1 seems necessary for survival and transdifferentiation of SMCs into a macrophage-like phenotype. The role of BCLAF1 in plaque vulnerability should be further evaluated.

Can we use radiomics in ultrasound imaging? Impact of preprocessing on feature repeatability

PURPOSE

The purpose of this study was to assess the inter-slice radiomic feature repeatability in ultrasound imaging and the impact of preprocessing using intensity standardization and grey-level discretization to help improve radiomics reproducibility.

MATERIALS AND METHODS

This single-center study enrolled consecutive patients with an orbital lesion who underwent ultrasound examination of the orbit from December 2015 to July 2019. Two images per lesion were randomly assigned to two subsets. Radiomic features were extracted and inter-slice repeatability was assessed using the intraclass correlation coefficient (ICC) between the subsets. The impact of preprocessing on feature repeatability was assessed using image intensity standardization with or without outliers removal on whole images, bounding boxes or regions of interest (ROI), and fixed bin size or fixed bin number grey-level discretization. Number of inter-slice repeatable features (ICC ≥0.7) between methods was compared.

RESULTS

Eighty-eight patients (37 men, 51 women) with a mean age of 51.5 ± 17 (SD) years (range: 20-88 years) were enrolled. Without preprocessing, 29/101 features (28.7%) were repeatable between slices. The greatest number of repeatable features (41/101) was obtained using intensity standardization with outliers removal on the ROI and fixed bin size discretization. Standardization performed better with outliers removal than without (P < 0.001), and on ROIs than on native images (P < 0.001). Fixed bin size discretization performed better than fixed bin number (P = 0.008).

CONCLUSION

Radiomic features extracted from ultrasound images are impacted by the slice and preprocessing. The use of intensity standardization with outliers removal applied to the ROI and a fixed bin size grey-level discretization may improve feature repeatability.

Deep Learning-Based Carotid Plaque Segmentation from B-Mode Ultrasound Images

Carotid ultrasound measurement of total plaque area (TPA) provides a method for quantifying carotid plaque burden and monitoring changes in carotid atherosclerosis in response to medical treatment. Plaque boundary segmentation is required to generate the TPA measurement; however, training of observers and manual delineation are time consuming. Thus, our objective was to develop an automated plaque segmentation method to generate TPA from longitudinal carotid ultrasound images. In this study, a deep learning-based method, modified U-Net, was used to train the segmentation model and generate TPA measurement. A total of 510 plaques from 144 patients were used in our study, where the Monte Carlo cross-validation was used by randomly splitting the data set into 2/3 and 1/3 for training and testing. Two observers were trained to manually delineate the 510 plaques separately, which were used as the ground-truth references. Two U-Net models (M1 and M2) were trained using the two different ground-truth data sets from the two observers to evaluate the accuracy, variability and sensitivity on the ground-truth data sets used for training our method. The results of the algorithm segmentations of the two models yielded strong agreement with the two manual segmentations with the Pearson correlation coefficient r = 0.989 (p < 0.0001) and r = 0.987 (p < 0.0001). Comparison of the U-Net and manual segmentations resulted in mean TPA differences of 0.05 ± 7.13 mm² (95% confidence interval: 14.02-13.02 mm²) and 0.8 ± 8.7 mm² (17.85-16.25 mm²) for the two models, which are small compared with the TPA range in our data set from 4.7 to 312.8 mm². Furthermore, the mean time to segment a plaque was only 8.3 ± 3.1 ms. The presented deep learning-based method described has sufficient accuracy with a short computation time and exhibits high agreement between the algorithm and manual TPA measurements, suggesting that the method could be used to measure TPA and to monitor the progression and regression of carotid atherosclerosis.

