Inter- and intra-observer variability analysis of completely automated cIMT measurement software (AtheroEdge™) and its benchmarking against commercial ultrasound scanner and expert Readers

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.

Deep learning artificial intelligence framework for multiclass coronary artery disease prediction using combination of conventional risk factors, carotid ultrasound, and intraplaque neovascularization

OBJECTIVE

Cardiovascular disease (CVD) is a major healthcare challenge and therefore early risk assessment is vital. Previous assessment techniques use either "conventional CVD risk calculators (CCVRC)" or machine learning (ML) paradigms. These techniques are ad-hoc, unreliable, not fully automated, and have variabilities. We, therefore, introduce AtheroEdge-MCDLAI (AE3.0DL) windows-based platform using multiclass Deep Learning (DL) system.

METHODS

Data was collected on 500 patients having both carotid ultrasound and corresponding coronary angiography scores (CAS), measured as stenosis in coronary arteries and considered as the gold standard. A total of 39 covariates were used, clubbed into three clusters, namely (i) Office-based: age, gender, body mass index, smoker, hypertension, systolic blood pressure, and diastolic blood pressure; (ii) Laboratory-based: Hyperlipidemia, hemoglobin A1c, and estimated glomerular filtration rate; and (iii) Carotid ultrasound image phenotypes: maximum plaque height, total plaque area, and intra-plaque neovascularization. Baseline characteristics for four classes (target labels) having significant (p < 0.0001) values were calculated using Chi-square and ANOVA. For handling the cohort's imbalance in the risk classes, AE3.0DL used the synthetic minority over-sampling technique (SMOTE). AE3.0DL used Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) DL models and the performance (accuracy and area-under-the-curve) was computed using 10-fold cross-validation (90% training, 10% testing) frameworks. AE3.0DL was validated and benchmarked.

RESULTS

The AE3.0DL using RNN and LSTM showed an accuracy and AUC (p < 0.0001) pairs as (95.00% and 0.98), and (95.34% and 0.99), respectively, and showed an improvement of 32.93% and 9.94% against CCVRC and ML, respectively. AE3.0DL runs in <1 s.

CONCLUSION

DL algorithms are a powerful paradigm for coronary artery disease (CAD) risk prediction and CVD risk stratification.

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.

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.

A hybrid deep learning paradigm for carotid plaque tissue characterization and its validation in multicenter cohorts using a supercomputer framework

BACKGROUND

Early and automated detection of carotid plaques prevents strokes, which are the second leading cause of death worldwide according to the World Health Organization. Artificial intelligence (AI) offers automated solutions for plaque tissue characterization. Recently, solo deep learning (SDL) models have been used, but they do not take advantage of the tandem connectivity offered by AI's hybrid nature. Therefore, this study explores the use of hybrid deep learning (HDL) models in a multicenter framework, making this study the first of its kind.

METHODS

We hypothesize that HDL techniques perform better than SDL and transfer learning (TL) techniques. We propose two kinds of HDL frameworks: (i) the fusion of two SDLs (Inception with ResNet) or (ii) 10 other kinds of tandem models that fuse SDL with ML. The system Atheromatic™ 2.0_HDL (AtheroPoint, CA, USA) was designed on an augmentation framework and three kinds of loss functions (cross-entropy, hinge, and mean-square-error) during training to determine the best optimization paradigm. These 11 combined HDL models were then benchmarked against one SDL model and five types of TL models; thus, this study considers a total of 17 AI models.

RESULTS

Among the 17 AI models, the best performing HDL system was that comprising CNN and decision tree (DT), as its accuracy and area-under-the-curve were 99.78 ± 1.05% and 0.99 (p<0.0001), respectively. These values are 6.4% and 3.2% better than those recorded for the SDL and TL models, respectively. We validated the performance of the HDL models with diagnostics odds ratio (DOR) and Cohen and Kappa statistics; here, HDL outperformed DL and TL by 23% and 7%, respectively. The online system ran in <2 s.

CONCLUSION

HDL is a fast, reliable, and effective tool for characterizing the carotid plaque for early stroke risk stratification.

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.

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.

Global perspective on carotid intima-media thickness and plaque: should the current measurement guidelines be revisited?

