Web-based accurate measurements of carotid lumen diameter and stenosis severity: An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials

COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography

Background and novelty

When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections.

Methodology

Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots.

Results

Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p < 0.001.

Conclusion

Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.

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.

Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest X-ray Scans

Background and Motivation: COVID-19 has resulted in a massive loss of life during the last two years. The current imaging-based diagnostic methods for COVID-19 detection in multiclass pneumonia-type chest X-rays are not so successful in clinical practice due to high error rates. Our hypothesis states that if we can have a segmentation-based classification error rate <5%, typically adopted for 510 (K) regulatory purposes, the diagnostic system can be adapted in clinical settings. Method: This study proposes 16 types of segmentation-based classification deep learning-based systems for automatic, rapid, and precise detection of COVID-19. The two deep learning-based segmentation networks, namely UNet and UNet+, along with eight classification models, namely VGG16, VGG19, Xception, InceptionV3, Densenet201, NASNetMobile, Resnet50, and MobileNet, were applied to select the best-suited combination of networks. Using the cross-entropy loss function, the system performance was evaluated by Dice, Jaccard, area-under-the-curve (AUC), and receiver operating characteristics (ROC) and validated using Grad-CAM in explainable AI framework. Results: The best performing segmentation model was UNet, which exhibited the accuracy, loss, Dice, Jaccard, and AUC of 96.35%, 0.15%, 94.88%, 90.38%, and 0.99 (p-value <0.0001), respectively. The best performing segmentation-based classification model was UNet+Xception, which exhibited the accuracy, precision, recall, F1-score, and AUC of 97.45%, 97.46%, 97.45%, 97.43%, and 0.998 (p-value <0.0001), respectively. Our system outperformed existing methods for segmentation-based classification models. The mean improvement of the UNet+Xception system over all the remaining studies was 8.27%. Conclusion: The segmentation-based classification is a viable option as the hypothesis (error rate <5%) holds true and is thus adaptable in clinical practice.

Brain Tumor Characterization Using Radiogenomics in Artificial Intelligence Framework

Brain tumor characterization (BTC) is the process of knowing the underlying cause of brain tumors and their characteristics through various approaches such as tumor segmentation, classification, detection, and risk analysis. The substantial brain tumor characterization includes the identification of the molecular signature of various useful genomes whose alteration causes the brain tumor. The radiomics approach uses the radiological image for disease characterization by extracting quantitative radiomics features in the artificial intelligence (AI) environment. However, when considering a higher level of disease characteristics such as genetic information and mutation status, the combined study of "radiomics and genomics" has been considered under the umbrella of "radiogenomics". Furthermore, AI in a radiogenomics' environment offers benefits/advantages such as the finalized outcome of personalized treatment and individualized medicine. The proposed study summarizes the brain tumor's characterization in the prospect of an emerging field of research, i.e., radiomics and radiogenomics in an AI environment, with the help of statistical observation and risk-of-bias (RoB) analysis. The PRISMA search approach was used to find 121 relevant studies for the proposed review using IEEE, Google Scholar, PubMed, MDPI, and Scopus. Our findings indicate that both radiomics and radiogenomics have been successfully applied aggressively to several oncology applications with numerous advantages. Furthermore, under the AI paradigm, both the conventional and deep radiomics features have made an impact on the favorable outcomes of the radiogenomics approach of BTC. Furthermore, risk-of-bias (RoB) analysis offers a better understanding of the architectures with stronger benefits of AI by providing the bias involved in them.

