Ankle–Brachial Index and Its Link to Automated Carotid Ultrasound Measurement of Intima–Media Thickness Variability in 500 Japanese Coronary Artery Disease Patients

MultiNet 2.0: A lightweight attention-based deep learning network for stenosis measurement in carotid ultrasound scans and cardiovascular risk assessment

BACKGROUND

Cardiovascular diseases (CVD) cause 19 million fatalities each year and cost nations billions of dollars. Surrogate biomarkers are established methods for CVD risk stratification; however, manual inspection is costly, cumbersome, and error-prone. The contemporary artificial intelligence (AI) tools for segmentation and risk prediction, including older deep learning (DL) networks employ simple merge connections which may result in semantic loss of information and hence low in accuracy.

METHODOLOGY

We hypothesize that DL networks enhanced with attention mechanisms can do better segmentation than older DL models. The attention mechanism can concentrate on relevant features aiding the model in better understanding and interpreting images. This study proposes MultiNet 2.0 (AtheroPoint, Roseville, CA, USA), two attention networks have been used to segment the lumen from common carotid artery (CCA) ultrasound images and predict CVD risks.

RESULTS

The database consisted of 407 ultrasound CCA images of both the left and right sides taken from 204 patients. Two experts were hired to delineate borders on the 407 images, generating two ground truths (GT1 and GT2). The results were far better than contemporary models. The lumen dimension (LD) error for GT1 and GT2 were 0.13±0.08 and 0.16±0.07 mm, respectively, the best in market. The AUC for low, moderate and high-risk patients' detection from stenosis data for GT1 were 0.88, 0.98, and 1.00 respectively. Similarly, for GT2, the AUC values for low, moderate, and high-risk patient detection were 0.93, 0.97, and 1.00, respectively. The system can be fully adopted for clinical practice in AtheroEdge™ model by AtheroPoint, Roseville, CA, USA.

Association of endothelial function and lower extremity perfusion in peripheral artery disease

Background: The current study aims to investigate the association between endothelial function and lower extremity perfusion in patients with peripheral artery disease (PAD). Patients and methods: In total 229 patients with PAD (Rutherford stage 0-3) were enrolled in the current study. Endothelial function was assessed by measuring flow-mediated dilation (FMD) and endothelial cell proliferation capacity (ECPC). Lower extremity perfusion was assessed by measuring oscillometry-based ankle brachial index (oABI) and pulse wave index (PWI). In addition, carotid intima-media-thickness (cIMT) was also measured as a surrogate marker for atherosclerosis. Correlations between FMD, ECPC, oABI, PWI, and cIMT were analysed using Pearson correlation coefficient. The relationship between the above variables and the severity of PAD was investigated using ordinal logistic regression analysis. Results: Correlation analysis showed that FMD negatively associated with PWI (r = -0.183, p = 0.005), ECPC positively associated with oABI (r = 0.162, p = 0.014), and oABI negatively associated with PWI (r = -0.264, p < 0.001). Ordinal logistic regression analysis showed that ECPC (β = -0.009, p = 0.048), oABI (β = -5.290, p < 0.001), and age (β = -0.058, p = 0.002) negatively associated with the PAD Rutherford stages. In addition, PWI (β = 0.006, p < 0.001), cIMT (β = 18.363, p = 0.043) positively associated with the PAD Rutherford stages. Conclusions: Endothelial function significantly associates with lower extremity perfusion in patients with PAD, and both are related to the severity of PAD.

Deep Learning Paradigm and Its Bias for Coronary Artery Wall Segmentation in Intravascular Ultrasound Scans: A Closer Look

BACKGROUND AND MOTIVATION

Coronary artery disease (CAD) has the highest mortality rate; therefore, its diagnosis is vital. Intravascular ultrasound (IVUS) is a high-resolution imaging solution that can image coronary arteries, but the diagnosis software via wall segmentation and quantification has been evolving. In this study, a deep learning (DL) paradigm was explored along with its bias.

METHODS

Using a PRISMA model, 145 best UNet-based and non-UNet-based methods for wall segmentation were selected and analyzed for their characteristics and scientific and clinical validation. This study computed the coronary wall thickness by estimating the inner and outer borders of the coronary artery IVUS cross-sectional scans. Further, the review explored the bias in the DL system for the first time when it comes to wall segmentation in IVUS scans. Three bias methods, namely (i) ranking, (ii) radial, and (iii) regional area, were applied and compared using a Venn diagram. Finally, the study presented explainable AI (XAI) paradigms in the DL framework.

