Segmentation of plaques in sequences of ultrasonic B-mode images of carotid arteries based on motion estimation and a Bayesian model

A Phantom-Free Approach for Estimating the Backscatter Coefficient of Aggregated Red Blood Cells Applied to COVID-19 Patients

The ultrasound backscatter coefficient (BSC) is a frequency-dependent quantity intrinsic to biological tissues that can be recovered from backscattered radio frequency (RF) signals, granted acquisitions on a reference phantom (RP) are available under the same system's settings. A phantom-free (PF) BSC estimation method is proposed based on Gaussian-shaped approximation of the point spread function (PSF) (electronics and piezoelectric characteristics of the scanner's probe) and the effective medium theory combined with the structure factor model (EMTSFM), albeit the proposed approach is amenable to other models. Meanwhile, the total attenuation due to intervening tissues is refined from its theoretical value, which is based on reported average behaviors of tissues, while allowing correction for diffraction due to the probe's geometry. The RP method adapted to a similar approach except for the Gaussian approximation is also presented. The proposed PF and RP methods were compared on ten COVID-19 positive patients and 12 control subjects with measures on femoral veins and arteries. In this context, red blood cells (RBCs) are viewed as scatterers that form aggregates increasing the backscatter under the COVID-19 inflammatory condition. The considered model comprises five parameters, including the mean aggregate size estimated according to the polydispersity of aggregates' radii, and anisotropy of their shape. The mean aggregate size over the two proposed methods presented an intraclass correlation coefficient (ICC) of 0.964 for consistency. The aggregate size presented a significant difference between the two groups with either two methods, despite the confounding effect of the maximum Doppler velocity within the blood vessel and its diameter.

A deep learning algorithm to identify carotid plaques and assess their stability

Background

Carotid plaques are major risk factors for stroke. Carotid ultrasound can help to assess the risk and incidence rate of stroke. However, large-scale carotid artery screening is time-consuming and laborious, the diagnostic results inevitably involve the subjectivity of the diagnostician to a certain extent. Deep learning demonstrates the ability to solve the aforementioned challenges. Thus, we attempted to develop an automated algorithm to provide a more consistent and objective diagnostic method and to identify the presence and stability of carotid plaques using deep learning.

Methods

A total of 3,860 ultrasound images from 1,339 participants who underwent carotid plaque assessment between January 2021 and March 2023 at the Shanghai Eighth People's Hospital were divided into a 4:1 ratio for training and internal testing. The external test included 1,564 ultrasound images from 674 participants who underwent carotid plaque assessment between January 2022 and May 2023 at Xinhua Hospital affiliated with Dalian University. Deep learning algorithms, based on the fusion of a bilinear convolutional neural network with a residual neural network (BCNN-ResNet), were used for modeling to detect carotid plaques and assess plaque stability. We chose AUC as the main evaluation index, along with accuracy, sensitivity, and specificity as auxiliary evaluation indices.

Results

Modeling for detecting carotid plaques involved training and internal testing on 1,291 ultrasound images, with 617 images showing plaques and 674 without plaques. The external test comprised 470 ultrasound images, including 321 images with plaques and 149 without. Modeling for assessing plaque stability involved training and internal testing on 764 ultrasound images, consisting of 494 images with unstable plaques and 270 with stable plaques. The external test was composed of 279 ultrasound images, including 197 images with unstable plaques and 82 with stable plaques. For the task of identifying the presence of carotid plaques, our model achieved an AUC of 0.989 (95% CI: 0.840, 0.998) with a sensitivity of 93.2% and a specificity of 99.21% on the internal test. On the external test, the AUC was 0.951 (95% CI: 0.962, 0.939) with a sensitivity of 95.3% and a specificity of 82.24%. For the task of identifying the stability of carotid plaques, our model achieved an AUC of 0.896 (95% CI: 0.865, 0.922) on the internal test with a sensitivity of 81.63% and a specificity of 87.27%. On the external test, the AUC was 0.854 (95% CI: 0.889, 0.830) with a sensitivity of 68.52% and a specificity of 89.49%.

Conclusion

Deep learning using BCNN-ResNet algorithms based on routine ultrasound images could be useful for detecting carotid plaques and assessing plaque instability.

Refined Feature-based Multi-frame and Multi-scale Fusing Gate network for accurate segmentation of plaques in ultrasound videos

The accurate segmentation of carotid plaques in ultrasound videos will provide evidence for clinicians to evaluate the properties of plaques and treat patients effectively. However, the confusing background, blurry boundaries and plaque movement in ultrasound videos make accurate plaque segmentation challenging. To address the above challenges, we propose the Refined Feature-based Multi-frame and Multi-scale Fusing Gate Network (RMFG_Net), which captures spatial and temporal features in consecutive video frames for high-quality segmentation results and no manual annotation of the first frame. A spatial-temporal feature filter is proposed to suppress the noise of low-level CNN features and promote the detailed target area. To obtain a more accurate plaque position, we propose a transformer-based cross-scale spatial location algorithm, which models the relationship between adjacent layers of consecutive video frames to achieve stable positioning. To make full use of more detailed and semantic information, multi-layer gated computing is applied to fuse features of different layers, ensuring sufficient useful feature map aggregation for segmentation. Experiments on two clinical datasets demonstrate that the proposed method outperforms other state-of-the-art methods under different evaluation metrics, and it processes images with a speed of 68 frames per second which is suitable for real-time segmentation. A large number of ablation experiments were conducted to demonstrate the effectiveness of each component and experimental setting, as well as the potential of the proposed method in ultrasound video plaque segmentation tasks. The codes can be publicly available from https://github.com/xifengHuu/RMFG_Net.git.

Ultrasound-Based Image Analysis for Predicting Carotid Artery Stenosis Risk: A Comprehensive Review of the Problem, Techniques, Datasets, and Future Directions

The carotid artery is a major blood vessel that supplies blood to the brain. Plaque buildup in the arteries can lead to cardiovascular diseases such as atherosclerosis, stroke, ruptured arteries, and even death. Both invasive and non-invasive methods are used to detect plaque buildup in the arteries, with ultrasound imaging being the first line of diagnosis. This paper presents a comprehensive review of the existing literature on ultrasound image analysis methods for detecting and characterizing plaque buildup in the carotid artery. The review includes an in-depth analysis of datasets; image segmentation techniques for the carotid artery plaque area, lumen area, and intima-media thickness (IMT); and plaque measurement, characterization, classification, and stenosis grading using deep learning and machine learning. Additionally, the paper provides an overview of the performance of these methods, including challenges in analysis, and future directions for research.

Modeling for Quantitative Analysis of Nakagami Imaging in Accurate Detection and Monitoring of Therapeutic Lesions by High-Intensity Focused Ultrasound

OBJECTIVE

Nakagami imaging is an appealing monitoring and evaluation technique for high-intensity focused ultrasound treatment when bubbles are present in ultrasound images. This study aimed to investigate the accuracy of thermal lesion detection using Nakagami imaging.

METHODS

Simulations were conducted to explore and quantify the influence of the bubbles and the subresolvable effect at the boundary of the thermal lesion on thermal lesion detection. The thermal ablation experiments were conducted in phantom and porcine liver ex vivo.