Automated Deep Learning-based Single-Step Diameter Estimation of Carotid Arteries in B-mode Ultrasound

Accurate measurement of blood vessel diameter on ultrasonic images is important in many vascular exams. In one of them, volumetric blood flow measurements, the volume flow rate is calculated by multiplying the time-averaged velocity with the cross-sectional area of the vessel (using diameter measured from B-mode images). Computation of lumen diameter is also vital for planning surgical procedures like carotid artery stenting and endarterectomy. More recently, several automated vessel diameter estimation methods employing deep learning have been proposed. In this paper, we propose a novel single-step automated deep learning-based vessel diameter estimation technique developed on B-mode images. Longitudinal images of the human common carotid artery were acquired by trained vascular sonographers in human subjects using a linear array probe. Ground truth measurements were obtained by a human expert to validate the proposed technique. 504 images (with augmentation) were divided into training, validation, and test sets. Three pre-trained deep learning networks were used for training, and the lumen diameter was predicted in a hold-out test set. The Mean Absolute Deviation (MAD) and Root Mean Square Error (RMSE) ranged from 0.22-0.65 mm and 0.32-0.82 mm, respectively, for the three networks. Furthermore, 5-fold cross-validation resulted in MAD and RMSE of 0.36±0.1 mm and 0.513±0.15 mm, respectively. Clinical Relevance- The results demonstrate that the technology can potentially be embedded in commercial scanners to make the workflow in vascular ultrasound more efficient.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0

BACKGROUND

COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.

METHOD

ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.

RESULTS

Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.

CONCLUSIONS

Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

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.

COVLIAS 1.0: Lung Segmentation in COVID-19 Computed Tomography Scans Using Hybrid Deep Learning Artificial Intelligence Models

BACKGROUND

COVID-19 lung segmentation using Computed Tomography (CT) scans is important for the diagnosis of lung severity. The process of automated lung segmentation is challenging due to (a) CT radiation dosage and (b) ground-glass opacities caused by COVID-19. The lung segmentation methodologies proposed in 2020 were semi- or automated but not reliable, accurate, and user-friendly. The proposed study presents a COVID Lung Image Analysis System (COVLIAS 1.0, AtheroPoint™, Roseville, CA, USA) consisting of hybrid deep learning (HDL) models for lung segmentation.

METHODOLOGY

The COVLIAS 1.0 consists of three methods based on solo deep learning (SDL) or hybrid deep learning (HDL). SegNet is proposed in the SDL category while VGG-SegNet and ResNet-SegNet are designed under the HDL paradigm. The three proposed AI approaches were benchmarked against the National Institute of Health (NIH)-based conventional segmentation model using fuzzy-connectedness. A cross-validation protocol with a 40:60 ratio between training and testing was designed, with 10% validation data. The ground truth (GT) was manually traced by a radiologist trained personnel. For performance evaluation, nine different criteria were selected to perform the evaluation of SDL or HDL lung segmentation regions and lungs long axis against GT.

RESULTS

Using the database of 5000 chest CT images (from 72 patients), COVLIAS 1.0 yielded AUC of ~0.96, ~0.97, ~0.98, and ~0.96 (p-value < 0.001), respectively within 5% range of GT area, for SegNet, VGG-SegNet, ResNet-SegNet, and NIH. The mean Figure of Merit using four models (left and right lung) was above 94%. On benchmarking against the National Institute of Health (NIH) segmentation method, the proposed model demonstrated a 58% and 44% improvement in ResNet-SegNet, 52% and 36% improvement in VGG-SegNet for lung area, and lung long axis, respectively. The PE statistics performance was in the following order: ResNet-SegNet > VGG-SegNet > NIH > SegNet. The HDL runs in <1 s on test data per image.

CONCLUSIONS

The COVLIAS 1.0 system can be applied in real-time for radiology-based clinical settings.

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.

Ultrasound-based stroke/cardiovascular risk stratification using Framingham Risk Score and ASCVD Risk Score based on "Integrated Vascular Age" instead of "Chronological Age": a multi-ethnic study of Asian Indian, Caucasian, and Japanese cohorts

Background

Vascular age (VA) has recently emerged for CVD risk assessment and can either be computed using conventional risk factors (CRF) or by using carotid intima-media thickness (cIMT) derived from carotid ultrasound (CUS). This study investigates a novel method of integrating both CRF and cIMT for estimating VA [so-called integrated VA (IVA)]. Further, the study analyzes and compares CVD/stroke risk using the Framingham Risk Score (FRS)-based risk calculator when adapting IVA against VA.