A 3-D Ultrasound Wearable Array Prognosis System With Advanced Imaging Capabilities

In the last few decades, the medical and healthcare scientific communities have focused their attention on the use or development of real-time monitoring devices and remote control systems. New generations of wearable, portable, and implantable devices offer better and more accurate measurements/prognosis for those that suffer from diseases and/or disabilities. Thus, there are still challenging issues of current ultrasound imaging (USI) systems, such as low-quality ultrasound images, slow time response to emergencies, and location-based operation. Thus, in response to these challenges, we present a new low-cost, portable/wearable 3-D array ultrasound prognosis system with advanced imaging capabilities that offer high-resolution (HR) accurate results in a near real-time response. The USI unique features are based on 2-D array transducers with 3-D overlapping capabilities and a new image enhancement methodology compatible with the system's structural characteristics to compensate for any loss of image quality. This system will offer an alternative way of ultrasound examination, independent of the radiologist's skills, that is, a system to be capable of automatic scanning of the volume of interest (VOI) without the guidance of the radiologist.

The Role of Carotid and Femoral Plaque Burden in the Diagnosis of Coronary Artery Disease

PURPOSE OF REVIEW

With limitations of cardiovascular disease risk stratification by traditional risk factors, the role of noninvasive imaging techniques, such as vascular ultrasound, has emerged as a prominent utility for decision-making in coronary artery disease. A review of current guidelines and contemporary approaches for carotid and femoral plaque assessment is needed to better inform the diagnosis, management, and treatment of atherosclerosis in clinical practice.

RECENT FINDINGS

The recent consensus-based guidelines for carotid plaque assessment in coronary artery disease have been established, supported by some outcomes-based research. Currently, there is a gap of evidence on the use of femoral ultrasound to detect atherosclerosis, as well as predict adverse cardiovascular outcomes. The quantification and characterization of individualized plaque burden are important to stratify risk in asymptomatic or symptomatic atherosclerosis patients. Standardized quantification guidelines, supported by further outcomes-based research, are required to assess disease severity and progression.

Recommendations for the Assessment of Carotid Arterial Plaque by Ultrasound for the Characterization of Atherosclerosis and Evaluation of Cardiovascular Risk: From the American Society of Echocardiography

Atherosclerotic plaque detection by carotid ultrasound provides cardiovascular disease risk stratification. The advantages and disadvantages of two-dimensional (2D) and three-dimensional (3D) ultrasound methods for carotid arterial plaque quantification are reviewed. Advanced and emerging methods of carotid arterial plaque activity and composition analysis by ultrasound are considered. Recommendations for the standardization of focused 2D and 3D carotid arterial plaque ultrasound image acquisition and measurement for the purpose of cardiovascular disease stratification are formulated. Potential clinical application towards cardiovascular risk stratification of recommended focused carotid arterial plaque quantification approaches are summarized.

Ultrasound risk marker variability in symptomatic carotid plaque: impact on risk reclassification and association with temporal variation pattern

Purpose

Ultrasound examinations of atherosclerotic carotid plaques can be used to calculate risk markers associated with plaque vulnerability. Recent studies demonstrate significant inter-frame variability in risk markers. Here, we investigate risk marker variability in symptomatic plaques and its impact on reclassification of plaque vulnerability, as well as its association with the shape of the temporal variation over the cardiac cycle.

Methods

56 patients with symptomatic carotid stenosis were included in this study. 88 plaques were identified and the plaque risk markers size (area), echogenicity (gray scale median, GSM) and heterogeneity (coarseness) were measured in all frames of ultrasound B-mode image sequences. Inter-frame variability was quantified using the coefficient of variation (CV).

Results

Inter-frame variabilities of the risk markers were area CV 5–8%; GSM CV 4–7%; coarseness CV 8–15% and was in general significantly lower in large as compared to smaller plaques. The variability in GSM risk marker caused a reclassification of vulnerability in 30 to 38% of the plaques. Temporal variations in GSM with a heart rate periodic or drift/trending pattern were found in smaller plaques (< 26 mm²), whereas random pattern was found in larger plaques. In addition, hypoechoic plaques (GSM < 25) were associated with cyclic variation pattern, independent of their size.

Conclusions

Risk marker variability causes substantial reclassification of plaque vulnerability in symptomatic patients. Inter-frame variation and its temporal pattern should be considered in the design of future studies related to risk markers.

