Automated plaque analysis for the prognostication of major adverse cardiac events

Prognostic value of serial coronary computed tomography angiography-derived perivascular fat-attenuation index and plaque volume in patients with suspected coronary artery disease

AIMS

To investigate the prognostic value of serial coronary computed tomography angiography (CCTA) derived plaque information, fractional flow reserve (CT-FFR), and perivascular fat-attenuation index (FAI) on major adverse cardiac events (MACE) in patients with suspected coronary artery disease.

MATERIALS AND METHODS

A total of 252 patients who underwent serial CCTA between January 2018 and December 2021 and were followed until June 2022. MACE were recorded. The analysis indexes included percent diameter stenosis (%DS), lesion length, plaque volume, CT-FFR, and FAI, with an emphasis on their changes between the baseline and follow-up CCTAs. Multivariate regression analysis were employed to identify independent risk factors for MACE.

RESULTS

After a median follow-up of 48-month, MACE occurred in 32 patients (12.7%). Patients with MACE displayed more severe stenosis, longer lesions, and larger plaque volumes in both baseline and follow-up CCTAs compared with no-MACE patients (all P<0.05). Patients with MACE displayed more severe stenosis, longer lesion, and larger plaque volume in both baseline and follow-up CCTAs compared with no-MACE patients. In addition, MACE patients also showed lower CT-FFR and higher △CT-FFR. Although FAI was significantly higher in MACE patients at baseline CCTA, FAI was notably increased in MACE patients, and decreased in the no-MACE patients (all P<0.05). Logistic regression analysis showed that ΔFAI, %DS, and plaque volume were independent predictors of MACE, with ΔFAI being the most significant (OR: 16.725, P<0.000). A multivariable model showed a significantly improved C-index of 0.903 (95% confidence interval: 0.836-0.970) for MACE prediction, when compared with single index alone.

CONCLUSIONS

Serial CCTA-derived ΔFAI, %DS, and plaque volume are crucial independent predictors of MACE in patients with suspected coronary artery disease, highlighting the importance of CCTA in patient risk stratification and prognostic assessment.

Intra- and inter-reader reproducibility in quantitative coronary plaque analysis on coronary computed tomography angiography

PURPOSE

Coronary artery plaque burden, low attenuation non-calcified plaque (LAP), and pericoronary adipose tissue (PCAT) on coronary CT angiography (CCTA), have been linked to future cardiac events. The purpose of this study was to evaluate intra- and inter reader reproducibility in the quantification of coronary plaque burden and its characteristics using an artificial intelligence-enhanced semi-automated software.

MATERIALS AND METHODS

A total of 10 women and 6 men, aged 52 (IQR 49-58) underwent CCTA using a Siemens Somatom Force, Somatom Definition AS and Somatom Definition Flash scanners. Two expert readers utilized dedicated semi-automatic software (vascuCAP, Elucid Bioimaging, Wenham, MA) to assess calcified plaque, low attenuation plaque and PCAT. Readers were blinded to all clinical information and repeated their analysis at 6 weeks in random order to minimize recall bias. Data analysis was performed on the right and left coronary arteries. Intra- and inter-reader reproducibility was compared using Pearson correlation coefficient, while absolute values between analyses and readers were compared with paired non-parametric tests. This is a sub-study of the Specialized Center of Research Excellence (SCORE) clinical trial (5U54AG062334).

RESULTS

A total of 64 vessels from 16 patients were analyzed. Intra-reader Pearson correlation coefficients for calcified plaque volume, LAP volume and PCAT volumes were 0.96, 0.99 and 0.92 for reader 1 and 0.94, 0.94 and 0.95 for reader 2, respectively, (all p < 0.0001). Inter-reader Pearson correlation coefficients for calcified plaque volume, LAP and PCAT volumes were 0.92, 0.96 and 0.78, and 0.99, 0.99 and 0.93 on the second analyses, all had a p value <0.0001. There was no significant bias on the corresponding Bland-Altman analyses.