Methods

The system follows a four-step process: (I) VA using cIMT based using linear-regression (LR) model and its coefficients; (II) VA prediction using ten CRF using a multivariate linear regression (MLR)-based model with gender adjustment; (III) coefficients from the LR-based model and MLR-based model are combined using a linear model to predict the final IVA; (IV) the final step consists of FRS-based risk stratification with IVA as inputs and benchmarked against FRS using conventional method of CA. Area-under-the-curve (AUC) is computed using IVA and benchmarked against CA while taking the response variable as a standardized combination of cIMT and glycated hemoglobin.

Results

The study recruited 648 patients, 202 were Japanese, 314 were Asian Indian, and 132 were Caucasians. Both left and right common carotid arteries (CCA) of all the population were scanned, thus a total of 1,287 ultrasound scans. The 10-year FRS using IVA reported higher AUC (AUC =0.78) compared with 10-year FRS using CA (AUC =0.66) by ~18%.

Conclusions

IVA is an efficient biomarker for risk stratifications for patients in routine practice.

Does the Carotid Bulb Offer a Better 10-Year CVD/Stroke Risk Assessment Compared to the Common Carotid Artery? A 1516 Ultrasound Scan Study

The objectives of this study are to (1) examine the "10-year cardiovascular risk" in the common carotid artery (CCA) versus carotid bulb using an integrated calculator called "AtheroEdge Composite Risk Score 2.0" (AECRS2.0) and (2) evaluate the performance of AECRS2.0 against "conventional cardiovascular risk calculators." These objectives are met by measuring (1) image-based phenotypes and AECRS2.0 score computation and (2) performance evaluation of AECRS2.0 against 12 conventional cardiovascular risk calculators. The Asian-Indian cohort (n = 379) with type 2 diabetes mellitus (T2DM), chronic kidney disease (CKD), or hypertension were retrospectively analyzed by acquiring the 1516 carotid ultrasound scans (mean age: 55 ± 10.1 years, 67% males, ∼92% with T2DM, ∼83% with CKD [stage 1-5], and 87.5% with hypertension [stage 1-2]). The carotid bulb showed a higher 10-year cardiovascular risk compared to the CCA by 18% (P < .0001). Patients with T2DM and/or CKD also followed a similar trend. The carotid bulb demonstrated a superior risk assessment compared to CCA in patients with T2DM and/or CKD by showing: (1) ∼13% better than CCA (0.93 vs 0.82, P = .0001) and (2) ∼29% better compared with 12 types of risk conventional calculators (0.93 vs 0.72, P = .06).

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.

Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease

We evaluated the association between automatically measured carotid total plaque area (TPA) and the estimated glomerular filtration rate (eGFR), a biomarker of chronic kidney disease (CKD). Automated average carotid intima-media thickness (cIMTave) and TPA measurements in carotid ultrasound (CUS) were performed using AtheroEdge (AtheroPoint). Pearson correlation coefficient (CC) was then computed between the TPA and eGFR for (1) males versus females, (2) diabetic versus nondiabetic patients, and (3) between the left and right carotid artery. Overall, 339 South Asian Indian patients with either type 2 diabetes mellitus (T2DM) or CKD, or hypertension (stage 1 or stage 2) were retrospectively analyzed by acquiring cIMTave and TPA measurements of their left and right common carotid arteries (CCA; total CUS: 678, mean age: 54.2 ± 9.8 years; 75.2% males; 93.5% with T2DM). The CC between TPA and eGFR for different scenarios were (1) for males and females -0.25 (P < .001) and -0.35 (P < .001), respectively; (2) for T2DM and non-T2DM -0.26 (P < .001) and -0.49 (P = .02), respectively, and (3) for left and right CCA -0.25 (P < .001) and -0.23 (P < .001), respectively. Automated TPA is an equally reliable biomarker compared with cIMTave for patients with CKD (with or without T2DM) with subclinical atherosclerosis.