Three-dimensional ultrasound evaluation of the effects of pomegranate therapy on carotid plaque texture using locality preserving projection

BACKGROUND AND OBJECTIVE

Dietary supplements are expected to confer a smaller beneficial effect than medical treatments. Therefore, there is a need to develop cost-effective biomarkers that can demonstrate the efficacy of such supplements for carotid atherosclerosis. The aim of this study is to develop such a biomarker based on the changes of 376 plaque textural features measured from 3D ultrasound images.

METHODS

Since the number of features (376) was greater than the number of subjects (171) in this study, principal component analysis (PCA) was applied to reduce the dimensionality of feature vectors. To generate a scalar biomarker for each subject, elements in the reduced feature vectors produced by PCA were weighted using locality preserving projections (LPP) to capture essential patterns exhibited locally in the feature space. 96 subjects treated by pomegranate juice and tablets, and 75 subjects receiving placebo-matching juice and tablets were evaluated in this study. The discriminative power of the proposed biomarker was evaluated and compared with existing biomarkers using t-tests. As the cost of a clinical trial is directly related to the number of subjects enrolled, the cost-effectiveness of the proposed biomarker was evaluated by sample size estimation.

RESULTS

The proposed biomarker was more able to discriminate plaque changes exhibited by the pomegranate and placebo groups than total plaque volume (TPV) according to the result of t-tests (TPV: p=0.34, Proposed biomarker: p=1.5×10^-5). The sample size required by the new biomarker to detect a significant effect was 20 times smaller than that required by TPV.

CONCLUSION

With the increase in cost-effectiveness afforded by the proposed biomarker, more proof-of-principle studies for novel treatment options could be performed.

Carotid artery ultrasound image analysis: A review of the literature

Stroke is one of the prominent causes of death in the recent days. The existence of susceptible plaque in the carotid artery can be used in ascertaining the possibilities of cardiovascular diseases and long-term disabilities. The imaging modality used for early screening of the disease is B-mode ultrasound image of the person in the artery area. The objective of this article is to give a widespread review of the imaging modes and methods used for studying the carotid artery for identifying stroke, atherosclerosis and related cardiovascular diseases. We encompass the review in methods used for artery wall tracking, intima-media, and lumen segmentation which will help in finding the extent of the disease. Due to the characteristics of the imaging modality used, the images have speckle noise which worsens the image quality. Adaptive homomorphic filtering with wavelet and contourlet transforms, Levy Shrink, gamma distribution were used for image denoising. Learning-based neural network approaches for denoising give better edge preservation. Domain knowledge-based segmentation approaches have proved to provide more accurate intima-media thickness measurements. There is a requirement of useful fully automatic segmentation approaches, 3D, 4D systems, and plaque motion analysis. Taking into consideration the image priors like geometry, imaging physics, intensity and temporal data, image analysis has to be performed. Encouragingly more research has focused on content-specific segmentation and classification techniques. With the evaluation of machine learning algorithms, classifying the image as with or without a fat deposit has gained better accuracy and sensitivity. Machine learning-based approaches like self-organizing map, k-nearest neighborhood and support vector machine achieve promising accuracy and sensitivity in classification. The literature reveals that there is more scope in identifying a patient-specific model in a fully automatic manner.

A cross-section study of main determinants of arterial stiffness in Hefei area, China

BACKGROUND

Arterial stiffness has emerged as an independent risk factor for adverse cardiovascular disease events and is the consequence of multiple risk factors. The aim of the present study is to explore the main determinants of arterial stiffness in a Chinese population and to study how the arterial stiffness levels affected by different number of risk factors.

METHODS

This study included 358 subjects in Hefei area of China. Anthropometric indexes, biochemical indexes, cardiovascular function indexes and lifestyle were achieved. Brachial-ankle pulse wave velocity (baPWV) was used to assess arterial stiffness. Multivariate linear regression model was performed to identify the main determinants of arterial stiffness levels.

RESULTS

baPWV was correlated with age, sex, hypertension, various blood pressure components (systolic blood pressure [SPB], diastolic blood pressure, pulse pressure, and central arterial pressure), serum lipids, fasting blood-glucose and body mass index, subendocardial viability ratio (SEVR) and ejection duration (ED) in bivariate correlation analysis. Moreover, baPWV was only positively correlated with age, hypertension and SBP and inversely correlated with SEVR and ED in multivariable regression model. These five variables explained about 74.8% variances of baPWV and age was the strongest determinant of arterial stiffness. In addition, the levels of arterial stiffness increased with the augmented number of risk factors when the total number of factors was no more than 4.