CONCLUSION

Volume measurement of coronary plaque burden and PCAT volume can be performed with high intra- and inter-reader agreement.

The Role of Artificial Intelligence in Cardiac Imaging

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

Bacteriophages in nature: recent advances in research tools and diverse environmental and biotechnological applications

Bacteriophages infect and replicate within bacteria and play a key role in the environment, particularly in microbial ecosystems and bacterial population dynamics. The increasing recognition of their significance stems from their wide array of environmental and biotechnological uses, which encompass the mounting issue of antimicrobial resistance (AMR). Beyond their therapeutic potential in combating antibiotic-resistant infections, bacteriophages also find vast applications such as water quality monitoring, bioremediation, and nutrient cycling within environmental sciences. Researchers are actively involved in isolating and characterizing bacteriophages from different natural sources to explore their applications. Gaining insights into key aspects such as the life cycle of bacteriophages, their host range, immune interactions, and physical stability is vital to enhance their application potential. The establishment of diverse phage libraries has become indispensable to facilitate their wide-ranging uses. Consequently, numerous protocols, ranging from traditional to cutting-edge techniques, have been developed for the isolation, detection, purification, and characterization of bacteriophages from diverse environmental sources. This review offers an exploration of tools, delves into the methods of isolation, characterization, and the extensive environmental applications of bacteriophages, particularly in areas like water quality assessment, the food sector, therapeutic interventions, and the phage therapy in various infections and diseases.

Predicting coronary plaque progression with conventional plaque parameters and radiomics features derived from coronary CT angiography

OBJECTIVES

To determine the value of combining conventional plaque parameters and radiomics features derived from coronary computed tomography angiography (CCTA) for predicting coronary plaque progression.

MATERIALS AND METHODS

Clinical data and CCTA images of 400 patients who underwent at least two CCTA examinations between January 2009 and August 2020 were analyzed retrospectively. Diameter stenosis, total plaque volume and burden, calcified plaque volume and burden, noncalcified plaque volume and burden (NCPB), pericoronary fat attenuation index (FAI), and other conventional plaque parameters were recorded. The patients were assigned to a training cohort (n = 280) and a validation cohort (n = 120) in a 7:3 ratio using a stratified random splitting method. The area under the receiver operating characteristics curve (AUC) was used to evaluate the predictive abilities of conventional parameters (model 1), radiomics features (model 2), and their combination (model 3).

RESULTS

FAI and NCPB were identified as independent risk factors for coronary plaque progression in the training cohort. Both model 2 (training cohort AUC: 0.814, p < 0.001; validation cohort AUC: 0.729, p = 0.288) and model 3 (training cohort AUC: 0.824, p < 0.001; validation cohort AUC: 0.758, p = 0.042) had better diagnostic performances in predicting plaque progression than model 1 (training cohort AUC: 0.646; validation cohort AUC: 0.654). Moreover, model 3 was slightly higher than model 2, although not statistically significant.

CONCLUSIONS

The combination of conventional coronary plaque parameters and CCTA-derived radiomics features had a better ability to predict plaque progression than conventional parameters alone.

CLINICAL RELEVANCE STATEMENT

The conventional coronary plaque characteristics such as noncalcified plaque burden, pericoronary fat attenuation index, and radiomics features derived from CCTA can identify plaques prone to progression, which is helpful for further clinical decision-making of coronary artery disease.

KEY POINTS

• FAI and NCPB were identified as independent risk factors for predicting plaque progression. • Coronary plaque radiomics features were more advantageous than conventional parameters in predicting plaque progression. • The combination of conventional coronary plaque parameters and radiomics features could significantly improve the predictive ability of plaque progression over conventional parameters alone.