FINDINGS AND CONCLUSIONS

UNet provides a powerful paradigm for the segmentation of coronary walls in IVUS scans due to its ability to extract automated features at different scales in encoders, reconstruct the segmented image using decoders, and embed the variants in skip connections. Most of the research was hampered by a lack of motivation for XAI and pruned AI (PAI) models. None of the UNet models met the criteria for bias-free design. For clinical assessment and settings, it is necessary to move from a paper-to-practice approach.

Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

Stroke and cardiovascular diseases (CVD) significantly affect the world population. The early detection of such events may prevent the burden of death and costly surgery. Conventional methods are neither automated nor clinically accurate. Artificial Intelligence-based methods of automatically detecting and predicting the severity of CVD and stroke in their early stages are of prime importance. This study proposes an attention-channel-based UNet deep learning (DL) model that identifies the carotid plaques in the internal carotid artery (ICA) and common carotid artery (CCA) images. Our experiments consist of 970 ICA images from the UK, 379 CCA images from diabetic Japanese patients, and 300 CCA images from post-menopausal women from Hong Kong. We combined both CCA images to form an integrated database of 679 images. A rotation transformation technique was applied to 679 CCA images, doubling the database for the experiments. The cross-validation K5 (80% training: 20% testing) protocol was applied for accuracy determination. The results of the Attention-UNet model are benchmarked against UNet, UNet++, and UNet3P models. Visual plaque segmentation showed improvement in the Attention-UNet results compared to the other three models. The correlation coefficient (CC) value for Attention-UNet is 0.96, compared to 0.93, 0.96, and 0.92 for UNet, UNet++, and UNet3P models. Similarly, the AUC value for Attention-UNet is 0.97, compared to 0.964, 0.966, and 0.965 for other models. Conclusively, the Attention-UNet model is beneficial in segmenting very bright and fuzzy plaque images that are hard to diagnose using other methods. Further, we present a multi-ethnic, multi-center, racial bias-free study of stroke risk assessment.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Metabolomics of peripheral artery disease

The science of metabolomics has emerged as a novel tool for studying changes in metabolism that accompany different disease states. Several studies have applied this evolving field to the study of various cardiovascular disease states, which has led to improved understanding of metabolic changes that underlie heart failure and ischemic heart disease. A significant amount of progress has also been made in the identification of novel biomarkers of cardiovascular disease. Another common atherosclerotic disease, peripheral artery disease (PAD) affects arteries of the lower extremities. Although certain aspects of the disease pathophysiology overlap with other cardiovascular diseases in general, PAD patients suffer unique manifestations that lead to significant morbidity and mortality as well as severe functional limitations. Furthermore, because over half of PAD patients are asymptomatic, there is a need for improved diagnostic and screening methods. Identification of metabolites associated with the disease may thus be a promising approach for PAD. However, PAD remains highly understudied. In this chapter, we discuss the application of metabolomics to the study of PAD.

Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization

The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms-random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~ 3% over the univariate analysis with IPN alone (0.97 vs. 0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~ 17.8% over the Cox-based model (0.86 vs. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.

Artificial intelligence framework for predictive cardiovascular and stroke risk assessment models: A narrative review of integrated approaches using carotid ultrasound

RECENT FINDINGS

Cardiovascular disease (CVD) is the leading cause of mortality and poses challenges for healthcare providers globally. Risk-based approaches for the management of CVD are becoming popular for recommending treatment plans for asymptomatic individuals. Several conventional predictive CVD risk models based do not provide an accurate CVD risk assessment for patients with different baseline risk profiles. Artificial intelligence (AI) algorithms have changed the landscape of CVD risk assessment and demonstrated a better performance when compared against conventional models, mainly due to its ability to handle the input nonlinear variations. Further, it has the flexibility to add risk factors derived from medical imaging modalities that image the morphology of the plaque. The integration of noninvasive carotid ultrasound image-based phenotypes with conventional risk factors in the AI framework has further provided stronger power for CVD risk prediction, so-called "integrated predictive CVD risk models."

PURPOSE

of the review: The objective of this review is (i) to understand several aspects in the development of predictive CVD risk models, (ii) to explore current conventional predictive risk models and their successes and challenges, and (iii) to refine the search for predictive CVD risk models using noninvasive carotid ultrasound as an exemplar in the artificial intelligence-based framework.