CONCLUSIONS

The main determinants of arterial stiffness were age, hypertension, SBP, SEVR and ED. Furthermore, the number of risk factors had an independent influence on arterial stiffness, it is of great importance to consider the number of risk factors when it comes to cardiovascular risk assessment.

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges

Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring the temporal and spatial characteristics of the tumor. Progress in computational methods, especially in artificial intelligence for medical image process and analysis, has converted these images into quantitative and minable data associated with clinical events in oncology management. This concept was first described as radiomics in 2012. Since then, computer scientists, radiologists, and oncologists have gravitated towards this new tool and exploited advanced methodologies to mine the information behind medical images. On the basis of a great quantity of radiographic images and novel computational technologies, researchers developed and validated radiomic models that may improve the accuracy of diagnoses and therapy response assessments. Here, we review the recent methodological developments in radiomics, including data acquisition, tumor segmentation, feature extraction, and modelling, as well as the rapidly developing deep learning technology. Moreover, we outline the main applications of radiomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalized medicine. Finally, we discuss the challenges in the field of radiomics and the scope and clinical applicability of these methods.

Risk Marker Variability in Subclinical Carotid Plaques Based on Ultrasound is Influenced by Cardiac Phase, Echogenicity and Size

Identification of risk markers based on quantitative ultrasound texture analysis of carotid plaques has the ability to define vulnerable components that correlate with increased cardiovascular risk. However, data describing factors with the potential to influence the measurement variability of risk markers are limited. The aim of this study was to evaluate the influence of electrocardiogram-guided image selection, plaque echogenicity and area on carotid plaque risk markers and their variability in asymptomatic carotid plaques. Plaque risk markers were measured in 57 plaques during three consecutive heartbeats at two cardiac cycle time instants corresponding to the electrocardiogram R-wave (end diastole) and end of T-wave (end systole), resulting in six measurements for each plaque. Risk marker variability was quantified by computing the coefficient of variation (CV) across the three heartbeats. The CV was significantly higher for small plaques (area <15 mm2, 10%) than for large plaques (area >15 mm2, 6%) (p < 0.001) in measurements of area, and the CV for measurements of gray-scale median were higher for echolucent plaques (<40, 15%) than for echogenic plaques (>40, 9%) (p < 0.001). No significant differences were found between systole and diastole for the mean of any risk marker or the corresponding CV value. However, in a sub-analysis, the echolucent plaques were found to have a higher CV during systole compared with diastole. The variability also caused plaque type reclassification in 16% to 25% of the plaques depending on cutoff value. The results of this study indicate that echolucent and small plaques each contribute to increased risk marker variability. Based on these results, we recommend that measurements in diastole are preferred to reduce variation, although we found that it may not be possible to characterize small plaques accurately using contemporary applied risk markers.

Methods to evaluate arterial structure and function in children - State-of-the art knowledge

BACKGROUND

With increasing rates of hypertension, obesity, and diabetes in the pediatric population, wide available, and reproducible methods are necessary to evaluate arterial structure and function in children and adolescents.

METHODS

MEDLINE/Pubmed was searched for articles published in years 2012-2017 on methodology of, current knowledge on, and limitations of the most commonly used methods to evaluate central, proximal and coronary arteries, as well as endothelial function in pediatric patients.

RESULTS

Among 1528 records screened (including 1475 records from years 2012 to 2017) 139 papers were found suitable for the review. Following methods were discussed in this review article: ultrasound measurements of the intima-media thickness, coronary calcium scoring using computed tomography, arterial stiffness measurements (pulse wave velocity and pulse wave analysis, carotid artery distensibility, pulse pressure, and ambulatory arterial stiffness index), ankle-brachial index, and methods to evaluate vascular endothelial function (flow-mediated vasodilation, peripheral arterial tonometry, Doppler laser flowmetry, and cellular and soluble markers of endothelial dysfunction).

