Maximum plaque height in carotid ultrasound predicts cardiovascular disease outcomes: a population-based validation study of the American society of echocardiography’s grade II–III plaque characterization and protocol

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

BACKGROUND

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

METHODOLOGY

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

RESULTS

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

CONCLUSIONS

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

Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort

The quantification of carotid plaque has been routinely used to predict cardiovascular risk in cardiovascular disease (CVD) and coronary artery disease (CAD). To determine how well carotid plaque features predict the likelihood of CAD and cardiovascular (CV) events using deep learning (DL) and compare against the machine learning (ML) paradigm. The participants in this study consisted of 459 individuals who had undergone coronary angiography, contrast-enhanced ultrasonography, and focused carotid B-mode ultrasound. Each patient was tracked for thirty days. The measurements on these patients consisted of maximum plaque height (MPH), total plaque area (TPA), carotid intima-media thickness (cIMT), and intraplaque neovascularization (IPN). CAD risk and CV event stratification were performed by applying eight types of DL-based models. Univariate and multivariate analysis was also conducted to predict the most significant risk predictors. The DL's model effectiveness was evaluated by the area-under-the-curve measurement while the CV event prediction was evaluated using the Cox proportional hazard model (CPHM) and compared against the DL-based concordance index (c-index). IPN showed a substantial ability to predict CV events (p < 0.0001). The best DL system improved by 21% (0.929 vs. 0.762) over the best ML system. DL-based CV event prediction showed a ~ 17% increase in DL-based c-index compared to the CPHM (0.86 vs. 0.73). CAD and CV incidents were linked to IPN and carotid imaging characteristics. For survival analysis and CAD prediction, the DL-based system performs superior to ML-based models.

Detection of subclinical atherosclerosis using vascular ultrasound as a vascular risk assessment method. Simplified protocol

Cardiovascular disease secondary to atherosclerosis is the main cause of morbidity and mortality in the world. Cardiovascular risk stratification has proven to be an insufficient approach to detect those subjects who are going to suffer a cardiovascular event, which is why for years other markers have been sought to help stratify each individual with greater precision. Two-dimensional vascular ultrasound is a excellent method for vascular risk assessment.

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.

Clinical significance of atherosclerotic risk factors differs in early and advanced stages of plaque formation: A longitudinal study in the general population

BACKGROUND

Carotid plaque is a well-known prognostic factor for cardiovascular diseases. It is unclear which risk factors are associated with the transformation of carotid plaque over time. In this longitudinal study, we examined the risk factors related to carotid plaque progression.

METHODS

We enrolled 738 men without medication (mean age: 55 ± 10 years) who underwent the first and second health examinations. We measured carotid plaque thickness (PT) at three points of the right and left carotid artery. Plaque score (PS) was calculated by summing all the PTs. We divided the PS into three groups: None-group (PS <1.1), Early-group (1.1 ≤ PS <5.1), and Advanced-group (PS ≥5.1). We analyzed the relationship between PS progression and parameters such as age, body mass index, systolic blood pressure (SBP), fasting blood sugar, low-density lipoprotein cholesterol (LDL-C), and smoking and exercise habits.

RESULTS

In multivariable logistic regression analysis, age and SBP were independent factors for PS progression from none to early stages (age, OR 1.07, p = 0.002; SBP, 10 mmHg, OR 1.27, p = 0.041). Age, follow-up period and LDL-C were independently associated factors for PS progression from early to advanced stages (age, OR 1.08,p < 0.001; follow-up period OR1.19, p = 0.041; LDL-C, 10 mg/dL, OR 1.10, p = 0.049).

CONCLUSIONS

SBP was independently associated with the progress of early atherosclerosis, while LDL-C was independently associated with the progression of advanced atherosclerosis in the general population. Further studies are needed to assess whether early control of SBP and LDL-C levels can reduce the occurrence of future cardiovascular events.

Associations between Circulating VEGFR2hi-Neutrophils and Carotid Plaque Burden in Patients Aged 40-64 without Established Atherosclerotic Cardiovascular Disease

Background

Neutrophils expressing vascular endothelial growth factor receptor (VEGFR) represent a distinct subtype of neutrophils with proangiogenic properties. The purpose of this study was to identify the interrelations between circulating CD16^hiCD11b^hiCD62L^loCXCR2^hiVEGFR2^hi-neutrophils and indicators of carotid plaque burden in patients without atherosclerotic cardiovascular diseases (ASCVD).