Artificial intelligence in cardiac computed tomography

Artificial Intelligence (AI) is a broad discipline of computer science and engineering. Modern application of AI encompasses intelligent models and algorithms for automated data analysis and processing, data generation, and prediction with applications in visual perception, speech understanding, and language translation. AI in healthcare uses machine learning (ML) and other predictive analytical techniques to help sort through vast amounts of data and generate outputs that aid in diagnosis, clinical decision support, workflow automation, and prognostication. Coronary computed tomography angiography (CCTA) is an ideal union for these applications due to vast amounts of data generation and analysis during cardiac segmentation, coronary calcium scoring, plaque quantification, adipose tissue quantification, peri-operative planning, fractional flow reserve quantification, and cardiac event prediction. In the past 5 years, there has been an exponential increase in the number of studies exploring the use of AI for cardiac computed tomography (CT) image acquisition, de-noising, analysis, and prognosis. Beyond image processing, AI has also been applied to improve the imaging workflow in areas such as patient scheduling, urgent result notification, report generation, and report communication. In this review, we discuss algorithms applicable to AI and radiomic analysis; we then present a summary of current and emerging clinical applications of AI in cardiac CT. We conclude with AI's advantages and limitations in this new field.

Recent advances in artificial intelligence for cardiac CT: Enhancing diagnosis and prognosis prediction

Recent advances in artificial intelligence (AI) for cardiac computed tomography (CT) have shown great potential in enhancing diagnosis and prognosis prediction in patients with cardiovascular disease. Deep learning, a type of machine learning, has revolutionized radiology by enabling automatic feature extraction and learning from large datasets, particularly in image-based applications. Thus, AI-driven techniques have enabled a faster analysis of cardiac CT examinations than when they are analyzed by humans, while maintaining reproducibility. However, further research and validation are required to fully assess the diagnostic performance, radiation dose-reduction capabilities, and clinical correctness of these AI-driven techniques in cardiac CT. This review article presents recent advances of AI in the field of cardiac CT, including deep-learning-based image reconstruction, coronary artery motion correction, automatic calcium scoring, automatic epicardial fat measurement, coronary artery stenosis diagnosis, fractional flow reserve prediction, and prognosis prediction, analyzes current limitations of these techniques and discusses future challenges.

Quantitative imaging biomarkers of coronary plaque morphology: insights from EVAPORATE

Aims

Residual cardiovascular risk persists despite statin therapy. In REDUCE-IT, icosapent ethyl (IPE) reduced total events, but the mechanisms of benefit are not fully understood. EVAPORATE evaluated the effects of IPE on plaque characteristics by coronary computed tomography angiography (CCTA). Given the conclusion that the IPE-treated patients demonstrate that plaque burden decreases has already been published in the primary study analysis, we aimed to demonstrate whether the use of an analytic technique defined and validated in histological terms could extend the primary study in terms of whether such changes could be reliably seen in less time on drug, at the individual (rather than only at the cohort) level, or both, as neither of these were established by the primary study result.

Methods and Results

EVAPORATE randomized the patients to IPE 4 g/day or placebo. Plaque morphology, including lipid-rich necrotic core (LRNC), fibrous cap thickness, and intraplaque hemorrhage (IPH), was assessed using the ElucidVivo® (Elucid Bioimaging Inc.) on CCTA. The changes in plaque morphology between the treatment groups were analyzed. A neural network to predict treatment assignment was used to infer patient representation that encodes significant morphological changes. Fifty-five patients completed the 18-month visit in EVAPORATE with interpretable images at each of the three time points. The decrease of LRNC between the patients on IPE vs. placebo at 9 months (reduction of 2 mm3 vs. an increase of 41 mm3, p = 0.008), widening at 18 months (6 mm3 vs. 58 mm3 increase, p = 0.015) were observed. While not statistically significant on a univariable basis, reductions in wall thickness and increases in cap thickness motivated multivariable modeling on an individual patient basis. The per-patient response assessment was possible using a multivariable model of lipid-rich phenotype at the 9-month follow-up, p < 0.01 (sustained at 18 months), generalizing well to a validation cohort.