CONCLUSIONS

Ultrasonographic measurement of carotid intima-media thickness and measurement of pulse wave velocity (by oscillometry or applanation tonometry) are highly reproducible methods applicable for both research and clinical practice with proved applicability for children aged ≥6 years or with height ≥120cm. Evaluation of ambulatory arterial stiffness index by ambulatory blood pressure monitoring is another promising option in pediatric high-risk patients. Clearly, further studies are necessary to evaluate usefulness of these and other methods for the detection of subclinical arterial damage in children.

A Lesion-Based Response Prediction Model Using Pretherapy PET/CT Image Features for Y90 Radioembolization to Hepatic Malignancies

We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient's response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.

Contemporary carotid imaging: from degree of stenosis to plaque vulnerability

Carotid artery stenosis is a well-established risk factor of ischemic stroke, contributing to up to 10%-20% of strokes or transient ischemic attacks. Many clinical trials over the last 20 years have used measurements of carotid artery stenosis as a means to risk stratify patients. However, with improvements in vascular imaging techniques such as CT angiography and MR angiography, ultrasonography, and PET/CT, it is now possible to risk stratify patients, not just on the degree of carotid artery stenosis but also on how vulnerable the plaque is to rupture, resulting in ischemic stroke. These imaging techniques are ushering in an emerging paradigm shift that allows for risk stratifications based on the presence of imaging features such as intraplaque hemorrhage (IPH), plaque ulceration, plaque neovascularity, fibrous cap thickness, and presence of a lipid-rich necrotic core (LRNC). It is important for the neurosurgeon to be aware of these new imaging techniques that allow for improved patient risk stratification and outcomes. For example, a patient with a low-grade stenosis but an ulcerated plaque may benefit more from a revascularization procedure than a patient with a stable 70% asymptomatic stenosis with a thick fibrous cap. This review summarizes the current state-of-the-art advances in carotid plaque imaging. Currently, MRI is the gold standard in carotid plaque imaging, with its high resolution and high sensitivity for identifying IPH, ulceration, LRNC, and inflammation. However, MRI is limited due to time constraints. CT also allows for high-resolution imaging and can accurately detect ulceration and calcification, but cannot reliably differentiate LRNC from IPH. PET/CT is an effective technique to identify active inflammation within the plaque, but it does not allow for assessment of anatomy, ulceration, IPH, or LRNC. Ultrasonography, with the aid of contrast enhancement, is a cost-effective technique to assess plaque morphology and characteristics, but it is limited in sensitivity and specificity for detecting LRNC, plaque hemorrhage, and ulceration compared with MRI. Also summarized is how these advanced imaging techniques are being used in clinical practice to risk stratify patients with low- and high-grade carotid artery stenosis. For example, identification of IPH on MRI in patients with low-grade carotid artery stenosis is a risk factor for failure of medical therapy, and studies have shown that such patients may fair better with carotid endarterectomy (CEA). MR plaque imaging has also been found to be useful in identifying revascularization candidates who would be better candidates for CEA than carotid artery stenting (CAS), as high intraplaque signal on time of flight imaging is associated with vulnerable plaque and increased rates of adverse events in patients undergoing CAS but not CEA.

An automated technique for carotid far wall classification using grayscale features and wall thickness variability

PURPOSE

To test a computer-aided diagnostic method for differentiating symptomatic from asymptomatic carotid B-mode ultrasonographic images.

METHODS

Our 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

RESULTS

The 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°, 78°, and 79° angles.

CONCLUSIONS

Classification 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.

Texture analysis and classification in coherent anti-Stokes Raman scattering (CARS) microscopy images for automated detection of skin cancer

Coherent anti-Stokes Raman scattering (CARS) microscopy is a powerful tool for fast label-free tissue imaging, which is promising for early medical diagnostics. To facilitate the diagnostic process, automatic image analysis algorithms, which are capable of extracting relevant features from the image content, are needed. In this contribution we perform an automated classification of healthy and tumor areas in CARS images of basal cell carcinoma (BCC) skin samples. The classification is based on extraction of texture features from image regions and subsequent classification of these regions into healthy and cancerous with a perceptron algorithm. The developed approach is capable of an accurate classification of texture types with high sensitivity and specificity, which is an important step towards an automated tumor detection procedure.