RESULTS

In the simulation, the estimated lateral and axial size of the thermal lesion in the Nakagami image was 4.91 and 4.79 mm, close to the actual size (5 × 5 mm). The simulation results indicated that the subresolvable region in high-intensity focused ultrasound treatment thermal ablation mainly happened at the boundary between bubbles and the untreated region and does not affect the accuracy of thermal lesion detection. The accurate detection of the thermal lesion using Nakagami imaging mainly depends on bubbles and thermal lesion characterization. Our thermal ablation experiments confirmed that Nakagami imaging has the ability to accurately identify thermal lesions from bubbles.

CONCLUSION

The subresolvable effect is helpful for thermal lesion identification, and precision is related to the Nakagami values chosen for boundary division in Nakagami imaging. Therefore, Nakagami imaging is a promising method for accurately evaluating thermal lesions. Further studies in vivo and in clinical settings will be needed to explore its potential applications.

Ultrasound carotid plaque segmentation via image reconstruction-based self-supervised learning with limited training labels

Carotid total plaque area (TPA) is an important contributing measurement to the evaluation of stroke risk. Deep learning provides an efficient method for ultrasound carotid plaque segmentation and TPA quantification. However, high performance of deep learning requires datasets with many labeled images for training, which is very labor-intensive. Thus, we propose an image reconstruction-based self-supervised learning algorithm (IR-SSL) for carotid plaque segmentation when few labeled images are available. IR-SSL consists of pre-trained and downstream segmentation tasks. The pre-trained task learns region-wise representations with local consistency by reconstructing plaque images from randomly partitioned and disordered images. The pre-trained model is then transferred to the segmentation network as the initial parameters in the downstream task. IR-SSL was implemented with two networks, UNet++ and U-Net, and evaluated on two independent datasets of 510 carotid ultrasound images from 144 subjects at SPARC (London, Canada) and 638 images from 479 subjects at Zhongnan hospital (Wuhan, China). Compared to the baseline networks, IR-SSL improved the segmentation performance when trained on few labeled images (n = 10, 30, 50 and 100 subjects). For 44 SPARC subjects, IR-SSL yielded Dice-similarity-coefficients (DSC) of 80.14-88.84%, and algorithm TPAs were strongly correlated (r=0.962-0.993, p < 0.001) with manual results. The models trained on the SPARC images but applied to the Zhongnan dataset without retraining achieved DSCs of 80.61-88.18% and strong correlation with manual segmentation (r=0.852-0.978, p < 0.001). These results suggest that IR-SSL could improve deep learning when trained on small labeled datasets, making it useful for monitoring carotid plaque progression/regression in clinical use and trials.

Review of Envelope Statistics Models for Quantitative Ultrasound Imaging and Tissue Characterization

The homodyned K-distribution and the K-distribution, viewed as a special case, as well as the Rayleigh and the Rice distributions, viewed as limit cases, are discussed in the context of quantitative ultrasound (QUS) imaging. The Nakagami distribution is presented as an approximation of the homodyned K-distribution. The main assumptions made are (1) the absence of log-compression or application of nonlinear filtering on the echo envelope of the radiofrequency signal and (2) the randomness and independence of the diffuse scatterers. We explain why other available models are less amenable to a physical interpretation of their parameters. We also present the main methods for the estimation of the statistical parameters of these distributions. We explain why we advocate the methods based on the X-statistics for the Rice and the Nakagami distributions and the K-distribution. The limitations of the proposed models are presented. Several new results are included in the discussion sections, with proofs in the appendix.

Learning-based initialization for correntropy-based level sets to segment atherosclerotic plaque in ultrasound images

Carotid artery atherosclerosis is a significant cause of stroke. Ultrasound imaging has been widely used in the diagnosis of atherosclerosis. Therefore, segmenting the atherosclerotic carotid plaque in an ultrasound image is an important task. Accurate plaque segmentation is helpful for the measurement of carotid plaque burden. This study proposes an automatic method for atherosclerotic plaque segmentation by using correntropy-based level sets (CLS) with learning-based initialization. We introduce the CLS model, containing the point-based local bias-field corrected image fitting method and correntropy-based distance measurement, to overcome the limitations of the ultrasound images. A supervised learning algorithm is employed to solve the automatic initialization problem of the variational methods. The proposed atherosclerotic plaque segmentation method is validated on 29 carotid ultrasound images, obtaining a Dice ratio of 90.6 ± 1.9% and an overlap index of 83.6 ± 3.2%. Moreover, by comparing the standard deviation of each evaluation index, it can be found that the proposed method is more robust for segmenting the atherosclerotic plaque. Our work shows that our proposed method can be more helpful than other variational models for measuring the carotid plaque burden.

Ultrafast Myocardial Principal Strain Ultrasound Elastography During Stress Tests: In Vitro Validation and In Vivo Feasibility

Objective myocardial contractility assessment during stress tests aims to improve the diagnosis of myocardial ischemia. Tissue Doppler imaging (TDI) or optical flow (OF) speckle tracking echocardiography (STE) has been used to quantify myocardial contractility at rest. However, this is more challenging during stress tests due to image decorrelation at high heart rates. Moreover, stress tests imply a high frame rate which leads to a limited lateral field of view. Therefore, a large lateral field-of-view robust ultrafast myocardial regularized OF-TDI principal strain estimator has been developed for high-frame-rate echocardiography of coherently compounded transmitted diverging waves. The feasibility and accuracy of the proposed estimator were validated in vitro (using sonomicrometry as the gold standard) and in vivo stress experiments. Compared with OF strain imaging, the proposed estimator improved the accuracy of principal major and minor strains during stress tests, with an average contrast-to-noise ratio improvement of 4.4 ± 2.7 dB ( p -value < 0.01). Moreover, there was a significant correlation and a very close agreement between the proposed estimator and sonomicrometry for tested heart rates between 60 and 180 beats per minute (bpm). The averages ± standard deviations (STD) of R² and biases ± STD between them were 0.96 ± 0.04 ( p -value < 0.01) and 0.01 ± 0.03% in the axial direction, respectively; and 0.94 ± 0.02 ( p -value < 0.01) and 0.04 ± 0.06% in the lateral direction, respectively. These results suggest that the proposed estimator could be useful clinically to provide an accurate and quantitative 2-D large lateral field-of-view myocardial strain assessment at high heart rates during stress echocardiography.