CONCLUSION

Conventional predictive CVD risk models are suboptimal and could be improved. This review examines the potential to include more noninvasive image-based phenotypes in the CVD risk assessment using powerful AI-based strategies.

Two-stage artificial intelligence model for jointly measurement of atherosclerotic wall thickness and plaque burden in carotid ultrasound: A screening tool for cardiovascular/stroke risk assessment

MOTIVATION

The early screening of cardiovascular diseases (CVD) can lead to effective treatment. Thus, accurate and reliable atherosclerotic carotid wall detection and plaque measurements are crucial. Current measurement methods are time-consuming and do not utilize the power of knowledge-based paradigms such as artificial intelligence (AI). We present an AI-based methodology for the joint automated detection and measurement of wall thickness and carotid plaque (CP) in the form of carotid intima-media thickness (cIMT) and total plaque area (TPA), a class of AtheroEdge™ system (AtheroPoint™, CA, USA).

METHOD

The novel system consists of two stages, and each stage comprises an independent deep learning (DL) model. In Stage I, the first DL model segregates the common carotid artery (CCA) patches from ultrasound (US) images into the rectangular wall and non-wall patches. The characterized wall patches are integrated to form the region of interest (ROI), which is then fed into Stage II. In Stage II, the second DL model segments the far wall region. Lumen-intima (LI) and media-adventitial (MA) boundaries are then extracted from the wall region, which is then used for cIMT and PA measurement.

RESULTS

Using the database of 250 carotid scans, the cIMT error using the AI model is 0.0935±0.0637 mm, which is lower than those of all previous methods. The PA error is found to be 2.7939±2.3702 mm². The system's correlation coefficient (CC) between AI and ground truth (GT) values for cIMT is 0.99 (p < 0.0001), which is higher compared with the CC of 0.96 (p < 0.0001) shown by the earlier DL method. The CC for PA between AI and GT values is 0.89 (p < 0.0001).

CONCLUSION

A novel AI-based strategy was applied to carotid US images for the joint detection of carotid wall thickness (cWT) and plaque area (PA), followed by cIMT and PA measurement. This AI-based strategy shows improved performance using the patch technique compared with previous methods using full carotid scans.

Integration of estimated glomerular filtration rate biomarker in image-based cardiovascular disease/stroke risk calculator: a south Asian-Indian diabetes cohort with moderate chronic kidney disease

BACKGROUND

Recently, a 10-year image-based integrated calculator (called AtheroEdge Composite Risk Score-AECRS1.0) was developed which combines conventional cardiovascular risk factors (CCVRF) with image phenotypes derived from carotid ultrasound (CUS). Such calculators did not include chronic kidney disease (CKD)-based biomarker called estimated glomerular filtration rate (eGFR). The novelty of this study is to design and develop an advanced integrated version called-AECRS2.0 that combines eGFR with image phenotypes to compute the composite risk score. Furthermore, AECRS2.0 was benchmarked against QRISK3 which considers eGFR for risk assessment.

METHODS

The method consists of three major steps: 1) five, current CUS image phenotypes (CUSIP) measurements using AtheroEdge system (AtheroPoint, CA, USA) consisting of: average carotid intima-media thickness (cIMTave), maximum cIMT (cIMTmax), minimum cIMT (cIMTmin), variability in cIMT (cIMTV), and total plaque area (TPA); 2) five, 10-year CUSIP measurements by combining these current five CUSIP with 11 CCVRF (age, ethnicity, gender, body mass index, systolic blood pressure, smoking, carotid artery type, hemoglobin, low-density lipoprotein cholesterol, total cholesterol, and eGFR); 3) AECRS2.0 risk score computation and its comparison to QRISK3 using area-under-the-curve (AUC).

RESULTS

South Asian-Indian 339 patients were retrospectively analyzed by acquiring their left/right common carotid arteries (678 CUS, mean age: 54.25±9.84 years; 75.22% males; 93.51% diabetic with HbA1c ≥6.5%; and mean eGFR 73.84±20.91 mL/min/1.73m²). The proposed AECRS2.0 reported higher AUC (AUC=0.89, P<0.001) compared to QRISK3 (AUC=0.51, P<0.001) by ~74% in CKD patients.

CONCLUSIONS

An integrated calculator AECRS2.0 can be used to assess the 10-year CVD/stroke risk in patients suffering from CKD. AECRS2.0 was much superior to QRISK3.

Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm

BACKGROUND

Stroke is in the top three leading causes of death worldwide. Non-invasive monitoring of stroke can be accomplished via stenosis measurements. The current conventional image-based methods for these measurements are not accurate and reliable. They do not incorporate shape and intelligent learning component in their design.