An integrated system for the segmentation of atherosclerotic carotid plaque ultrasound video

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.

Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization

Characterization of carotid atherosclerosis and classification into either symptomatic or asymptomatic is crucial in terms of diagnosis and treatment planning for a range of cardiovascular diseases. This paper presents a computer-aided diagnosis (CAD) system (Atheromatic) that analyzes ultrasound images and classifies them into symptomatic and asymptomatic. The classification result is based on a combination of discrete wavelet transform, higher order spectra (HOS) and textural features. In this study, we compare support vector machine (SVM) classifiers with different kernels. The classifier with a radial basis function (RBF) kernel achieved an average accuracy of 91.7% as well as a sensitivity of 97%, and specificity of 80%. Thus, it is evident that the selected features and the classifier combination can efficiently categorize plaques into symptomatic and asymptomatic classes. Moreover, a novel symptomatic asymptomatic carotid index (SACI), which is an integrated index that is based on the significant features, has been proposed in this work. Each analyzed ultrasound image yields on SACI number. A high SACI value indicates that the image shows symptomatic and low value indicates asymptomatic plaques. We hope this SACI can support vascular surgeons during routine screening for asymptomatic plaques.

Computed tomography carotid wall plaque characterization using a combination of discrete wavelet transform and texture features: A pilot study

In 30% of stroke victims, the cause of stroke has been found to be the stenosis caused by plaques in the carotid artery. Early detection of plaque and subsequent classification of the same into symptomatic and asymptomatic can help the clinicians to choose only those patients who are at a higher risk of stroke for risky surgeries and stenosis treatments. Therefore, in this work, we have proposed a non-invasive computer-aided diagnostic technique to classify the detected plaque into the two classes. Computed tomography (CT) images of the carotid artery images were used to extract Local Binary Pattern (LBP) features and wavelet energy features. Significant features were then used to train and test several supervised learning algorithm based classifiers. The Support Vector Machine (SVM) classifier with various kernel configurations was evaluated using LBP and wavelet features. The SVM classifier presented the highest accuracy of 88%, sensitivity of 90.2%, and specificity of 86.5% for radial basis function (RBF) kernel function. The CT images of the carotid artery provide unique 3D images of the artery and plaque that could be used for calculating percentage of stenosis. Our proposed technique enables automatic classification of plaque into asymptomatic and symptomatic with high accuracy, and hence, it can be used for deciding the course of treatment. We have also proposed a single-valued integrated index (Atheromatic Index) using the significant features which can provide a more objective and faster prediction of the class.

Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment

In the case of carotid atherosclerosis, to avoid unnecessary surgeries in asymptomatic patients, it is necessary to develop a technique to effectively differentiate symptomatic and asymptomatic plaques. In this paper, we have presented a data mining framework that characterizes the textural differences in these two classes using several grayscale features based on a novel combination of trace transform and fuzzy texture. The features extracted from the delineated plaque regions in B-mode ultrasound images were used to train several classifiers in order to prepare them for classification of new test plaques. Our CAD system was evaluated using two different databases consisting of 146 (44 symptomatic to 102 asymptomatic) and 346 (196 symptomatic and 150 asymptomatic) images. Both these databases differ in the way the ground truth was determined. We obtained classification accuracies of 93.1 and 85.3 %, respectively. The techniques are low cost, easily implementable, objective, and non-invasive. For more objective analysis, we have also developed novel integrated indices using a combination of significant features.

EVALUATION OF THE RISK OF STROKE WITH CONFIDENCE PREDICTIONS BASED ON ULTRASOUND CAROTID IMAGE ANALYSIS

Conformal Predictors (CPs) are Machine Learning algorithms that can provide reliable confidence measures to their predictions. In this work, we make use of the Conformal Prediction framework for the assessment of stroke risk based on ultrasound images of atherosclerotic carotid plaques. For this application, images were recorded from 137 asymptomatic and 137 symptomatic plaques (symptoms are Stroke, Transient Ischaemic Attack (TIA), and Amaurosis Fugax (AF)). Two feature sets were extracted from the plaques; the first based on morphological image analysis and the second based on image texture analysis. Both sets were used in order to evaluate the performance of CPs on this problem. Four CPs were constructed using four popular classification methods, namely Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Naive Bayes Classification (NBC), and k -Nearest Neighbours. The results given by all CPs demonstrate the reliability and importance of the obtained confidence measures on the problem of stroke risk assessment.