Non-Invasive Vascular Elastography as a One-Step Imaging Technique to Evaluate Early Vascular Changes in Children Compared to B-Mode-Based Intima-Media Thickness Technique : A Validation Study Using Inter- and Intra-Rater Reliability

Background: Childhood obesity is linked to higher adult mortality and morbidity from atherosclerosis. It is primordial to detect at-risk children earlier-on to prevent disease progression. Carotid intima-media thickness (IMT) is a subclinical radiological marker for early atherosclerosis. B-mode ultrasound is a known technique to assess IMT, but no gold standard technique exists in children. Non-invasive vascular elastography (NIVE) using speckle statistics is an innovative alternative to evaluate IMT and adds by providing translation, strain and shear strain measurements. Validation studies for both techniques lack in children. Purpose: Validate the reproducibility of the 2 techniques in Canadian children. Methods: We conducted a prospective study where anthropometry, blood pressure, IMT and elastography were measured. Six operators obtained 2 measurements for both carotid arteries using both techniques, for a total of 720 measurements. Inter- and intra-class correlation coefficients (ICC) were calculated for each measurement technique and elastography parameters. Results: 30 participants (13.0 ± 1.26 years, 17 girls) were recruited. Twelve were overweight. No significant difference was found in mean IMT between weight groups for either technique (P = .15 and P = .60). We found excellent inter- (ICC = .98 [95% Confidence Interval (CI): .97; .99]) and intra- (ICC = .90-.93) operator reliability for the B-mode technique, and good inter (ICC = .70 [95% CI: .47; .85]) and intra- (ICC = .71-.91) operator reliability for the NIVE-based technique. Poor reliability was found between techniques (ICC = .30 [95% CI: -.31; .65). For elastography parameters, translation was the most reliable (ICC = .94-.95). Conclusion: IMT measurement is reproducible in children but not between techniques. NIVE gives the advantage of evaluating elastography.

Regional pleural strain measurements during mechanical ventilation using ultrasound elastography: A randomized, crossover, proof of concept physiologic study

Background

Mechanical ventilation is a common therapy in operating rooms and intensive care units. When ill-adapted, it can lead to ventilator-induced lung injury (VILI), which is associated with poor outcomes. Excessive regional pulmonary strain is thought to be a major mechanism responsible for VILI. Scarce bedside methods exist to measure regional pulmonary strain. We propose a novel way to measure regional pleural strain using ultrasound elastography. The objective of this study was to assess the feasibility and reliability of pleural strain measurement by ultrasound elastography and to determine if elastography parameters would correlate with varying tidal volumes.

Methods

A single-blind randomized crossover proof of concept study was conducted July to October 2017 at a tertiary care referral center. Ten patients requiring general anesthesia for elective surgery were recruited. After induction, patients received tidal volumes of 6, 8, 10, and 12 mL.kg^–1 in random order, while pleural ultrasound cineloops were acquired at 4 standardized locations. Ultrasound radiofrequency speckle tracking allowed computing various pleural translation, strain and shear components. We screened 6 elastography parameters (lateral translation, lateral absolute translation, lateral strain, lateral absolute strain, lateral absolute shear and Von Mises Strain) to identify those with the best dose-response with tidal volumes using linear mixed effect models. Goodness-of-fit was assessed by the coefficient of determination. Intraobserver, interobserver and test-retest reliability were calculated using intraclass correlation coefficients.

Results

Analysis was possible in 90.7% of ultrasound cineloops. Lateral absolute shear, lateral absolute strain and Von Mises strain varied significantly with tidal volume and offered the best dose-responses and data modeling fits. Point estimates for intraobserver reliability measures were excellent for all 3 parameters (0.94, 0.94, and 0.93, respectively). Point estimates for interobserver (0.84, 0.83, and 0.77, respectively) and test-retest (0.85, 0.82, and 0.76, respectively) reliability measures were good.

Conclusion

Strain imaging is feasible and reproducible. Future studies will have to investigate the clinical relevance of this novel imaging modality.

Clinical trial registration

www.Clinicaltrials.gov, identifier NCT03092557.

Associative Prediction of Carotid Artery Plaques Based on Ultrasound Strain Imaging and Cardiovascular Risk Factors in People Living With HIV and Age-Matched Control Subjects of the CHACS Cohort

BACKGROUND

There is a need for a specific atherosclerotic risk assessment for people living with HIV (PLWH).

SETTING

A machine learning classification model was applied to PLWH and control subjects with low-to-intermediate cardiovascular risks to identify associative predictors of diagnosed carotid artery plaques. Associations with plaques were made using strain elastography in normal sections of the common carotid artery and traditional cardiovascular risk factors.

METHODS

One hundred two PLWH and 84 control subjects were recruited from the prospective Canadian HIV and Aging Cohort Study (57 ± 8 years; 159 men). Plaque presence was based on clinical ultrasound scans of left and right common carotid arteries and internal carotid arteries. A classification task for identifying subjects with plaque was defined using random forest (RF) and logistic regression models. Areas under the receiver operating characteristic curves (AUC-ROCs) were applied to select 5 among 50 combinations of 4 or less features yielding the highest AUC-ROCs.

RESULTS

To retrospectively classify individuals with and without plaques, the 5 most discriminant combinations of features had AUC-ROCs between 0.76 and 0.79. AUC-ROCs from RF were statistically significantly higher than those obtained with logistic regressions ( P = 0.0001). The most discriminant features of RF classifications in PLWH were age, smoking status, maximum axial strain and pulse pressure (equal weights), and sex and antiretroviral therapy exposure (equal weights). When considering the whole population, the HIV status was identified as a cofactor associated with carotid artery plaques.

CONCLUSIONS

Strain elastography adds to traditional cardiovascular risk factors for identifying individuals with carotid artery plaques.

Shear Wave Elastography and Quantitative Ultrasound as Biomarkers to Characterize Deep Vein Thrombosis In Vivo

OBJECTIVE

Investigate shear wave elastography (SWE) and quantitative ultrasound (QUS) parameters in patients hospitalized for lower limb deep vein thrombosis (DVT).

METHOD

Sixteen patients with DVT were recruited and underwent SWE and radiofrequency data acquisitions for QUS on day 0, day 7, and day 30 after the beginning of symptoms, in both proximal and distal zones of the clot identified on B-mode scan. SWE and QUS features were computed to differentiate between thrombi at day 0, day 7, and day 30 following treatment with heparin or oral anticoagulant. The Young's modulus from SWE was computed, as well as QUS homodyned K-distribution (HKD) parameters reflecting blood clot structure. Median and interquartile range of SWE and QUS parameters within clot were taken as features.

RESULTS

In the proximal zone of the clot, the HKD ratio of coherent-to-diffuse backscatter median showed a significant decrease from day 7 to day 30 (P = .036), while the HKD ratio of diffuse-to-total backscatter median presented a significant increase from day 7 to day 30 (P = .0491). In the distal zone of the clot, the HKD normalized intensity of the echo envelope median showed a significant increase from day 0 to day 30 (P = .0062). No SWE features showed statistically significant differences over time. Nonetheless, a trend of lower median of Young's modulus within clot for patients who developed a pulmonary embolism was observed.

CONCLUSION

QUS features may be relevant to characterize clot's evolution over time. Further analysis of their clinical interpretation and validation on a larger dataset would deserve to be studied.

Impact of Applying a Skin Compression With the Ultrasound Probe on Carotid Artery Strain Elastography

OBJECTIVE

To study the impact of varying the external compression exerted by the ultrasound probe when performing a carotid strain elastography exam.