METHODS

In this study, we propose a deep learning (DL)-based methodology for accurate measurement of stenosis in common carotid artery (CCA) ultrasound (US) scans using a class of AtheroEdge system from AtheroPoint, USA. Three radiologists manually traced the lumen-intima (LI) for the near and the far walls, respectively, which served as a gold standard (GS) for training the DL-based model. Three DL-based systems were developed based on three types of GS.

RESULTS

IRB approved (Toho University, Japan) 407 US scans from 204 patients were collected. The risk was characterized into three classes: low, moderate, and high-risk. The area-under-curve (AUC) corresponding to three DL systems using receiver operating characteristic (ROC) analysis computed were: 0.90, 0.94 and 0.86, respectively.

CONCLUSIONS

Novel DL-based strategy showed reliable, accurate and stable stenosis severity index (SSI) measurements.

Effect of carotid image-based phenotypes on cardiovascular risk calculator: AECRS1.0

Today, the 10-year cardiovascular risk largely relies on conventional cardiovascular risk factors (CCVRFs) and suffers from the effect of atherosclerotic wall changes. In this study, we present a novel risk calculator AtheroEdge Composite Risk Score (AECRS1.0), designed by fusing CCVRF with ultrasound image-based phenotypes. Ten-year risk was computed using the Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study 56 (UKPDS56), UKPDS60, Reynolds Risk Score (RRS), and pooled composite risk (PCR) score. AECRS1.0 was computed by measuring the 10-year five carotid phenotypes such as IMT (ave., max., min.), IMT variability, and total plaque area (TPA) by fusing eight CCVRFs and then compositing them. AECRS1.0 was then benchmarked against the five conventional cardiovascular risk calculators by computing the receiver operating characteristics (ROC) and area under curve (AUC) values with a 95% CI. Two hundred four IRB-approved Japanese patients' left/right common carotid arteries (407 ultrasound scans) were collected with a mean age of 69 ± 11 years. The calculators gave the following AUC: FRS, 0.615; UKPDS56, 0.576; UKPDS60, 0.580; RRS, 0.590; PCRS, 0.613; and AECRS1.0, 0.990. When fusing CCVRF, TPA reported the highest AUC of 0.81. The patients were risk-stratified into low, moderate, and high risk using the standardized thresholds. The AECRS1.0 demonstrated the best performance on a Japanese diabetes cohort when compared with five conventional calculators. Graphical abstract AECRS1.0: Carotid ultrasound image phenotype-based 10-year cardiovascular risk calculator. The figure provides brief overview of the proposed carotid image phenotype-based 10-year cardiovascular risk calculator called AECRS1.0. AECRS1.0 was also benchmarked against five conventional cardiovascular risk calculators (Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study 56 (UKPDS56), UKPDS60, Reynolds Risk Score (RRS), and pooled composite risk (PCR) score).

Nonlinear model for the carotid artery disease 10-year risk prediction by fusing conventional cardiovascular factors to carotid ultrasound image phenotypes: A Japanese diabetes cohort study

MOTIVATION

This study presents a novel nonlinear model which can predict 10-year carotid ultrasound image-based phenotypes by fusing nine traditional cardiovascular risk factors (ethnicity, gender, age, artery type, body mass index, hemoglobin A1c, hypertension, low-density lipoprotein, and smoking) with five types of carotid automated image phenotypes (three types of carotid intima-media thickness (IMT), wall variability, and total plaque area).

METHODOLOGY

Two-step process was adapted: First, five baseline carotid image-based phenotypes were automatically measured using AtheroEdge^™ (AtheroPoint^™ , CA, USA) system by two operators (novice and experienced) and an expert. Second, based on the annual progression rates of cIMT due to nine traditional cardiovascular risk factors, a novel nonlinear model was adapted for 10-year predictions of carotid phenotypes.

RESULTS

Institute review board (IRB) approved 204 Japanese patients' left/right common carotid artery (407 ultrasound scans) was collected with a mean age of 69 ± 11 years. Age and hemoglobin were reported to have a high influence on the 10-year carotid phenotypes. Mean correlation coefficient (CC) between 10-year carotid image-based phenotype and age was improved by 39.35% in males and 25.38% in females. The area under the curves for the 10-year measurements of five phenotypes IMT_ave10yr , IMT_max10yr , IMT_min10yr , IMTV_10yr , and TPA_10yr were 0.96, 0.94, 0.90, 1.0, and 1.0. Inter-operator variability between two operators showed significant CC (P < 0.0001).