The role of carotid stenosis ultrasound scale in the prediction of ischemic stroke

INTRODUCTION

To improve the accuracy of ultrasound techniques for the assessment of carotid stenosis, we designed a novel carotid artery stenosis ultrasound scale (CASUS), and evaluated its accuracy, reliability, and its value in predicting the occurrence of cardiovascular and cerebrovascular diseases in a prospective study.

METHODS

A total of 750 patients with first-time ischemic stroke and hospitalized within 24 h were enrolled in the study. Using color Doppler ultrasound (CDUS), the degree of stenosis and blood flow (BF) in bilateral internal carotid arteries (ICA) and the V1-V3 segment of vertebral arteries (VA) was assessed. Cubic simulation curves for BF and global blood flow (GBF) over the stenosis score (SS), total stenosis score (TSS), and radiological imaging- total stenosis score (RI-TSS) were fitted and compared. The receiver operating characteristic (ROC) curves using TSS, RI-TSS, or GBF to predict various ischemic stroke endpoints were also analyzed and compared.

RESULTS

There was a linear relationship between SS and BF both ICA and VA (R2 were 0.734 and 0.783, respectively, both P < 0.05). Both TSS and RI-TSS with GBF showed an inverse "S" curve relationship (R2 was 0.839 and 0.843, all P < 0.05). The AUC values of TSS-based and RI-TSS-based predictions of each endpoint were all greater than 0.7 (all P < 0.05), but the differences of the AUC values between TSS, RI-TSS, and GBF were not statistically significant (all P > 0.05).

CONCLUSIONS

The novel CASUS can better reflect the level of cerebral reperfusion in patients with ischemic stroke and can better predict the occurrence of cardiovascular and cerebrovascular diseases.

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.

A Special Report on Changing Trends in Preventive Stroke/Cardiovascular Risk Assessment Via B-Mode Ultrasonography

PURPOSE OF REVIEW

Cardiovascular disease (CVD) and stroke risk assessment have been largely based on the success of traditional statistically derived risk calculators such as Pooled Cohort Risk Score or Framingham Risk Score. However, over the last decade, automated computational paradigms such as machine learning (ML) and deep learning (DL) techniques have penetrated into a variety of medical domains including CVD/stroke risk assessment. This review is mainly focused on the changing trends in CVD/stroke risk assessment and its stratification from statistical-based models to ML-based paradigms using non-invasive carotid ultrasonography.

RECENT FINDINGS

In this review, ML-based strategies are categorized into two types: non-image (or conventional ML-based) and image-based (or integrated ML-based). The success of conventional (non-image-based) ML-based algorithms lies in the different data-driven patterns or features which are used to train the ML systems. Typically these features are the patients' demographics, serum biomarkers, and multiple clinical parameters. The integrated (image-based) ML-based algorithms integrate the features derived from the ultrasound scans of the arterial walls (such as morphological measurements) with conventional risk factors in ML frameworks. Even though the review covers ML-based system designs for carotid and coronary ultrasonography, the main focus of the review is on CVD/stroke risk scores based on carotid ultrasound. There are two key conclusions from this review: (i) fusion of image-based features with conventional cardiovascular risk factors can lead to more accurate CVD/stroke risk stratification; (ii) the ability to handle multiple sources of information in big data framework using artificial intelligence-based paradigms (such as ML and DL) is likely to be the future in preventive CVD/stroke risk assessment.

A Stroke Risk Detection: Improving Hybrid Feature Selection Method

Background

Stroke is one of the most common diseases that cause mortality. Detecting the risk of stroke for individuals is critical yet challenging because of a large number of risk factors for stroke.

Objective

This study aimed to address the limitation of ineffective feature selection in existing research on stroke risk detection. We have proposed a new feature selection method called weighting- and ranking-based hybrid feature selection (WRHFS) to select important risk factors for detecting ischemic stroke.

Methods

WRHFS integrates the strengths of various filter algorithms by following the principle of a wrapper approach. We employed a variety of filter-based feature selection models as the candidate set, including standard deviation, Pearson correlation coefficient, Fisher score, information gain, Relief algorithm, and chi-square test and used sensitivity, specificity, accuracy, and Youden index as performance metrics to evaluate the proposed method.