METHODS

Nine healthy volunteers (mean age 43 years ±13 years; 6 men) underwent a vascular ultrasound elastography exam using a custom made sound feedback handle embedding the probe, and allowing the sonographer to adjust the applied compression. A clinical standard practice (SP) force was first recorded, and then predetermined compression (PDC) forces were applied, ranging from 0 to 5 N for the left common carotid artery (CCA) or 2-12 N for the left internal carotid artery (ICA). Six carotid elastography features, namely maximum and cumulated axial strains, maximum and cumulated shear strains, cumulated axial translation, and cumulated lateral translation were assessed with noninvasive vascular elastography (NIVE) on near and far walls of carotids. The carotid intima media thickness (IMT) and diameter were also measured.

RESULTS

All elastography features on the near wall of both CCA and ICA decreased statistically significantly as the PDC force increased; this association was also observed for half of the features on the far wall. Three NIVE features at the lowest PDC force (out of 72 that were tested) were statistically significantly different than values at the SP force. Overall, NIVE showed some variance to probe compression with linear regression slopes revealing changes of 10.1%-45.6% in magnitude over the whole compression range on both walls. The maximum IMT for the ICA near wall, and carotid lumen diameters of both CCA and ICA were statistically significantly associated with PDC forces; these features underwent a decrease of 10.2%, 36.2%, and 17.6%, respectively, over the whole range of PDC force increase. Other IMT measurements were not statistically significantly associated with applied PDC forces.

CONCLUSION

These results suggest the need of technical guidelines for carotid strain elastography. Using the lowest probe compression while allowing a good B-mode image quality is recommended to improve the robustness of NIVE measurements.

Strain Ultrasound Elastography of Aneurysm Sac Content after Randomized Endoleak Embolization with Sclerosing and Non-sclerosing Chitosan-based Hydrogels in a Canine Model

PURPOSE

To compare the mechanical properties of aneurysm content after endoleak embolization with a chitosan hydrogel (CH) versus a chitosan hydrogel with sodium tetradecyl sulphate (CH-STS) using strain ultrasound elastography (SUE).

MATERIALS AND METHODS

Bilateral common iliac artery type Ia endoleaks were created in nine dogs. Per animal, one endoleak was randomized to blinded embolization with CH, and the other, with CH-STS. Brightness mode ultrasound, Doppler ultrasound, SUE radiofrequency ultrasound, and computed tomography were performed for up to six months until sacrifice. Radiological and histopathological studies were co-registered to identify three regions of interest: embolic agent, intraluminal thrombus (ILT), and aneurysm sac. SUE segmentations were performed by two blinded, independent observers. Maximum axial strain (MAS) was the primary outcome. Statistical analysis was performed using Fisher's exact test, multivariable linear mixed-effects models, and intraclass correlation coefficients (ICCs).

RESULTS

Residual endoleaks were identified in 7/9 (78%) and 4/9 (44%) aneurysms embolized with CH and CH-STS, respectively (p=0.3348). CH-STS had 66% lower MAS (p<0.001) than CH. The ILT had 37% lower MAS (p=0.01) than CH and 77% greater MAS (p=0.079) than CH-STS. There was no significant difference in ILT between treatments. Aneurysm sacs embolized with CH-STS had 29% lower MAS (p<0.001) than those embolized with CH. Residual endoleak was associated with 53% greater aneurysm sac MAS (p<0.001). The ICC for MAS was 0.807 (95% confidence interval: 0.754-0.849) between segmentations.

CONCLUSION

CH-STS confers stiffer intraluminal properties to embolized aneurysms. Persistent endoleaks are associated with increased sac strain, an observation which may help guide management.

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.

Deep Learning-Based Measurement of Total Plaque Area in B-Mode Ultrasound Images

Measurement of total-plaque-area (TPA) is important for determining long term risk for stroke and monitoring carotid plaque progression. Since delineation of carotid plaques is required, a deep learning method can provide automatic plaque segmentations and TPA measurements; however, it requires large datasets and manual annotations for training with unknown performance on new datasets. A UNet++ ensemble algorithm was proposed to segment plaques from 2D carotid ultrasound images, trained on three small datasets (n = 33, 33, 34 subjects) and tested on 44 subjects from the SPARC dataset (n = 144, London, Canada). The ensemble was also trained on the entire SPARC dataset and tested with a different dataset (n = 497, Zhongnan Hospital, China). Algorithm and manual segmentations were compared using Dice-similarity-coefficient (DSC), and TPAs were compared using the difference ( ∆TPA), Pearson correlation coefficient (r) and Bland-Altman analyses. Segmentation variability was determined using the intra-class correlation coefficient (ICC) and coefficient-of-variation (CoV). For 44 SPARC subjects, algorithm DSC was 83.3-85.7%, and algorithm TPAs were strongly correlated (r = 0.985-0.988; p < 0.001) with manual results with marginal biases (0.73-6.75) mm ² using the three training datasets. Algorithm ICC for TPAs (ICC = 0.996) was similar to intra- and inter-observer manual results (ICC = 0.977, 0.995). Algorithm CoV = 6.98% for plaque areas was smaller than the inter-observer manual CoV (7.54%). For the Zhongnan dataset, DSC was 88.6% algorithm and manual TPAs were strongly correlated (r = 0.972, p < 0.001) with ∆TPA = -0.44 ±4.05 mm ² and ICC = 0.985. The proposed algorithm trained on small datasets and segmented a different dataset without retraining with accuracy and precision that may be useful clinically and for research.

Automatic segmentation for ultrasound image of carotid intimal-media based on improved superpixel generation algorithm and fractal theory

OBJECTIVE

Carotid atherosclerosis (CAS) is the main reason leading to cardiovascular conditions such as coronary heart disease and cerebrovascular diseases. In the carotid ultrasound images, the carotid intima-media structure can be observed in an annular narrow strip, which its inner contour corresponds to the carotid intima, and the outer contour corresponds to the carotid extima. With the development of carotid atherosclerosis, the carotid intima-media will gradually thicken. Therefore, doctors can observe the carotid intima-media so as to obtain the pathological changes of the internal structure of the patient's carotid arteries. However, due to the presence of artifacts and noises the quality of the ultrasound images are degraded, making it difficult to obtain accurate carotid intima-media structures. This article presents a novel self-adaptive method to enable obtaining the carotid intima-media through carotid intima/extima segmentation.

METHOD

After preprocessing the ultrasound images by homomorphic filtering and median filtering, we propose an improved superpixel generation algorithm that employs the fusion of gray-level and luminosity-based information to decompose the image into numerous superpixels and later presents the carotid intima. Meanwhile, based on the features of the carotid artery, the initial position of the carotid extima is located by the normalized cut algorithm and later the fractal theory is employed to segment the carotid extima.

RESULTS

The proposed method for segmenting carotid intima obtained mean values of the DICE true positive ratio (TPR), false positive ratio (FPR), precision scores of 97.797%, 99.126%, 0.540%, 97.202%, respectively. Further from the segmentation method of the carotid extima the performance measures such as mean DICE, TPR, accuracy, F-score obtained are 95.00%, 92.265%, 97.689%, 94.997%, respectively.

CONCLUSION

Comparing with traditional methods, the proposed method performed better. The experimental results indicated that the proposed method obtained the carotid intima-media both automatically and accurately thus effectively assist doctors in the diagnosis of CAS.