Conclusion

Plaques in the IPE-treated patients acquired more characteristics of stability. Reliable assessment using histologically validated analysis of individual response is possible at 9 months, with sustained stabilization at 18 months, providing a quantitative basis to elucidate drug mechanism and assess individual patient response.

Computed Tomography Assessment of Coronary Atherosclerosis: From Threshold-Based Evaluation to Histologically Validated Plaque Quantification

Arterial plaque rupture and thrombosis is the primary cause of major cardiovascular and neurovascular events. The identification of atherosclerosis, especially high-risk plaques, is therefore crucial to identify high-risk patients and to implement preventive therapies. Computed tomography angiography has the ability to visualize and characterize vascular plaques. The standard methods for plaque evaluation rely on the assessment of plaque burden, stenosis severity, the presence of positive remodeling, napkin ring sign, and spotty calcification, as well as Hounsfield Unit (HU)-based thresholding for plaque quantification; the latter with multiple shortcomings. Semiautomated threshold-based segmentation techniques with predefined HU ranges identify and quantify limited plaque characteristics, such as low attenuation, non-calcified, and calcified plaque components. Contrary to HU-based thresholds, histologically validated plaque characterization, and quantification, an emerging Artificial intelligence-based approach has the ability to differentiate specific tissue types based on a biological correlate, such as lipid-rich necrotic core and intraplaque hemorrhage that determine plaque vulnerability. In this article, we review the relevance of plaque characterization and quantification and discuss the benefits and limitations of the currently available plaque assessment and classification techniques.

Multiparametric Quantitative Imaging in Risk Prediction: Recommendations for Data Acquisition, Technical Performance Assessment, and Model Development and Validation

Combinations of multiple quantitative imaging biomarkers (QIBs) are often able to predict the likelihood of an event of interest such as death or disease recurrence more effectively than single imaging measurements can alone. The development of such multiparametric quantitative imaging and evaluation of its fitness of use differs from the analogous processes for individual QIBs in several key aspects. A computational procedure to combine the QIB values into a model output must be specified. The output must also be reproducible and be shown to have reasonably strong ability to predict the risk of an event of interest. Attention must be paid to statistical issues not often encountered in the single QIB scenario, including overfitting and bias in the estimates of model performance. This is the fourth in a five-part series on statistical methodology for assessing the technical performance of multiparametric quantitative imaging. Considerations for data acquisition are discussed and recommendations from the literature on methodology to construct and evaluate QIB-based models for risk prediction are summarized. The findings in the literature upon which these recommendations are based are demonstrated through simulation studies. The concepts in this manuscript are applied to a real-life example involving prediction of major adverse cardiac events using automated plaque analysis.

Atherosclerosis risk classification with computed tomography angiography: A radiologic-pathologic validation study

BACKGROUND AND AIMS

The application of machine learning to assess plaque risk phenotypes on cardiovascular CT angiography (CTA) is an area of active investigation. Studies using accepted histologic definitions of plaque risk as ground truth for machine learning models are uncommon. The aim was to evaluate the accuracy of a machine-learning software for determining plaque risk phenotype as compared to expert pathologists (histologic ground truth).

METHODS

Sections of atherosclerotic plaques paired with CTA were prospectively collected from patients undergoing carotid endarterectomy at two centers. Specimens were annotated for lipid-rich necrotic core, calcification, matrix, and intraplaque hemorrhage at 2 mm spacing and classified as minimal disease, stable plaque, or unstable plaque according to a modified American Heart Association histological definition. Phenotype is determined in two steps: plaque morphology is delineated according to histological tissue definitions, followed by a machine learning classifier. The performance in derivation and validation cohorts for plaque risk categorization and stenosis was compared to histologic ground truth at each matched cross-section.