Results

This study chose 792 samples from the electronic records of 13,421 patients in a community hospital. Each sample included 28 features (24 blood test features and 4 demographic features). The results of evaluation showed that the proposed method selected 9 important features out of the original 28 features and significantly outperformed baseline methods. Their cumulative contribution was 0.51. The WRHFS method achieved a sensitivity of 82.7% (329/398), specificity of 80.4% (317/394), classification accuracy of 81.5% (645/792), and Youden index of 0.63 using only the top 9 features. We have also presented a chart for visualizing the risk of having ischemic strokes.

Conclusions

This study has proposed, developed, and evaluated a new feature selection method for identifying the most important features for building effective and parsimonious models for stroke risk detection. The findings of this research provide several novel research contributions and practical implications.

Ranking of stroke and cardiovascular risk factors for an optimal risk calculator design: Logistic regression approach

PURPOSE

Conventional cardiovascular risk factors (CCVRFs) and carotid ultrasound image-based phenotypes (CUSIP) are independently associated with long-term risk of cardiovascular (CV) disease. In this study, 26 cardiovascular risk (CVR) factors which consisted of a combination of CCVRFs and CUSIP together were ranked. Further, an optimal risk calculator using AtheroEdge composite risk score (AECRS1.0) was designed and benchmarked against seven conventional CV risk (CVR) calculators.

METHODS

Two types of ranking were performed: (i) ranking of 26 CVR factors and (ii) ranking of eight types of 10-year risk calculators. In the first case, multivariate logistic regression was used to compute the odds ratio (OR) and in the second, receiver operating characteristic curves were used to evaluate the performance of eight types of CVR calculators using SPSS23.0 and MEDCALC12.0 with validation against STATA15.0.

RESULTS

The left and right common carotid arteries (CCA) of 202 Japanese patients were examined to obtain 404 ultrasound scans. CUSIP ranked in the top 50% of the 26 covariates. Intima-media thickness variability (IMTV) and IMTV_10yr were the most influential carotid phenotypes for left CCA (OR = 250, P < 0.0001 and OR = 207, P < 0.0001 respectively) and right CCA (OR = 1614, P < 0.0001 and OR = 626, P < 0.0001 respectively). However, for the mean CCA, AECRS1.0 and AECRS1.0_10yr reported the most highly significant OR among all the CVR factors (OR = 1.073, P < 0.0001 and OR = 1.104, P < 0.0001). AECRS1.0_10yr also reported highest area-under-the-curve (AUC = 0.904, P < 0.0001) compared to seven types of conventional calculators. Age and glycated haemoglobin reported highest OR (1.96, P < 0.0001 and 1.05, P = 0.012) among all other CCVRFs.

CONCLUSION

AECRS1.0_10yr demonstrated the best performance due to presence of CUSIP and ranked at the first place with highest AUC.

Performance evaluation of 10-year ultrasound image-based stroke/cardiovascular (CV) risk calculator by comparing against ten conventional CV risk calculators: A diabetic study

MOTIVATION

AtheroEdge Composite Risk Score (AECRS1.0_10yr) is an integrated stroke/cardiovascular risk calculator that was recently developed and computes the 10-year risk of carotid image phenotypes by integrating conventional cardiovascular risk factors (CCVRFs). It is therefore important to understand how closely AECRS1.0_10yr is associated with the ten other currently available conventional cardiovascular risk calculators (CCVRCs).

METHODS

The Institutional Review Board of Toho University approved the examination of the left/right common carotid arteries of 202 Japanese patients. Step 1 consists of measurement of AECRS1.0_10yr, given current image phenotypes and CCVRFs. Step 2 consists of computing the risk score using ten different CCVRCs given CCVR factors: QRISK3, Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study (UKPDS) 56, UKPDS60, Reynolds Risk Score (RRS), Pooled cohort Risk Score (PCRS or ASCVD), Systematic Coronary Risk Evaluation (SCORE), Prospective Cardiovascular Munster Study (PROCAM) calculator, NIPPON, and World Health Organization (WHO) risk. Step 3 consists of computing the closeness factor between AECRS1.0_10yr and ten CCVRCs using cumulative ranking index derived using eight different statistically derived metrics.