Methods

The study included 145 patients, 51.7% men and 48.3% women, median age—49.0 years. All patients underwent carotid duplex ultrasound scanning. The maximal carotid plaque thickness was used as an indicator of carotid plaque burden. Also, carotid intima-media thickness (cIMT) and femoral IMT were measured. The phenotyping of neutrophil subpopulations was executed by the flow cytometry via the Navios 6/2. Results. The subpopulation of VEGFR2^hi-neutrophils accounted for about 5% of the total pool of circulating neutrophils. A decrease in VEGFR2^hi-neutrophils with an increase in carotid plaque burden was statistically significant (p = 0.036). A decrease in VEGFR2^hi-neutrophils < 4.52% allowed to predict the presence of plaque with a maximum height > 2.1 mm (Q4), with sensitivity of 78.9% and specificity of 61.5% (AUC 0.693; 95% CI 0.575-0.811; p = 0.007). Inverse correlations were established between the carotid and femoral IMT and the absolute and relative number of VEGFR2^hi-neutrophils (p < 0.01).

Conclusion

In patients aged 40-64 years without established ASCVD, with an increase in indicators of the carotid plaque burden, a significant decrease in the proportion of circulating VEGFR2^hi-neutrophils was noticed. A decrease in the relative number of VEGFR2^hi-neutrophils of less than 4.52% made it possible to predict the presence of extent carotid atherosclerosis with sensitivity of 78.9% and specificity of 61.5%.

Unseen Artificial Intelligence-Deep Learning Paradigm for Segmentation of Low Atherosclerotic Plaque in Carotid Ultrasound: A Multicenter Cardiovascular Study

BACKGROUND

The early detection of carotid wall plaque is recommended in the prevention of cardiovascular disease (CVD) in moderate-risk patients. Previous techniques for B-mode carotid atherosclerotic wall plaque segmentation used artificial intelligence (AI) methods on monoethnic databases, where training and testing are from the "same" ethnic group ("Seen AI"). Therefore, the versatility of the system is questionable. This is the first study of its kind that uses the "Unseen AI" paradigm where training and testing are from "different" ethnic groups. We hypothesized that deep learning (DL) models should perform in 10% proximity between "Unseen AI" and "Seen AI".

METHODOLOGY

Two cohorts from multi-ethnic groups (330 Japanese and 300 Hong Kong (HK)) were used for the validation of our hypothesis. We used a four-layered UNet architecture for the segmentation of the atherosclerotic wall with low plaque. "Unseen AI" (training: Japanese, testing: HK or vice versa) and "Seen AI" experiments (single ethnicity or mixed ethnicity) were performed. Evaluation was conducted by measuring the wall plaque area. Statistical tests were conducted for its stability and reliability.

RESULTS

When using the UNet DL architecture, the "Unseen AI" pair one (Training: 330 Japanese and Testing: 300 HK), the mean accuracy, dice-similarity, and correlation-coefficient were 98.55, 78.38, and 0.80 (p < 0.0001), respectively, while for "Unseen AI" pair two (Training: 300 HK and Testing: 330 Japanese), these were 98.67, 82.49, and 0.87 (p < 0.0001), respectively. Using "Seen AI", the same parameters were 99.01, 86.89 and 0.92 (p < 0.0001), respectively.

CONCLUSION

We demonstrated that "Unseen AI" was in close proximity (<10%) to "Seen AI", validating our DL model for low atherosclerotic wall plaque segmentation. The online system runs < 1 s.

Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound

The automated and accurate carotid plaque segmentation in B-mode ultrasound (US) is an essential part of stroke risk stratification. Previous segmented methods used AtheroEdge™ 2.0 (AtheroPoint™, Roseville, CA) for the common carotid artery (CCA). This study focuses on automated plaque segmentation in the internal carotid artery (ICA) using solo deep learning (SDL) and hybrid deep learning (HDL) models. The methodology consists of a novel design of 10 types of SDL/HDL models (AtheroEdge™ 3.0 systems (AtheroPoint™, Roseville, CA) with a depth of four layers each. Five of the models use cross-entropy (CE)-loss, and the other five models use Dice similarity coefficient (DSC)-loss functions derived from UNet, UNet+, SegNet, SegNet-UNet, and SegNet-UNet+. The K10 protocol (Train:Test:90%:10%) was applied for all 10 models for training and predicting (segmenting) the plaque region, which was then quantified to compute the plaque area in mm². Further, the data augmentation effect was analyzed. The database consisted of 970 ICA B-mode US scans taken from 99 moderate to high-risk patients. Using the difference area threshold of 10 mm² between ground truth (GT) and artificial intelligence (AI), the area under the curve (AUC) values were 0.91, 0.911, 0.908, 0.905, and 0.898, all with a p-value of <0.001 (for CE-loss models) and 0.883, 0.889, 0.905, 0.889, and 0.907, all with a p-value of <0.001 (for DSC-loss models). The correlations between the AI-based plaque area and GT plaque area were 0.98, 0.96, 0.97, 0.98, and 0.97, all with a p-value of <0.001 (for CE-loss models) and 0.98, 0.98, 0.97, 0.98, and 0.98 (for DSC-loss models). Overall, the online system performs plaque segmentation in less than 1 s. We validate our hypothesis that HDL and SDL models demonstrate comparable performance. SegNet-UNet was the best-performing hybrid architecture.