RESULTS

A total of 496 and 408 vessel cross-sections in the derivation and validation cohorts (from 30 and 23 patients, respectively). The software demonstrated excellent agreement in the validation cohort with histological ground truth plaque risk phenotypes with weighted kappa of 0.82 [0.78-0.86] and area under the receiver operating curve for correct identification of plaque type was 0.97 [0.96, 0.98], 0.95 [0.94, 0.97], 0.99 [0.99, 1.0] for unstable plaque, stable plaque, and minimal disease, respectively. Diameter stenosis correlated poorly to histologically defined plaque type; weighted kappa 0.25 in the validation cohort.

CONCLUSIONS

A machine-learning software trained on histological ground-truth tissue inputs demonstrated high accuracy for identifying plaque stability phenotypes as compared to expert pathologists.

Virtual pathology: Reaching higher standards for noninvasive CTA tissue characterization capability by using histology as a truth standard

AIMS

Despite advances in therapy, reduction in myocardial infarction or death remains elusive. Whereas computed tomography angiography (CTA) is increasingly appreciated, the analyses are often subjective or qualitative. Methods for specific tissue characterization using histopathologic correlates have recently been reported. We extend this here to demonstrate accurate discrimination between, and quantitation of, lipid-rich necrotic core (LRNC), intraplaque hemorrhage (IPH), and fibrotic tissues.

METHODS

NCT02143102 collected 576 tissue samples with paired CTA. Cardiovascular pathologists annotated LRNC, IPH, and dense calcification (CALC) regions as a reference standard. Blinded to histology, CTA was analyzed using ElucidVivo (Elucid Bioimaging Inc., Boston, MA USA). Structure and tissue characteristics of atherosclerotic plaque from CTA, accounting for both the imaging acquisition process and the biology, accounting for differences in density distributions that result from the different cellular and molecular level milieu of the relevant tissue types.

RESULTS

LRNC was tested across a true range of 0-10 mm², with a difference of 0.15 mm² and a slope of 0.92. IPH was tested across a true range of 0-18 mm², with a difference from histology of 1.68 mm² and a slope of 0.95. CALC was tested across a range of 0-14 mm², with a difference of -0.06 mm² and a slope of 0.99. Matrix tissue (MATX) was tested across a range of 4-52 mm², with a difference of 0.02 mm² and a slope of 0.91.

CONCLUSION

LRNC, IPH, CALC, and MATX may be objectively quantified using histopathologic correlates automatically from CTA for use singly or in combination to optimize patient care. The availability of objectively validated quantitative markers that may be followed longitudinally may extend the clinical utility of CTA. Additionally, these measures contribute efficacy variables for developing novel drugs and clinical decision support tools for tailored therapeutics.

Biomechanical Assessment of Macro-Calcification in Human Carotid Atherosclerosis and Its Impact on Smooth Muscle Cell Phenotype

Intimal calcification and vascular stiffening are predominant features of end-stage atherosclerosis. However, their role in atherosclerotic plaque instability and how the extent and spatial distribution of calcification influence plaque biology remain unclear. We recently showed that extensive macro calcification can be a stabilizing feature of late-stage human lesions, associated with a reacquisition of more differentiated properties of plaque smooth muscle cells (SMCs) and extracellular matrix (ECM) remodeling. Here, we hypothesized that biomechanical forces related to macro-calcification within plaques influence SMC phenotype and contribute to plaque stabilization. We generated a finite element modeling (FEM) pipeline to assess plaque tissue stretch based on image analysis of preoperative computed tomography angiography (CTA) of carotid atherosclerotic plaques to visualize calcification and soft tissues (lipids and extracellular matrix) within the lesions. Biomechanical stretch was significantly reduced in tissues in close proximity to macro calcification, while increased levels were observed within distant soft tissues. Applying this data to an in vitro stretch model on primary vascular SMCs revealed upregulation of typical markers for differentiated SMCs and contractility under low stretch conditions but also impeded SMC alignment. In contrast, high stretch conditions in combination with calcifying conditions induced SMC apoptosis. Our findings suggest that the load bearing capacities of macro calcifications influence SMC differentiation and survival and contribute to atherosclerotic plaque stabilization.