Atherosclerotic risk stratification strategy for carotid arteries using texture-based features

Plaques in the carotid artery result in stenosis, which is one of the main causes for stroke. Patients have to be carefully selected for stenosis treatments as they carry some risk. Since patients with symptomatic plaques have greater risk for strokes, an objective classification technique that classifies the plaques into symptomatic and asymptomatic classes is needed. We present a computer aided diagnostic (CAD) based ultrasound characterization methodology (a class of Atheromatic systems) that classifies the patient into symptomatic and asymptomatic classes using two kinds of datasets: (1) plaque regions in ultrasound carotids segmented semi-automatically and (2) far wall gray-scale intima-media thickness (IMT) regions along the common carotid artery segmented automatically. For both kinds of datasets, the protocol consists of estimating texture-based features in frameworks of local binary patterns (LBP) and Law's texture energy (LTE) and applying these features for obtaining the training parameters, which are then used for classification. Our database consists of 150 asymptomatic and 196 symptomatic plaque regions and 342 IMT wall regions. When using the Atheromatic-based system on semiautomatically determined plaque regions, support vector machine (SVM) classifier was adapted with highest accuracy of 83%. The accuracy registered was 89.5% on the far wall gray-scale IMT regions when using SVM, K-nearest neighbor (KNN) or radial basis probabilistic neural network (RBPNN) classifiers. LBP/LTE-based techniques on both kinds of carotid datasets are noninvasive, fast, objective and cost-effective for plaque characterization and, hence, will add more value to the existing carotid plaque diagnostics protocol. We have also proposed an index for each type of datasets: AtheromaticPi, for carotid plaque region, and AtheromaticWi, for IMT carotid wall region, based on the combination of the respective significant features. These indices show a separation between symptomatic and asymptomatic by 4.53 units and 4.42 units, respectively, thereby supporting the texture hypothesis classification.

Automatic segmentation of carotid B-mode images using fuzzy classification

This paper presents a new method for the automatic segmentation of the common carotid artery in B-mode images. This method uses the instantaneous coefficient of variation edge detector, fuzzy classification of edges and dynamic programming. Several discriminating features of the intima and adventitia boundaries are considered, like the edge strength, the intensity gradient orientation, the valley shaped intensity profile and contextual information of the region delimited by those boundaries. The adopted fuzzy classification of edges helps avoiding low-pass filtering. The method is suited to real-time processing and user interaction is not required. Both the near and far wall boundaries can be detected in arteries with plaques of different types and sizes. Both expert manual and automatic tracings are significantly better for the far wall, due to the better visibility of the intima and adventitia boundaries. The automatic detection of the far wall shows an accuracy similar to the manual detections. For this wall, the error coefficient of variation for the mean intima-media thickness is in the range [5.6, 6.6 %] for automatic detections and in [6.7, 7.1 %] for manual ones. In the case of the near wall, the same coefficient of variation is in [11.2, 13.0 %] for automatic detections and in [5.9, 9.0 %] for manual detections. The mean intima-media thickness measurement errors observed for the far wall [Formula: see text] are among the best values reported for other fully automatic approaches. The application of this approach in clinical practice is encouraged by the results for the far wall and the short processing time (mean of 2.1 s per image).