CONCLUSIONS

A nonlinear model was developed and validated by fusing nine conventional CV risk factors with current carotid image-based phenotypes for predicting the 10-year carotid ultrasound image-based phenotypes which may be used risk assessment.

Morphologic TPA (mTPA) and composite risk score for moderate carotid atherosclerotic plaque is strongly associated with HbA1c in diabetes cohort

BACKGROUND

This study examines the association between six types of carotid artery disease image-based phenotypes and HbA1c in diabetes patients. Six phenotypes (intima-media thickness measurements (cIMT (ave.), cIMT (max.), cIMT (min.)), bidirectional wall variability (cIMTV), morphology-based total plaque area (mTPA), and composite risk score (CRS)) were measured in an automated setting using AtheroEdge™ (AtheroPoint, CA, USA).

METHOD

Consecutive 199 patients (157 M, age: 68.96 ± 10.98 years), L/R common carotid artery (CCA; 398 US scans) who underwent a carotid ultrasound (L/R) were retrospectively analyzed using AtheroEdge™ system. Two operators (novice and experienced) manually calibrated all the US scans using AtheroEdge™. Logistic regression (LR) and Odds ratio (OR) was computed and phenotypes were ranked.

RESULTS

The baseline results showed 150 low-risk patients (HbA1c < 6.50 mg/dl) and 49 high-risk patients (HbA1c ≥ 6.50 mg/dl). The fasting blood sugar (FBS) was highly associated with HbA1c (P < 0.001). Except for cIMTV, all phenotypes showed an OR > 1.0 (P < 0.001) for left common carotid artery (LCCA), right carotid artery (RCCA), and mean of left and right common carotid artery (MCCA). After adjusting the FBS, the OR for mTPA showed a higher risk for LCCA, RCCA, and MCCA. The coefficient of correlation (CC) between phenotypes and HbA1c were strong and inter-CC between cIMT and mTPA/CRS was above 0.9 (P < 0.001). The statistical tests showed that phenotypes were significantly associated with diabetes (P-value<0.0001).

CONCLUSIONS

All phenotypes using AtheroEdge™, except cIMTV, showed a strong association with HbA1c. mTPA and CRS were equally strong phenotypes as cIMT. The CRS phenotype showed the strongest relationship to HbA1c.

Intima-media thickness and ankle-brachial index are correlated with the extent of coronary artery disease measured by the SYNTAX score

Introduction

The extent of peripheral artery disease (PAD) measured by the ankle-brachial index (ABI) and intima-media thickness (IMT) is correlated with the complexity of coronary artery disease (CAD) in stable angina patients. However, data regarding patients with acute coronary syndromes are still lacking.

Aim

To compare coronary complexity measured by the SYNTAX score in patients with and without PAD presenting with myocardial infarction (MI).

Material and methods

Both ABI and IMT were measured in 101 consecutive patients who underwent primary diagnostic due to MI. Patients were divided into three tertile groups depending on the SYNTAX score (0-4; 5-11; 12 and more points).

Results

Mean ABI in the general population was 0.9 ±0.26, mean IMT was 0.8 ±0.3 mm and mean SYNTAX score was 7.8 ±5.4 points. We found significant correlations between ABI and SYNTAX score (p = 0.01), IMT and SYNTAX score (p < 0.001), and IMT and ABI (p < 0.001). The highest mean values of IMT (p < 0.001) and lowest mean values of ABI (p = 0.015) were found in patients in the highest SYNTAX score group. When analyzing receiver operating characteristics (ROC) curves, IMT had greater specificity and sensitivity than ABI.

Conclusions

Both IMT and ABI are correlated with SYNTAX score (positively for IMT and negatively for ABI values). In our study, IMT was a better predictor of SYNTAX score than ABI. Our study suggests that the higher rate of cardiovascular events in patients with PAD presenting with MI may be partially explained by greater coronary lesion complexity.

Wall-based measurement features provides an improved IVUS coronary artery risk assessment when fused with plaque texture-based features during machine learning paradigm

BACKGROUND

Planning of percutaneous interventional procedures involves a pre-screening and risk stratification of the coronary artery disease. Current screening tools use stand-alone plaque texture-based features and therefore lack the ability to stratify the risk.