Anatomic and Hemodynamic Plaque Characteristics for Subsequent Coronary Events

Objectives

While coronary computed tomography angiography (CCTA) enables the evaluation of anatomic and hemodynamic plaque characteristics of coronary artery disease (CAD), the clinical roles of these characteristics are not clear. We sought to evaluate the prognostic implications of CCTA-derived anatomic and hemodynamic plaque characteristics in the prediction of subsequent coronary events.

Methods

The study cohort consisted of 158 patients who underwent CCTA with suspected CAD within 6–36 months before percutaneous coronary intervention (PCI) for acute myocardial infarction (MI) or unstable angina and age-/sex-matched 62 patients without PCI as the control group. Preexisting high-risk plaque characteristics (HRPCs: low attenuation plaque, positive remodeling, napkin-ring sign, spotty calcification, minimal luminal area &lt;4 mm2, or plaque burden ≥70%) and hemodynamic parameters (per-vessel fractional flow reserve [FFRCT], per-lesion ΔFFRCT, and percent ischemic myocardial mass) were analyzed from prior CCTA. The primary outcome was a subsequent coronary event, which was defined as a composite of vessel-specific MI or revascularization for unstable angina. The prognostic impact of clinical risk factors, HRPCs, and hemodynamic parameters were compared between vessels with (160 vessels) and without subsequent coronary events (329 vessels).

Results

Vessels with a subsequent coronary event had higher number of HRPCs (2.6 ± 1.4 vs. 2.3 ± 1.4, P = 0.012), lower FFRCT (0.76 ± 0.13 vs. 0.82 ± 0.11, P &lt; 0.001), higher ΔFFRCT (0.14 ± 0.12 vs. 0.09 ± 0.08, P &lt; 0.001), and higher percent ischemic myocardial mass (29.0 ± 18.5 vs. 26.0 ± 18.4, P = 0.022) than those without a subsequent coronary event. Compared with clinical risk factors, HRPCs and hemodynamic parameters showed higher discriminant abilities for subsequent coronary events with ΔFFRCT being the most powerful predictor. HRPCs showed additive discriminant ability to clinical risk factors (c-index 0.620 vs. 0.558, P = 0.027), and hemodynamic parameters further increased discriminant ability (c-index 0.698 vs. 0.620, P = 0.001) and reclassification abilities (NRI 0.460, IDI 0.061, P &lt; 0.001 for all) for subsequent coronary events. Among vessels with negative FFRCT (&gt;0.80), adding HRPCs into clinical risk factors significantly increased discriminant and reclassification abilities for subsequent coronary events (c-index 0.687 vs. 0.576, P = 0.005; NRI 0.412, P = 0.002; IDI 0.064, P = 0.001) but not for vessels with positive FFRCT (≤0.80).

Conclusion

In predicting subsequent coronary events, both HRPCs and hemodynamic parameters by CCTA allow better prediction of subsequent coronary events than clinical risk factors. HRPCs provide more incremental predictability than clinical risk factors alone among vessels with negative FFRCT but not among vessels with positive FFRCT.

Clinical Trial Registration

PreDiction and Validation of Clinical CoursE of Coronary Artery DiSease With CT-Derived Non-INvasive HemodYnamic Phenotyping and Plaque Characterization (DESTINY Study), NCT04794868.

Recent Advances in Coronary Computed Tomography Angiogram: The Ultimate Tool for Coronary Artery Disease

PURPOSE OF REVIEW

The emerging technologies in multidetector computed tomography scanners gave the ability to image coronary arteries in a single heartbeat, at a higher quality, and low radiation dose. Furthermore, incorporating artificial intelligence and machine learning into image processing and interpretation have extended the use for coronary computed tomography angiogram (CCTA) and its applications. In this review, we will explore the recent evidence and advances supporting CCTA to become the ultimate tool for coronary artery disease.