A Review on Joint Carotid Intima-Media Thickness and Plaque Area Measurement in Ultrasound for Cardiovascular/Stroke Risk Monitoring: Artificial Intelligence Framework

Cardiovascular diseases (CVDs) are the top ten leading causes of death worldwide. Atherosclerosis disease in the arteries is the main cause of the CVD, leading to myocardial infarction and stroke. The two primary image-based phenotypes used for monitoring the atherosclerosis burden is carotid intima-media thickness (cIMT) and plaque area (PA). Earlier segmentation and measurement methods were based on ad hoc conventional and semi-automated digital imaging solutions, which are unreliable, tedious, slow, and not robust. This study reviews the modern and automated methods such as artificial intelligence (AI)-based. Machine learning (ML) and deep learning (DL) can provide automated techniques in the detection and measurement of cIMT and PA from carotid vascular images. Both ML and DL techniques are examples of supervised learning, i.e., learn from "ground truth" images and transformation of test images that are not part of the training. This review summarizes (1) the evolution and impact of the fast-changing AI technology on cIMT/PA measurement, (2) the mathematical representations of ML/DL methods, and (3) segmentation approaches for cIMT/PA regions in carotid scans based for (a) region-of-interest detection and (b) lumen-intima and media-adventitia interface detection using ML/DL frameworks. AI-based methods for cIMT/PA segmentation have emerged for CVD/stroke risk monitoring and may expand to the recommended parameters for atherosclerosis assessment by carotid ultrasound.

Parameterized Strain Estimation for Vascular Ultrasound Elastography With Sparse Representation

Ultrasound vascular strain imaging has shown its potential to interrogate the motion of the vessel wall induced by the cardiac pulsation for predicting plaque instability. In this study, a sparse model strain estimator (SMSE) is proposed to reconstruct a dense strain field at a high resolution, with no spatial derivatives, and a high computation efficiency. This sparse model utilizes the highly-compacted property of discrete cosine transform (DCT) coefficients, thereby allowing to parameterize displacement and strain fields with truncated DCT coefficients. The derivation of affine strain components (axial and lateral strains and shears) was reformulated into solving truncated DCT coefficients and then reconstructed with them. Moreover, an analytical solution was derived to reduce estimation time. With simulations, the SMSE reduced estimation errors by up to 50% compared with the state-of-the-art window-based Lagrangian speckle model estimator (LSME). The SMSE was also proven to be more robust than the LSME against global and local noise. For in vitro and in vivo tests, residual strains assessing cumulated errors with the SMSE were 2 to 3 times lower than with the LSME. Regarding computation efficiency, the processing time of the SMSE was reduced by 4 to 25 times compared with the LSME, according to simulations, in vitro and in vivo results. Finally, phantom studies demonstrated the enhanced spatial resolution of the proposed SMSE algorithm against LSME.

Deep Learning for Carotid Plaque Segmentation using a Dilated U-Net Architecture

Carotid plaque segmentation in ultrasound longitudinal B-mode images using deep learning is presented in this work. We report on 101 severely stenotic carotid plaque patients. A standard U-Net is compared with a dilated U-Net architecture in which the dilated convolution layers were used in the bottleneck. Both a fully automatic and a semi-automatic approach with a bounding box was implemented. The performance degradation in plaque segmentation due to errors in the bounding box is quantified. We found that the bounding box significantly improved the performance of the networks with U-Net Dice coefficients of 0.48 for automatic and 0.83 for semi-automatic segmentation of plaque. Similar results were also obtained for the dilated U-Net with Dice coefficients of 0.55 for automatic and 0.84 for semi-automatic when compared to manual segmentations of the same plaque by an experienced sonographer. A 5% error in the bounding box in both dimensions reduced the Dice coefficient to 0.79 and 0.80 for U-Net and dilated U-Net respectively.

Added Value of Quantitative Ultrasound and Machine Learning in BI-RADS 4-5 Assessment of Solid Breast Lesions

The purpose of this study was to evaluate various combinations of 13 features based on shear wave elasticity (SWE), statistical and spectral backscatter properties of tissues, along with the Breast Imaging Reporting and Data System (BI-RADS), for classification of solid breast lesions at ultrasonography by means of random forests. One hundred and three women with 103 suspicious solid breast lesions (BI-RADS categories 4-5) were enrolled. Before biopsy, additional SWE images and a cine sequence of ultrasound images were obtained. The contours of lesions were delineated, and parametric maps of the homodyned-K distribution were computed on three regions: intra-tumoral, supra-tumoral and infra-tumoral zones. Maximum elasticity and total attenuation coefficient were also extracted. Random forests yielded receiver operating characteristic (ROC) curves for various combinations of features. Adding BI-RADS category improved the classification performance of other features. The best result was an area under the ROC curve of 0.97, with 75.9% specificity at 98% sensitivity.

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.

Diagnostic Accuracy of Echo Envelope Statistical Modeling Compared to B-Mode and Power Doppler Ultrasound Imaging in Patients With Clinically Diagnosed Lateral Epicondylosis of the Elbow

OBJECTIVES

To compare the accuracy of homodyned K quantitative ultrasound (QUS) with that of B-mode and Doppler ultrasound imaging for discriminating between lateral epicondylosis (LE) and asymptomatic elbows.

METHODS

This prospective study received Institutional Review Board approval, and participants provided written informed consent. Between February 2015 and March 2017, 30 LE elbows in 27 patients and 24 asymptomatic elbows in 13 volunteers underwent B-mode, Doppler, and radiofrequency ultrasound imaging of the common extensor tendon (CET) and radial collateral ligament (RCL). Two readers classified the elbows independently on the basis of a review of B-mode and Doppler images. The global and local estimates of QUS parameters (μ _n , 1/α, and k) were computed in the CET and CET-RCL regions, respectively, and the area of each region was calculated. A random-forest classifier identified the most discriminating 3-parameter combination: CET global estimate of 1/α, CET-RCL area, and local estimate of k.

RESULTS

The patients with LE had a mean age of 50 years (range, 31-66 years), and the volunteers had a mean age of 50 years (range, 37-57 years). The area under the receiver operating characteristic curve, sensitivity, and specificity of reader 1, reader 2, and the QUS-based model were 0.80 (95% confidence interval [CI], 0.66-0.95), 0.72 (95% CI, 0.56-0.89), and 0.88 (95% CI, 0.72-1.04); 0.79 (95% CI, 0.66-0.93), 0.65 (95% CI, 0.47-0.82), and 0.84 (95% CI, 0.67-1.01); and 0.82 (95% CI, 0.80-0.85), 0.73, and 0.79, respectively.

CONCLUSIONS

An automated, computer-based QUS technique diagnosed LE with accuracy of 0.82. This technique could provide quantitative biomarkers for the characterization of LE disease.