RESULTS

AECRS1.0_10yr reported the highest area-under-the-curve (0.927;P < 0.001) among all the risk calculators. The top three CCVRCs closest to AECRS1.0_10yr were QRISK3, FRS, and UKPDS60 with cumulative ranking scores of 2.1, 3.0, and 3.8, respectively.

CONCLUSION

AECRS1.0_10yr produced the largest AUC due to the integration of image-based phenotypes with CCVR factors, and ranked at first place with the highest AUC. Cumulative ranking of ten CCVRCs demonstrated that QRISK3 was the closest calculator to AECRS1.0_10yr, which is also consistent with the industry trend.

Geometric Total Plaque Area Is an Equally Powerful Phenotype Compared With Carotid Intima-Media Thickness for Stroke Risk Assessment: A Deep Learning Approach

Currently, carotid intima-media thickness (cIMT) and geometric total plaque area (gTPA) are computed manually and thus are tedious and prone to interobserver and intraobserver variabilities. This study presents an intelligence-based automated deep learning (DL)–based technique for carotid wall interface detection, cIMT, and lumen diameter (LD) measurements, followed by a 3D cylindrical approach for TPA measurement. The observers were used for manual tracings of which were then used for the design of two DL-based systems. The DL boundaries for inner lumen wall and outer interadventitial borders were used for computing the cIMT and LD. Using cylindrical approach, we computed the gTPA. Furthermore, we compute the 10-year image-based cIMT and gTPA, using the progression rates. A total of 396 B-mode ultrasound right and left common carotid artery images were taken from 203 patients. The mean cIMT and gTPA using DL1 and DL2 is 0.91 mm, 20.52 mm2 and 0.88 mm, 19.44 mm2, respectively. The coefficient of correlation between gTPA and cIMT using DL1 and DL2 is 0.92 ( P < .001) and 0.94 ( P < .001), respectively. The area under the curve (AUC) for gTPA showed an improvement over cIMT by 14.36% and 12.57% for DL1 and DL2, respectively. The corresponding 10-year risk improvements were 9.09% and 6.26%. Our statistical significance tests successfully passed t test, Mann-Whitney, Wilcoxon, Kolmogorov-Smirnov, and Friedman. The study shows gTPA as an equally powerful carotid risk biomarker like cIMT. Given the cIMT and LD, cylindrical fitting is a fast method for gTPA measurements.

Intra- and inter-operator reproducibility of automated cloud-based carotid lumen diameter ultrasound measurement

BACKGROUND

Common carotid artery lumen diameter (LD) ultrasound measurement systems are either manual or semi-automated and lack reproducibility and variability studies. This pilot study presents an automated and cloud-based LD measurements software system (AtheroCloud) and evaluates its: (i) intra/inter-operator reproducibility and (ii) intra/inter-observer variability.

METHODS

100 patients (83M, mean age: 68±11years), IRB approved, consisted of L/R CCA artery (200 ultrasound images), acquired using a 7.5-MHz linear transducer. The intra/inter-operator reproducibility was verified using three operator's readings. Near-wall and far carotid wall borders were manually traced by two observers for intra/inter-observer variability analysis.

RESULTS

The mean coefficient of correlation (CC) for intra- and inter-operator reproducibility between all the three automated reading pairs were: 0.99 (P<0.0001) and 0.97 (P<0.0001), respectively. The mean CC for intra- and inter-observer variability between both the manual reading pairs were 0.98 (P<0.0001) and 0.98 (P<0.0001), respectively. The Figure-of-Merit between the mean of the three automated readings against the four manuals were 98.32%, 99.50%, 98.94% and 98.49%, respectively.

CONCLUSIONS

The AtheroCloud LD measurement system showed high intra/inter-operator reproducibility hence can be adapted for vascular screening mode or pharmaceutical clinical trial mode.