RECENT FINDINGS

Results from the EVINCI, ISCHEMIA, SCOT-HEART, and PROMISE showed that CCTA is better in patients' risk stratification and in detecting subclinical atherosclerosis, resulting in earlier interventions and lesser events. Additionally, CCTA gave us a closer look on atherosclerotic disease by identifying different type of plaque and their clinical significance. Furthermore, FFR_CT is a notable example of incorporating artificial intelligence into CCTA. This technology helped us to accurately and non-invasively identify flow limiting lesions, guiding revascularization. As a result of the recent evidence, CCTA have made its way into the chest pain guidelines all over the world. Moreover, CCTA have the potential to revolutionize our understanding and standards in screening, preventing, and managing heart disease.

Artificial Intelligence in Cardiovascular Atherosclerosis Imaging

At present, artificial intelligence (AI) has already been applied in cardiovascular imaging (e.g., image segmentation, automated measurements, and eventually, automated diagnosis) and it has been propelled to the forefront of cardiovascular medical imaging research. In this review, we presented the current status of artificial intelligence applied to image analysis of coronary atherosclerotic plaques, covering multiple areas from plaque component analysis (e.g., identification of plaque properties, identification of vulnerable plaque, detection of myocardial function, and risk prediction) to risk prediction. Additionally, we discuss the current evidence, strengths, limitations, and future directions for AI in cardiac imaging of atherosclerotic plaques, as well as lessons that can be learned from other areas. The continuous development of computer science and technology may further promote the development of this field.

CT angiographic biomarkers help identify vulnerable carotid artery plaque

OBJECTIVE

Current risk assessment for patients with carotid atherosclerosis relies primarily on measuring the degree of stenosis. More reliable risk-stratification could improve patient selection for targeted treatment. We developed and validated a model to predict major adverse neurological events (MANE; stroke, transient ischemic attack, and amaurosis fugax) incorporating a combination of plaque morphology, patient demographics, and patient clinical information.

METHODS

We enrolled 221 patients with asymptomatic carotid stenosis of any severity who had CT angiography at baseline and at least 6 months later. Images were analyzed for carotid plaque morphology (plaque geometry and tissue composition). Data were partitioned (training and validation cohorts). 190 patients had complete records and were advanced to analysis. The training cohort was used to develop the best model for predicting MANE, incorporating patient and plaque features. First, single-variable correlation and unsupervised clustering were performed. Next, several multi-variable models were implemented for the response variable of MANE. The best model was selected by optimizing area under the receiver operating characteristic curve (AUC, ROC) and Kappa. The model was validated on the sequestered data to demonstrate generalizability.

RESULTS

Sixty-two patients suffered a MANE on follow-up. Unsupervised clustering of patient and plaque features identified single-variable predictors of MANE. Multi-variable predictive modeling showed that a combination of plaque features at baseline (matrix, intra-plaque hemorrhage (IPH), wall thickness, plaque burden) with clinical features (age, BMI, lipid levels) best predicted MANE (AUC 0.79), while percent diameter stenosis performed worst (AUC 0.55). The strongest single variable in discriminating between patients with and without events was IPH, and the most predictive model was produced when IPH was considered together with wall remodeling. The selected model also performed well on the validation dataset (AUC of 0.64) and maintained superiority over percent diameter stenosis (AUC of 0.49).

CONCLUSIONS

A composite of plaque geometry, plaque tissue composition, patient demographics, and clinical information predicts MANE better than the traditionally utilized degree of stenosis alone in carotid atherosclerosis. Implementing this predictive model in the clinical setting can help identify patients at high-risk for major adverse neurological events.

The evolving role of artificial intelligence in cardiac image analysis

Research in artificial intelligence (AI) have progressed over the last decade. The field of cardiac imaging has seen significant developments using newly developed deep learning methods for automated image analysis and AI tools for disease detection and prognostication. This review article is aimed at those without special background in AI. We review AI concepts and we survey the growing contemporary applications of AI for image analysis in echocardiography, nuclear cardiology, cardiac computed tomography, cardiac magnetic resonance, and invasive angiography.