Assessment of Carotid Artery Plaque Components With Machine Learning Classification Using Homodyned-K Parametric Maps and Elastograms

Quantitative ultrasound (QUS) imaging methods, including elastography, echogenicity analysis, and speckle statistical modeling, are available from a single ultrasound (US) radio-frequency data acquisition. Since these US imaging methods provide complementary quantitative tissue information, characterization of carotid artery plaques may gain from their combination. Sixty-six patients with symptomatic ( n = 26 ) and asymptomatic ( n = 40 ) carotid atherosclerotic plaques were included in the study. Of these, 31 underwent magnetic resonance imaging (MRI) to characterize plaque vulnerability and quantify plaque components. US radio-frequency data sequence acquisitions were performed on all patients and were used to compute noninvasive vascular US elastography and other QUS features. Additional QUS features were computed from three types of images: homodyned-K (HK) parametric maps, Nakagami parametric maps, and log-compressed B-mode images. The following six classification tasks were performed: detection of 1) a small area of lipid; 2) a large area of lipid; 3) a large area of calcification; 4) the presence of a ruptured fibrous cap; 5) differentiation of MRI-based classification of nonvulnerable carotid plaques from neovascularized or vulnerable ones; and 6) confirmation of symptomatic versus asymptomatic patients. Feature selection was first applied to reduce the number of QUS parameters to a maximum of three per classification task. A random forest machine learning algorithm was then used to perform classifications. Areas under receiver-operating curves (AUCs) were computed with a bootstrap method. For all tasks, statistically significant higher AUCs were achieved with features based on elastography, HK parametric maps, and B-mode gray levels, when compared to elastography alone or other QUS alone ( ). For detection of a large area of lipid, the combination yielding the highest AUC (0.90, 95% CI 0.80-0.92, ) was based on elastography, HK, and B-mode gray-level features. To detect a large area of calcification, the highest AUC (0.95, 95% CI 0.94-0.96, ) was based on HK and B-mode gray level features. For other tasks, AUCs varied between 0.79 and 0.97. None of the best combinations contained Nakagami features. This study shows the added value of combining different features computed from a single US acquisition with machine learning to characterize carotid artery plaques.

Interoperator Reproducibility of Carotid Elastography for Identification of Vulnerable Atherosclerotic Plaques

Ultrasound-based carotid elastography has been developed to evaluate the vulnerability of carotid atherosclerotic plaques. The aim of this study was to investigate the in vivo interoperator reproducibility of carotid elastography for the identification of vulnerable plaques, with high-resolution magnetic resonance imaging (MRI) as reference. Ultrasound radio-frequency data of 45 carotid arteries (including 53 plaques) from 32 volunteers were acquired separately by two experienced operators in the longitudinal view and then were used to estimate the interframe axial strain rate (ASR) with a two-step optical flow method. The maximum 99th percentile of absolute ASR of all plaques in a carotid artery was used as the elastographic index. MRI scanning was also performed on each volunteer to identify the vulnerable plaque. The results showed no systematic bias in the Bland-Altman plot and an intraclass correlation coefficient of 0.66 between the two operators. In addition, no statistical significance was found between the receiver operating characteristic (ROC) curves from the two operators ( ), and their areas under the ROC curves were 0.83 and 0.77, respectively. Using the mean measurements of the two operators as the classification criterion, a sensitivity of 71.4%, a specificity of 87.1%, and an accuracy of 82.2% were obtained with a cutoff value of 1.37 [Formula: see text]. This study validates the interoperator reproducibility of ultrasound-based carotid elastography for identifying vulnerable carotid plaques.

Investigation of out-of-plane motion artifacts in 2D noninvasive vascular ultrasound elastography

Ultrasound noninvasive vascular elastography (NIVE) has shown its potential to measure strains of carotid arteries to predict plaque instability. When two-dimensional (2D) strain estimation is performed, either in longitudinal or cross-sectional view, only in-plane motions are considered. The motions in elevation direction (i.e. perpendicular to the imaging plane), can induce estimation artifacts affecting the accuracy of 2D NIVE. The influence of such out-of-plane motions on the performance of axial strain and axial shear strain estimations has been evaluated in this study. For this purpose, we designed a diseased carotid bifurcation phantom with a 70% stenosis and an in vitro experimental setup to simulate orthogonal out-of-plane motions of 1 mm, 2 mm and 3 mm. The Lagrangian speckle model estimator (LSME) was used to estimate axial strains and shears under pulsatile conditions. As anticipated, in vitro results showed more strain estimation artifacts with increasing magnitudes of motions in elevation. However, even with an out-of-plane motion of 2.0 mm, strain and shear estimations having inter-frame correlation coefficients higher than 0.85 were obtained. To verify findings of in vitro experiments, a clinical LSME dataset obtained from 18 participants with carotid artery stenosis was used. Deduced out-of-plane motions (ranging from 0.25 mm to 1.04 mm) of the clinical dataset were classified into three groups: small, moderate and large elevational motions. Clinical results showed that pulsatile time-varying strains and shears remained reproducible for all motion categories since inter-frame correlation coefficients were higher than 0.70, and normalized cross-correlations (NCC) between radiofrequency (RF) images were above 0.93. In summary, the performance of LSME axial strain and shear estimations appeared robust in the presence of out-of-plane motions (<2 mm) as encountered during clinical ultrasound imaging.

Carotid Plaque Vulnerability Assessment Using Ultrasound Elastography and Echogenicity Analysis

OBJECTIVE

The purpose of this study was to evaluate ultrasound elastography and echogenicity analysis to discriminate between carotid plaques in patients with symptomatic internal carotid artery (ICA) stenosis versus patients with asymptomatic stenosis.

SUBJECTS AND METHODS

Patients with symptomatic and asymptomatic ICA stenosis of more than 50% were recruited for the study. After both carotid arteries were scanned, plaque translation and elastography and echogenicity features were assessed. Parameters of index stenosis (i.e., symptomatic or more severe stenosis) were compared between populations. For further validation, parameters of index stenosis were also compared with those of the contralateral artery for segments with plaque. Segments without plaque on the index side were also evaluated between populations. ROC curve analyses were performed using a cross-validation method with bootstrapping to calculate sensitivity and specificity.

RESULTS

Sixty-six patients with symptomatic (n = 26) or asymptomatic (n = 40) carotid stenoses were included. The maximum axial strain (p < 0.001), maximum axial shear strain magnitude (p = 0.03), and percentage of low-intensity of gray level (p = 0.01) of the index ICA were lower for patients with symptoms than for those without symptoms. In both groups, the contralateral ICA had translation and elastography and echogenicity parameters similar to those of the index ICA in patients with asymptomatic stenosis. The ROC curve for the detection of vulnerable plaques in patients with symptomatic stenosis was higher when ultrasound elastography and ultrasound echogenicity were used in combination than when each method was used alone (p < 0.001); a sensitivity of 71.6% and a specificity of 79.3% were obtained.

CONCLUSION

This pilot study establishes the usefulness of combining elastography with echogenicity analysis to discriminate plaques in patients with symptomatic ICA stenosis versus asymptomatic stenosis.