METHOD

This IRB approved study presents a novel strategy for coronary artery disease risk stratification using an amalgamation of IVUS plaque texture-based and wall-based measurement features. Due to common genetic plaque makeup, carotid plaque burden was chosen as a gold standard for risk labels during training-phase of machine learning (ML) paradigm. Cross-validation protocol was adopted to compute the accuracy of the ML framework. A set of 59 plaque texture-based features was padded with six wall-based measurement features to show the improvement in stratification accuracy. The ML system was executed using principle component analysis-based framework for dimensionality reduction and uses support vector machine classifier for training and testing-phases.

RESULTS

The ML system produced a stratification accuracy of 91.28%, demonstrating an improvement of 5.69% when wall-based measurement features were combined with plaque texture-based features. The fused system showed an improvement in mean sensitivity, specificity, positive predictive value, and area under the curve by: 6.39%, 4.59%, 3.31% and 5.48%, respectively when compared to the stand-alone system. While meeting the stability criteria of 5%, the ML system also showed a high average feature retaining power and mean reliability of 89.32% and 98.24%, respectively.

CONCLUSIONS

The ML system showed an improvement in risk stratification accuracy when the wall-based measurement features were fused with the plaque texture-based features.

Validation of the Carotid Intima-Media Thickness Variability: Can Manual Segmentations Be Trusted as Ground Truth?

The common carotid artery intima-media thickness (IMT) is widely accepted and used as an indicator of atherosclerosis. Recent studies, however, have found that the irregularity of the IMT along the carotid artery wall has a stronger correlation with atherosclerosis than the IMT itself. We set out to validate IMT variability (IMTV), a parameter defined to assess IMT irregularities along the wall. In particular, we analyzed whether or not manual segmentations of the lumen-intima and media-adventitia can be considered reliable in calculation of the IMTV parameter. To do this, we used a total of 60 simulated ultrasound images with a priori IMT and IMTV values. The images, simulated using the Fast And Mechanistic Ultrasound Simulation software, presented five different morphologies, four nominal IMT values and three different levels of variability along the carotid artery wall (no variability, small variability and large variability). Three experts traced the lumen-intima (LI) and media-adventitia (MA) profiles, and two automated algorithms were employed to obtain the LI and MA profiles. One expert also re-traced the LI and MA profiles to test intra-reader variability. The average IMTV measurements of the profiles used to simulate the longitudinal B-mode images were 0.002 ± 0.002, 0.149 ± 0.035 and 0.286 ± 0.068 mm for the cases of no variability, small variability and large variability, respectively. The IMTV measurements of one of the automated algorithms were statistically similar (p > 0.05, Wilcoxon signed rank) when considering small and large variability, but non-significant when considering no variability (p < 0.05, Wilcoxon signed rank). The second automated algorithm resulted in statistically similar values in the small variability case. Two readers' manual tracings, however, produced IMTV measurements with a statistically significant difference considering all three variability levels, whereas the third reader found a statistically significant difference in both the no variability and large variability cases. Moreover, the error range between the reader and automatic IMTV values was approximately 0.15 mm, which is on the same order of small IMTV values, indicating that manual and automatic IMTV readings should be not used interchangeably in clinical practice. On the basis of our findings, we conclude that expert manual tracings should not be considered reliable in IMTV measurement and, therefore, should not be trusted as ground truth. On the other hand, our automated algorithm was found to be more reliable, indicating how automated techniques could therefore foster analysis of the carotid artery intima-media thickness irregularity.

Accurate cloud-based smart IMT measurement, its validation and stroke risk stratification in carotid ultrasound: A web-based point-of-care tool for multicenter clinical trial