Carotid intima-media thickness (cIMT) and carotid plaque (CP) currently act as risk predictors for CVD/Stroke risk assessment. Over 2000 articles have been published that cover either use cIMT/CP or alterations of cIMT/CP and additional image-based phenotypes to associate cIMT related markers with CVD/Stroke risk. These articles have shown variable results, which likely reflect a lack of standardization in the tools for measurement, risk stratification, and risk assessment. Guidelines for cIMT/CP measurement are influenced by major factors like the atherosclerosis disease itself, conventional risk factors, 10-year measurement tools, types of CVD/Stroke risk calculators, incomplete validation of measurement tools, and the fast pace of computer technology advancements. This review discusses the following major points: 1) the American Society of Echocardiography and Mannheim guidelines for cIMT/CP measurements; 2) forces that influence the guidelines; and 3) calculators for risk stratification and assessment under the influence of advanced intelligence methods. The review also presents the knowledge-based learning strategies such as machine and deep learning which may play a future role in CVD/stroke risk assessment. We conclude that both machine learning and non-machine learning strategies will flourish for current and 10-year CVD/Stroke risk prediction as long as they integrate image-based phenotypes with conventional risk factors.

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.

State-of-the-art review on automated lumen and adventitial border delineation and its measurements in carotid ultrasound

BACKGROUND AND OBJECTIVE

Accurate, reliable, efficient, and precise measurements of the lumen geometry of the common carotid artery (CCA) are important for (a) managing the progression/regression of atherosclerotic build-up and (b) the risk of stroke. The image-based degree of stenosis in the carotid artery and the plaque burden can be predicted using the automated carotid lumen diameter (LD)/inter-adventitial diameter (IAD) measurements from B-mode ultrasound images. The objective of this review is to present the state-of-the-art methods and systems for the measurement of LD/IAD in CCA based on automated or semi-automated strategies. Further, the performance of these systems is compared based on various metrics for its measurements.

METHODS

The automated algorithms proposed for the segmentation of carotid lumen are broadly classified into two different categories as: region-based and boundary-based. These techniques are discussed in detail specifying their pros and cons. Further, we discuss the challenges encountered in the segmentation process along with its quantitative assessment. Lastly, we present stenosis quantification and risk stratification strategies.

RESULTS

Even though, we have found more boundary-based approaches compared to region-based approaches in the literature, however, the region-based strategy yield more satisfactory performance. Novel risk stratification strategies are presented. On a patient database containing 203 patients, 9 patients are identified as high risk patients, whereas 27 patients are identified as medium risk patients.

CONCLUSIONS

We have presented different techniques for the lumen segmentation of the common carotid artery from B-mode ultrasound images and measurement of lumen diameter and inter-adventitial diameter. We believe that the issue regarding boundary-based techniques can be compensated by taking regional statistics embedded with boundary-based information.

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.

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.

Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings.

Automated ultrasound edge-tracking software comparable to established semi-automated reference software for carotid intima-media thickness analysis

Many commercial ultrasound systems are now including automated analysis packages for the determination of carotid intima-media thickness (cIMT); however, details regarding their algorithms and methodology are not published. Few studies have compared their accuracy and reliability with previously established automated software, and those that have were in asymptomatic adults. Therefore, this study compared cIMT measures from a fully automated ultrasound edge-tracking software (EchoPAC PC, Version 110.0.2; GE Medical Systems, Horten, Norway) to an established semi-automated reference software (Artery Measurement System (AMS) II, Version 1.141; Gothenburg, Sweden) in 30 healthy preschool children (ages 3-5 years) and 27 adults with coronary artery disease (CAD; ages 48-81 years). For both groups, Bland-Altman plots revealed good agreement with a negligible mean cIMT difference of -0·03 mm. Software differences were statistically, but not clinically, significant for preschool images (P = 0·001) and were not significant for CAD images (P = 0·09). Intra- and interoperator repeatability was high and comparable between software for preschool images (ICC, 0·90-0·96; CV, 1·3-2·5%), but slightly higher with the automated ultrasound than the semi-automated reference software for CAD images (ICC, 0·98-0·99; CV, 1·4-2·0% versus ICC, 0·84-0·89; CV, 5·6-6·8%). These findings suggest that the automated ultrasound software produces valid cIMT values in healthy preschool children and adults with CAD. Automated ultrasound software may be useful for ensuring consistency among multisite research initiatives or large cohort studies involving repeated cIMT measures, particularly in adults with documented CAD.

Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment

BACKGROUND AND OBJECTIVES

Standardization of the carotid IMT requires a reference marker in ultrasound scans. It has been shown previously that manual reference marker and manually created carotid segments are used for measuring IMT in these segments. Manual methods are tedious, time consuming, subjective, and prone to errors. Bulb edge can be considered as a reference marker for measurements of the cIMT. However, bulb edge can be difficult to locate in ultrasound scans due to: (a) low signal to noise ratio in the bulb region as compared to common carotid artery region; (b) uncertainty of bulb location in craniocaudal direction; and (c) variability in carotid bulb shape and size. This paper presents an automated system (a class of AtheroEdge™ system from AtheroPoint™, Roseville, CA, USA) for locating the bulb edge as a reference marker and further develop segmental-IMT (sIMT) which measures IMT in 10mm segments (namely: s1, s2 and s3) proximal to the bulb edge.

METHODS

The patented methodology uses an integrated approach which combines carotid geometry and pixel-classification paradigms. The system first finds the bulb edge and then measures the sIMT proximal to the bulb edge. The system also estimates IMT in bulb region (bIMT). The 649 image database consists of varying plaque (light, moderate to heavy), image resolutions, shapes, sizes and ethnicity.

RESULTS

Our results show that the IMT contributions in different carotid segments are as follows: bulb-IMT 34%, s1-IMT 29.46%, s2-IMT 11.48%, and s3-IMT 12.75%, respectively. We compare our automated results against reader's tracings demonstrating the following performance: mean lumen-intima error: 0.01235 ± 0.01224mm, mean media-adventitia error: 0.020933 ± 0.01539mm and mean IMT error: 0.01063 ± 0.0031mm. Our system's Precision of Merit is: 98.23%, coefficient of correlation between automated and Reader's IMT is: 0.998 (p-value < 0.0001). These numbers are improved compared to previous publications by Suri's group which is automated multi-resolution conventional cIMT.

CONCLUSIONS

Our fully automated bulb detection system reports 92.67% precision against ideal bulb edge locations as marked by the reader in the bulb transition zone.

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.

Inter-observer Variability Analysis of Automatic Lung Delineation in Normal and Disease Patients

Human interaction has become almost mandatory for an automated medical system wishing to be accepted by clinical regulatory agencies such as Food and Drug Administration. Since this interaction causes variability in the gathered data, the inter-observer and intra-observer variability must be analyzed in order to validate the accuracy of the system. This study focuses on the variability from different observers that interact with an automated lung delineation system that relies on human interaction in the form of delineation of the lung borders. The database consists of High Resolution Computed Tomography (HRCT): 15 normal and 81 diseased patients' images taken retrospectively at five levels per patient. Three observers manually delineated the lungs borders independently and using software called ImgTracer™ (AtheroPoint™, Roseville, CA, USA) to delineate the lung boundaries in all five levels of 3-D lung volume. The three observers consisted of Observer-1: lesser experienced novice tracer who is a resident in radiology under the guidance of radiologist, whereas Observer-2 and Observer-3 are lung image scientists trained by lung radiologist and biomedical imaging scientist and experts. The inter-observer variability can be shown by comparing each observer's tracings to the automated delineation and also by comparing each manual tracing of the observers with one another. The normality of the tracings was tested using D'Agostino-Pearson test and all observers tracings showed a normal P-value higher than 0.05. The analysis of variance (ANOVA) test between three observers and automated showed a P-value higher than 0.89 and 0.81 for the right lung (RL) and left lung (LL), respectively. The performance of the automated system was evaluated using Dice Similarity Coefficient (DSC), Jaccard Index (JI) and Hausdorff (HD) Distance measures. Although, Observer-1 has lesser experience compared to Obsever-2 and Obsever-3, the Observer Deterioration Factor (ODF) shows that Observer-1 has less than 10% difference compared to the other two, which is under acceptable range as per our analysis. To compare between observers, this study used regression plots, Bland-Altman plots, two tailed T-test, Mann-Whiney, Chi-Squared tests which showed the following P-values for RL and LL: (i) Observer-1 and Observer-3 were: 0.55, 0.48, 0.29 for RL and 0.55, 0.59, 0.29 for LL; (ii) Observer-1 and Observer-2 were: 0.57, 0.50, 0.29 for RL and 0.54, 0.59, 0.29 for LL; (iii) Observer-2 and Observer-3 were: 0.98, 0.99, 0.29 for RL and 0.99, 0.99, 0.29 for LL. Further, CC and R-squared coefficients were computed between observers which came out to be 0.9 for RL and LL. All three observers however manage to show the feature that diseased lungs are smaller than normal lungs in terms of area.

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.