Ex Vivo and In Vivo Monitoring and Characterization of Thermal Lesions by High-Intensity Focused Ultrasound and Microwave Ablation Using Ultrasonic Nakagami Imaging

The feasibility of ultrasonic Nakagami imaging to evaluate thermal lesions by high-intensity focused ultrasound and microwave ablation was explored in ex vivo and in vivo liver models. Dynamic changes of the ultrasonic Nakagami parameter in thermal lesions were calculated, and ultrasonic B-mode and Nakagami images were reconstructed simultaneously. The contrast-to-noise ratio (CNR) between thermal lesions and normal tissue was used to estimate the contrast resolution of the monitoring images. After thermal ablation, a bright hyper-echoic region appeared in the ultrasonic B-mode and Nakagami images, identifying the thermal lesion. During thermal ablation, mean values of Nakagami parameter showed an increasing trend from 0.72 to 1.01 for the ex vivo model and 0.54 to 0.72 for the in vivo model. After thermal ablation, mean CNR values of the ultrasonic Nakagami images were 1.29 dB (ex vivo) and 0.80 dB (in vivo), significantly higher ( ) than those for B-mode images. Thermal lesion size, assessed using ultrasonic Nakagami images, shows a good correlation to those obtained from the gross-pathology images (for the ex vivo model: length, = 0.96; width, = 0.90; for the in vivo model: length, = 0.95; width, = 0.85). This preliminary study suggests that ultrasonic Nakagami parameter may have a potential use in evaluating the formation of thermal lesions with better image contrast. Moreover, ultrasonic Nakagami imaging combined with B-mode imaging may be utilized as an alternative modality in developing monitoring systems for image-guided thermal ablation treatments.

Carotid plaque segmentation from three-dimensional ultrasound images by direct three-dimensional sparse field level-set optimization

Total plaque volume (TPV) measured from 3D carotid ultrasound has been shown to be able to predict cardiovascular events and is sensitive in detecting treatment effects. Manual plaque segmentation was performed in previous studies to quantify TPV, but is tedious, requires long training times and is prone to observer variability. This article introduces the first 3D direct volume-based level-set algorithm to segment plaques from 3D carotid ultrasound images. The plaque surfaces were first initialized based on the lumen and outer wall boundaries generated by a previously described semi-automatic algorithm and then deformed by a direct three-dimensional sparse field level-set algorithm, which enforced the longitudinal continuity of the segmented plaque surfaces. This is a marked advantage as compared to a previously proposed 2D slice-by-slice plaque segmentation method. In plaque boundary initialization, the previous technique performed a search on lines connecting corresponding point pairs of the outer wall and lumen boundaries. A limitation of this initialization strategy was that an inaccurate initial plaque boundary would be generated if the plaque was not enclosed entirely by the wall and lumen boundaries. A mechanism is proposed to extend the search range in order to capture the entire plaque if the outer wall boundary lies on a weak edge in the 3D ultrasound image. The proposed method was compared with the previously described 2D slice-by-slice plaque segmentation method in 26 three-dimensional carotid ultrasound images containing 27 plaques with volumes ranging from 12.5 to 450.0 mm³. The manually segmented plaque boundaries serve as the surrogate gold standard. Segmentation accuracy was quantified by volume-, area- and distance-based metrics, including absolute plaque volume difference (|ΔPV|), Dice similarity coefficient (DSC), mean and maximum absolute distance (MAD and MAXD). The proposed direct 3D plaque segmentation algorithm was associated with a significantly lower |ΔPV|, MAD and MAXD, and a significantly higher DSC compared to the previously described slice-by-slice algorithm (|ΔPV|:p=0.012, DSC: p=2.1×10^-4, MAD: p=1.3×10^-4, MAXD: p=5.2×10^-4). The proposed 3D volume-based algorithm required 72±22 s to segment a plaque, which is 40% lower than the 2D slice-by-slice algorithm (114±18 s). The proposed automatic plaque segmentation method generates accurate and reproducible boundaries efficiently and will allow for streamlining plaque quantification based on 3D ultrasound images.

Carotid artery intima-media thickness measurement in children with normal and increased body mass index: a comparison of three techniques

BACKGROUND

Common carotid artery intima-media thickness is a marker of subclinical atherosclerosis. In children, increased intima-media thickness is associated with obesity and the risk of cardiovascular events in adulthood.

OBJECTIVE

To compare intima-media thickness measurements using B-mode ultrasound, radiofrequency (RF) echo tracking, and RF speckle probability distribution in children with normal and increased body mass index (BMI).

MATERIALS AND METHODS

We prospectively measured intima-media thickness in 120 children randomly selected from two groups of a longitudinal cohort: normal BMI and increased BMI, defined by BMI ≥85th percentile for age and gender. We followed Mannheim recommendations. We used M'Ath-Std for automated B-mode imaging, M-line processing of RF signal amplitude for RF echo tracking, and RF signal segmentation and averaging using probability distributions defining image speckle. Statistical analysis included Wilcoxon and Mann-Whitney tests, and Pearson correlation coefficient and intra-class correlation coefficient (ICC).

RESULTS

Children were 10-13 years old (mean: 11.7 years); 61% were boys. The mean age was 11.4 years (range: 10.0-13.1 years) for the normal BMI group and 12.0 years (range: 10.1-13.5 years) for the increased BMI group. The normal BMI group included 58% boys and the increased BMI group 63% boys. RF echo tracking method was successful in 79 children as opposed to 114 for the B-mode method and all 120 for the probability distribution method. Techniques were weakly correlated: ICC=0.34 (95% confidence interval [CI]: 0.27-0.39). Intima-media thickness was significantly higher in the increased BMI than normal BMI group using the RF techniques and borderline for the B-mode technique. Mean differences between weight groups were: B-mode, 0.02 mm (95% CI: 0.00 to 0.04), P=0.05; RF echo tracking, 0.03 mm (95% CI: 0.01 to 0.05), P=0.01; and RF speckle probability distribution, 0.03 mm (95% CI: 0.01 to 0.05), P=0.002.

CONCLUSION

Though techniques are not interchangeable, all showed increased intima-media thickness in children with increased BMI. RF echo tracking method had the lowest success rate at calculating intima-media thickness. For patient follow-up and cohort comparisons, the same technique should be used throughout.

An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image

BACKGROUND AND OBJECTIVE

Carotid artery atherosclerosis is an important cause of stroke. Ultrasound imaging has been widely used in the diagnosis of atherosclerosis. Therefore, segmenting atherosclerotic carotid plaque in ultrasound image is an important task. Accurate plaque segmentation is helpful for the measurement of carotid plaque burden. In this paper, we propose and evaluate a novel learning-based integrated framework for plaque segmentation.

METHODS

In our study, four different classification algorithms, along with the auto-context iterative algorithm, were employed to effectively integrate features from ultrasound images and later also the iteratively estimated and refined probability maps together for pixel-wise classification. The four classification algorithms were support vector machine with linear kernel, support vector machine with radial basis function kernel, AdaBoost and random forest. The plaque segmentation was implemented in the generated probability map. The performance of the four different learning-based plaque segmentation methods was tested on 29 B-mode ultrasound images. The evaluation indices for our proposed methods were consisted of sensitivity, specificity, Dice similarity coefficient, overlap index, error of area, absolute error of area, point-to-point distance, and Hausdorff point-to-point distance, along with the area under the ROC curve.

RESULTS

The segmentation method integrated the random forest and an auto-context model obtained the best results (sensitivity 80.4 ± 8.4%, specificity 96.5 ± 2.0%, Dice similarity coefficient 81.0 ± 4.1%, overlap index 68.3 ± 5.8%, error of area -1.02 ± 18.3%, absolute error of area 14.7 ± 10.9%, point-to-point distance 0.34 ± 0.10 mm, Hausdorff point-to-point distance 1.75 ± 1.02 mm, and area under the ROC curve 0.897), which were almost the best, compared with that from the existed methods.