This study presents AtheroCloud™ - a novel cloud-based smart carotid intima-media thickness (cIMT) measurement tool using B-mode ultrasound for stroke/cardiovascular risk assessment and its stratification. This is an anytime-anywhere clinical tool for routine screening and multi-center clinical trials. In this pilot study, the physician can upload ultrasound scans in one of the following formats (DICOM, JPEG, BMP, PNG, GIF or TIFF) directly into the proprietary cloud of AtheroPoint from the local server of the physician's office. They can then run the intelligent and automated AtheroCloud™ cIMT measurements in point-of-care settings in less than five seconds per image, while saving the vascular reports in the cloud. We statistically benchmark AtheroCloud™ cIMT readings against sonographer (a registered vascular technologist) readings and manual measurements derived from the tracings of the radiologist. One hundred patients (75 M/25 F, mean age: 68±11 years), IRB approved, Toho University, Japan, consisted of Left/Right common carotid artery (CCA) artery (200 ultrasound scans), (Toshiba, Tokyo, Japan) were collected using a 7.5MHz transducer. The measured cIMTs for L/R carotid were as follows (in mm): (i) AtheroCloud™ (0.87±0.20, 0.77±0.20); (ii) sonographer (0.97±0.26, 0.89±0.29) and (iii) manual (0.90±0.20, 0.79±0.20), respectively. The coefficient of correlation (CC) between sonographer and manual for L/R cIMT was 0.74 (P<0.0001) and 0.65 (P<0.0001), while, between AtheroCloud™ and manual was 0.96 (P<0.0001) and 0.97 (P<0.0001), respectively. We observed that 91.15% of the population in AtheroCloud™ had a mean cIMT error less than 0.11mm compared to sonographer's 68.31%. The area under curve for receiving operating characteristics was 0.99 for AtheroCloud™ against 0.81 for sonographer. Our Framingham Risk Score stratified the population into three bins as follows: 39% in low-risk, 70.66% in medium-risk and 10.66% in high-risk bins. Statistical tests were performed to demonstrate consistency, reliability and accuracy of the results. The proposed AtheroCloud™ system is completely reliable, automated, fast (3-5 seconds depending upon the image size having an internet speed of 180Mbps), accurate, and an intelligent, web-based clinical tool for multi-center clinical trials and routine telemedicine clinical care.

A new method for IVUS-based coronary artery disease risk stratification: A link between coronary & carotid ultrasound plaque burdens

Interventional cardiologists have a deep interest in risk stratification prior to stenting and percutaneous coronary intervention (PCI) procedures. Intravascular ultrasound (IVUS) is most commonly adapted for screening, but current tools lack the ability for risk stratification based on grayscale plaque morphology. Our hypothesis is based on the genetic makeup of the atherosclerosis disease, that there is evidence of a link between coronary atherosclerosis disease and carotid plaque built up. This novel idea is explored in this study for coronary risk assessment and its classification of patients between high risk and low risk. This paper presents a strategy for coronary risk assessment by combining the IVUS grayscale plaque morphology and carotid B-mode ultrasound carotid intima-media thickness (cIMT) - a marker of subclinical atherosclerosis. Support vector machine (SVM) learning paradigm is adapted for risk stratification, where both the learning and testing phases use tissue characteristics derived from six feature combinational spaces, which are then used by the SVM classifier with five different kernels sets. These six feature combinational spaces are designed using 56 novel feature sets. K-fold cross validation protocol with 10 trials per fold is used for optimization of best SVM-kernel and best feature combination set. IRB approved coronary IVUS and carotid B-mode ultrasound were jointly collected on 15 patients (2 days apart) via: (a) 40MHz catheter utilizing iMap (Boston Scientific, Marlborough, MA, USA) with 2865 frames per patient (42,975 frames) and (b) linear probe B-mode carotid ultrasound (Toshiba scanner, Japan). Using the above protocol, the system shows the classification accuracy of 94.95% and AUC of 0.95 using optimized feature combination. This is the first system of its kind for risk stratification as a screening tool to prevent excessive cost burden and better patients' cardiovascular disease management, while validating our two hypotheses.

ULTRASOUND B-MODE DESCRIPTORS AND THEIR ASSOCIATION TO AGE AND AUTOMATED IMT AND IMT VARIABILITY

The aim of this paper is to evaluate the association between four simple B-mode image descriptors and age, to further assess the association between the descriptors and automated intima-media thickness (IMT) and intima-media thickness variability (IMTV) measurements, and finally analyze the predictive value of the B-mode image descriptors. A database of 1774 images of the carotid artery is used to manually calculate the contrast and the signal-to-noise ratio (SNR) between the (i) intima-media complex and lumen, and (ii) adventitial wall layer and intima-media complex. A subset of 200 images is then used to automatically measure the IMT and IMTV parameters with a previously developed algorithm. Correlation studies and logistic regression analysis are then performed. The contrast and SNR between the intima-media complex and lumen (contrastIM and SNRIM) are 112.691[Formula: see text][Formula: see text][Formula: see text]247.427 and 19.542[Formula: see text][Formula: see text][Formula: see text]6.236, respectively; whereas between the adventitial wall layer and intima-media complex the parameters (contrastADV and SNRADV) are found to be 1.684[Formula: see text][Formula: see text][Formula: see text]1.182 and 32.859[Formula: see text][Formula: see text][Formula: see text]10.766, respectively. Pearson’s rho is significantly different from zero considering the contrastIM and the SNRADV descriptors when tested for the association with age. The automated IMT and IMTV measurements are 0.796[Formula: see text][Formula: see text][Formula: see text]0.152[Formula: see text]mm and 0.096[Formula: see text][Formula: see text][Formula: see text]0.044[Formula: see text]mm, respectively. Testing the association with the IMT and IMTV measurements yielded Pearson’s rho values which are significantly different from zero except in the case of contrastIM for the IMTV measurement. The logistic regression results showed the IMTV measurement and the SNR descriptor between the intima-media complex and the lumen has a significant predictive value. Considering the association between the IMT and IMTV, the B-mode image descriptors showed a strong and statistically significant association. Moreover, the SNR between the intima-media complex and lumen is found to be a predictive variable in demonstrating its effectiveness as an image descriptor.