Feature selection applied to ultrasound carotid images segmentation

The automated tracing of the carotid layers on ultrasound images is complicated by noise, different morphology and pathology of the carotid artery. In this study we benchmarked four methods for feature selection on a set of variables extracted from ultrasound carotid images. The main goal was to select those parameters containing the highest amount of information useful to classify the pixels in the carotid regions they belong to. Six different classes of pixels were identified: lumen, lumen-intima interface, intima-media complex, media-adventitia interface, adventitia and adventitia far boundary. The performances of QuickReduct Algorithm (QRA), Entropy-Based Algorithm (EBR), Improved QuickReduct Algorithm (IQRA) and Genetic Algorithm (GA) were compared using Artificial Neural Networks (ANNs). All methods returned subsets with a high dependency degree, even if the average classification accuracy was about 50%. Among all classes, the best results were obtained for the lumen. Overall, the four methods for feature selection assessed in this study return comparable results. Despite the need for accuracy improvement, this study could be useful to build a pre-classifier stage for the optimization of segmentation performance in ultrasound automated carotid segmentation.

Carotid far wall characterization using LBP, Laws' Texture Energy and wall variability: a novel class of Atheromatic systems

In this work, we present a Computer Aided Diagnostic (CAD) technique (a class of Atheromatic systems) that classifies the automatically segmented carotid far wall Intima-Media Thickness (IMT) regions along the common carotid artery into symptomatic and asymptomatic classes. We extracted texture features based on Local Binary Patterns (LBP) and Law's Texture Energy (LTE) and used the significant features to train and test the Support Vector Machine classifier. We developed the classifiers using three-fold stratified cross validation data resampling technique on 342 IMT wall regions. An accuracy of 89.5% was registered. Thus, the proposed technique is accurate, robust, non-invasive, fast, objective, and cost-effective, and hence, will add more value to the existing carotid plaque diagnostics protocol.

Ultrasonic image analysis and image-guided interventions

The fields of medical image analysis and computer-aided interventions deal with reducing the large volume of digital images (X-ray, computed tomography, magnetic resonance imaging (MRI), positron emission tomography and ultrasound (US)) to more meaningful clinical information using software algorithms. US is a core imaging modality employed in these areas, both in its own right and used in conjunction with the other imaging modalities. It is receiving increased interest owing to the recent introduction of three-dimensional US, significant improvements in US image quality, and better understanding of how to design algorithms which exploit the unique strengths and properties of this real-time imaging modality. This article reviews the current state of art in US image analysis and its application in image-guided interventions. The article concludes by giving a perspective from clinical cardiology which is one of the most advanced areas of clinical application of US image analysis and describing some probable future trends in this important area of ultrasonic imaging research.

Comparison of multiresolution features for texture classification of carotid atherosclerosis from B-mode ultrasound

In this paper, a multiresolution approach is suggested for texture classification of atherosclerotic tissue from B-mode ultrasound. Four decomposition schemes, namely, the discrete wavelet transform, the stationary wavelet transform, wavelet packets (WP), and Gabor transform (GT), as well as several basis functions, were investigated in terms of their ability to discriminate between symptomatic and asymptomatic cases. The mean and standard deviation of the detail subimages produced for each decomposition scheme were used as texture features. Feature selection included 1) ranking the features in terms of their divergence values and 2) appropriately thresholding by a nonlinear correlation coefficient. The selected features were subsequently input into two classifiers using support vector machines (SVM) and probabilistic neural networks. WP analysis and the coiflet 1 produced the highest overall classification performance (90% for diastole and 75% for systole) using SVM. This might reflect WP's ability to reveal differences in different frequency bands, and therefore, characterize efficiently the atheromatous tissue. An interesting finding was that the dominant texture features exhibited horizontal directionality, suggesting that texture analysis may be affected by biomechanical factors (plaque strains).

Multiscale morphological analysis of the atherosclerotic carotid plaque

The aim of this paper was to investigate the usefulness of multiscale morphological analysis in the assessment of atherosclerotic carotid plagues. Ultrasound images were recorded from 137 asymptomatic and 137 symptomatic plaques and were converted to binary images at low, middle and high intensity intervals based on structural morphology. Low images represent low intensity regions corresponding to blood, thrombus, lipid or hemorrhage, whereas high images describe the collagen and calcified components of the plaque. Middle image describe image regions that fall between low and high components. The morphological pattern spectra were computed and several classifiers like the K-Nearest Neighbor (KNN), 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 diagnostic yield achieved was 67% that is slightly lower than texture analysis carried out on the same data set.