CONCLUSIONS

Our proposed learning-based integrated framework investigated in this study could be useful for atherosclerotic carotid plaque segmentation, which will be helpful for the measurement of carotid plaque burden.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

Carotid Artery Plaque Vulnerability Assessment Using Noninvasive Ultrasound Elastography: Validation With MRI

OBJECTIVE

Vulnerable and nonvulnerable carotid artery plaques have different tissue morphology and composition that may affect plaque biomechanics. The objective of this study is to evaluate plaque vulnerability with the use of ultrasound noninvasive vascular elastography (NIVE).

MATERIALS AND METHODS

Thirty-one patients (mean [± SD] age, 69 ± 7 years) with stenosis of the internal carotid artery of 50% or greater were enrolled in this cross-sectional study. Elastography parameters quantifying axial strain, shear strain, and translation motion were used to characterize carotid artery plaques as nonvulnerable, neovascularized, and vulnerable. Maximum axial strain, cumulated axial strain, mean shear strain, cumulated shear strain, cumulated axial translation, and cumulated lateral translations were measured. Cumulated measurements were summed over a cardiac cycle. The ratio of cumulated axial strain to cumulated axial translation was also evaluated. The reference method used to characterize plaques was high-resolution MRI.

RESULTS

According to MRI, seven plaques were vulnerable, 12 were nonvulnerable without neovascularity, and 12 were nonvulnerable with neovascularity (a precursor of vulnerability). The two parameters cumulated axial translation and the ratio of cumulated axial strain to cumulated axial translation could discriminate between nonvulnerable plaques and vulnerable plaques or determine the presence of neovascularity in nonvulnerable plaques (which was also possible with the mean shear strain parameter). All parameters differed between the non-vulnerable plaque group and the group that combined vulnerable plaques and plaques with neovascularity. The most discriminating parameter for the detection of vulnerable neovascularized plaques was the ratio of cumulated axial strain to cumulated axial translation (expressed as percentage per millimeter) (mean ratio, 39.30%/mm ± 12.80%/mm for nonvulnerable plaques without neovascularity vs 63.79%/mm ± 17.59%/mm for vulnerable plaques and nonvulnerable plaques with neovascularity, p = 0.002), giving an AUC value of 0.886.

CONCLUSION

The imaging parameters cumulated axial translation and the ratio of cumulated axial strain to cumulated axial translation, as computed using NIVE, were able to discriminate vulnerable carotid artery plaques characterized by MRI from nonvulnerable carotid artery plaques. Consideration of neovascularized plaques improved the performance of NIVE. NIVE may be a valuable alternative to MRI for carotid artery plaque assessment.

Feasibility of Using Ultrasonic Nakagami Imaging for Monitoring Microwave-Induced Thermal Lesion in Ex Vivo Porcine Liver

The feasibility of using ultrasonic Nakagami imaging to evaluate thermal lesions induced by microwave ablation (MWA) in ex vivo porcine liver was explored. Dynamic changes in echo amplitudes and Nakagami parameters in the region of the MWA-induced thermal lesion, as well as the contrast-to-noise ratio (CNR) between the MWA-induced thermal lesion and the surrounding normal tissue, were calculated simultaneously during the MWA procedure. After MWA exposure, a bright hyper-echoic region appeared in ultrasonic B-mode and Nakagami parameter images as an indicator of the thermal lesion. Mean values of the Nakagami parameter in the thermal lesion region increased to 0.58, 0.71 and 0.91 after 1, 3 and 5 min of MVA. There were no significant differences in envelope amplitudes in the thermal lesion region among ultrasonic B-mode images obtained after different durations of MWA. Unlike ultrasonic B-mode images, Nakagami images were less affected by the shadow effect in monitoring of MWA exposure, and a fairly complete hyper-echoic region was observed in the Nakagami image. The mean value of the Nakagami parameter increased from approximately 0.47 to 0.82 during MWA exposure. At the end of the postablation stage, the mean value of the Nakagami parameter decreased to 0.55 and was higher than that before MWA exposure. CNR values calculated for Nakagami parameter images increased from 0.13 to approximately 0.61 during MWA and then decreased to 0.26 at the end of the post-ablation stage. The corresponding CNR values calculated for ultrasonic B-mode images were 0.24, 0.42 and 0.17. This preliminary study on ex vivo porcine liver suggested that Nakagami imaging have potential use in evaluating the formation of MWA-induced thermal lesions. Further in vivo studies are needed to evaluate the potential application.

Lumen segmentation and motion estimation in B-mode and contrast-enhanced ultrasound images of the carotid artery in patients with atherosclerotic plaque

In standard B-mode ultrasound (BMUS), segmentation of the lumen of atherosclerotic carotid arteries and studying the lumen geometry over time are difficult owing to irregular lumen shapes, noise, artifacts, and echolucent plaques. Contrast enhanced ultrasound (CEUS) improves lumen visualization, but lumen segmentation remains challenging owing to varying intensities, CEUS-specific artifacts and lack of tissue visualization. To overcome these challenges, we propose a novel method using simultaneously acquired BMUS&CEUS image sequences. Initially, the method estimates nonrigid motion (NME) from the image sequences, using intensity-based image registration. The motion-compensated image sequence is then averaged to obtain a single "epitome" image with improved signal-to-noise ratio. The lumen is segmented from the epitome image through an intensity joint-histogram classification and a graph-based segmentation. NME was validated by comparing displacements with manual annotations in 11 carotids. The average root mean square error (RMSE) was 112±73 μm . Segmentation results were validated against manual delineations in the epitome images of two different datasets, respectively containing 11 (RMSE 191±43 μm) and 10 (RMSE 351±176 μm ) carotids. From the deformation fields, we derived arterial distensibility with values comparable to the literature. The average errors in all experiments were in the inter-observer variability range. To the best of our knowledge, this is the first study exploiting combined BMUS&CEUS images for atherosclerotic carotid lumen segmentation.

Fully automated carotid plaque segmentation in combined contrast-enhanced and B-mode ultrasound

Carotid plaque segmentation in B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) is crucial to the assessment of plaque morphology and composition, which are linked to plaque vulnerability. Segmentation in BMUS is challenging because of noise, artifacts and echo-lucent plaques. CEUS allows better delineation of the lumen but contains artifacts and lacks tissue information. We describe a method that exploits the combined information from simultaneously acquired BMUS and CEUS images. Our method consists of non-rigid motion estimation, vessel detection, lumen-intima segmentation and media-adventitia segmentation. The evaluation was performed in training (n = 20 carotids) and test (n = 28) data sets by comparison with manually obtained ground truth. The average root-mean-square errors in the training and test data sets were comparable for media-adventitia (411 ± 224 and 393 ± 239 μm) and for lumen-intima (362 ± 192 and 388 ± 200 μm), and were comparable to inter-observer variability. To the best of our knowledge, this is the first method to perform fully automatic carotid plaque segmentation using combined BMUS and CEUS.

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.