Shape-based approach for coronary calcium lesion volume measurement on intravascular ultrasound imaging and its association with carotid intima-media thickness

OBJECTIVES

Coronary calcification plays an important role in diagnostic classification of lesion subsets. According to histopathologic studies, vulnerable atherosclerotic plaque contains calcified deposits, and there can be considerable variation in the extent and degree of calcification. Intravascular ultrasound (IVUS) has demonstrated its role in imaging coronary arteries, thereby displaying calcium lesions. The aim of this work was to develop a fully automated system for detection, area and volume measurement, and characterization of the largest calcium deposits in coronary arteries. Furthermore, we demonstrate the correlation between the coronary calcium IVUS volume and the neurologic risk biomarker B-mode carotid intima-media thickness (IMT).

METHODS

Our system automatically detects the frames with calcium, identifies the largest calcium region, and performs shape-based volume measurements. The carotid IMT is measured by using AtheroEdge software (AtheroPoint, LLC) on B-mode ultrasound imaging.

RESULTS

Our database consists of low-contrast IVUS videos and corresponding B-mode images from 100 patients. Our experiments showed that the correlation between calcium volumes and carotid IMT was higher for the left carotid artery compared to the right carotid artery (r = 0.066 for the left carotid artery and 0.121 for the right carotid artery). We obtained 97% accuracy for automated calcium detection compared against the scoring given by our expert radiologists. Furthermore, we benchmarked shape-based volume measurement against the conventional method, which used integration of regions and showed a correlation of 84%.

CONCLUSIONS

Since carotid IMT is an independent prognostic factor for myocardial infarction, and calcium lesions are correlated with stroke risk, we believe that this automated system for calcium volume measurement could be useful for assessing patients' cardiovascular risk.

The combination of the ankle brachial index and brachial ankle pulse wave velocity exhibits a superior association with outcomes in diabetic patients

OBJECTIVE

Patients with type 2 diabetes mellitus (T2DM) and peripheral arterial disease are classified as having very high cardiovascular risks. We therefore sought to determine whether assessments of the ankle brachial index (ABI) and brachial ankle pulse wave velocity (baPWV) together exhibited a superior association with the outcomes of T2DM.

METHODS

A retrospective analysis of patients receiving ABI and baPWV during the period 2005-2007 was performed. Patients A total of 452 subjects were enrolled and followed-up for a mean 5.8 years after being grouped according to the ABI (<0.9 vs. ≥0.9) and baPWV (<1,700 cm/s vs. ≥1,700 cm/s).

RESULTS

The outcomes were all-cause mortality and composite events (all-cause mortality, hospitalization for coronary artery disease, stroke, re-vascularization, amputation and diabetic foot). Inter-group differences in the smoking rate, duration of diabetes, systolic and pulse blood pressure, anti-platelet drugs, estimated glomerular filtration rate, and urine albumin excretion were significant. During the follow-up period, 17 (3.7%) individuals died and composite events were recorded in 64 cases (14.1%). A low ABI plus high baPWV was found be associated with poor outcomes compared with a normal ABI plus low baPWV (p<0.001). Meanwhile, a low ABI plus high baPWV was associated with an increased risk of all-cause mortality [hazard ratio (HR) 17.01, 95% confidence interval (CI) 1.57-183.73, p=0.019] and composite events (HR 8.53, 95% CI 3.31-21.99, p<0.001).

CONCLUSION

In this study, the outcomes of patients with a low ABI plus high baPWV were the worst, while the subjects with a low ABI plus low baPWV or normal ABI exhibited similar outcomes. Therefore, the ABI plus baPWV exhibits a better association with the outcomes of T2DM.