Carotid Plaque Phenotyping by Correlating Plaque Morphology from Computed Tomography Angiography with Transcriptional Profiling

OBJECTIVE

Ischaemic strokes can be caused by unstable carotid atherosclerosis, but methods for identification of high risk lesions are lacking. Carotid plaque morphology imaging using software for visualisation of plaque components in computed tomography angiography (CTA) may improve assessment of plaque phenotype and stroke risk, but it is unknown if such analyses also reflect the biological processes related to lesion stability. Here, we investigated how carotid plaque morphology by image analysis of CTA is associated with biological processes assessed by transcriptomic analyses of corresponding carotid endarterectomies (CEAs).

METHODS

Carotid plaque morphology was assessed in patients undergoing CEA for symptomatic or asymptomatic carotid stenosis consecutively enrolled between 2006 and 2015. Computer based analyses of pre-operative CTA was performed to define calcification, lipid rich necrotic core (LRNC), intraplaque haemorrhage (IPH), matrix (MATX), and plaque burden. Plaque morphology was correlated with molecular profiles obtained from microarrays of corresponding CEAs and models were built to assess the ability of plaque morphology to predict symptomatology.

RESULTS

Carotid plaques (n = 93) from symptomatic patients (n = 61) had significantly higher plaque burden and LRNC compared with plaques from asymptomatic patients (n = 32). Lesions selected from the transcriptomic cohort (n = 40) with high LRNC, IPH, MATX, or plaque burden were characterised by molecular signatures coupled with inflammation and extracellular matrix degradation, typically linked with instability. In contrast, highly calcified plaques had a molecular signature signifying stability with enrichment of profibrotic pathways and repressed inflammation. In a cross validated prediction model for symptoms, plaque morphology by CTA alone was superior to the degree of stenosis.

CONCLUSION

The study demonstrates that CTA image analysis for evaluation of carotid plaque morphology, also reflects prevalent biological processes relevant for assessment of plaque phenotype. The results support the use of CTA image analysis of plaque morphology for risk stratification and management of patients with carotid stenosis.

Phenylacetylglutamine is associated with the degree of coronary atherosclerotic severity assessed by coronary computed tomographic angiography in patients with suspected coronary artery disease

BACKGROUND AND AIMS

Phenylacetylglutamine (PAG), a gut microbiota metabolite, has recently been found to be associated with major adverse cardiovascular events. In this study, we analyzed the relationship between plasma PAG and coronary atherosclerotic severity assessed by coronary computed tomographic angiography (CCTA).

METHODS

We enrolled consecutive patients with suspected coronary artery disease (CAD) who underwent CCTA. Plasma PAG was measured by mass spectrometry. Coronary atherosclerotic severity was evaluated based on plaque burden and plaque vulnerability. Plaque burden was quantified as percent atheroma volume (PAV), CCTA-derived SYNTAX score (CT-SYNTAX) and CAD reporting and data system score (CAD-RADS). Plaque vulnerability was evaluated by the presence of adverse characteristics.

RESULTS

A total of 686 patients were enrolled. The patients were divided into two groups based on median plasma PAG (3.25 μM). A correlation was found between plasma PAG and PAV (r = 0.499, p < 0.01). Patients with obstructive CAD (CAD-RADS>3) and high coronary lesion complexity (CT-SYNTAX≥23) had higher plasma PAG (2.04 vs. 3.8 μM and 2.85 vs. 4.49 μM, respectively; p < 0.01 for all). After adjustment for confounding factors, plasma PAG remained associated with PAV (β: 0.98, p < 0.01), and patients in the higher PAG group had higher risks of obstructive CAD (odds ratio [OR]: 1.88, p < 0.01) and high coronary lesion complexity (OR: 1.47; p < 0.01). In addition, a high plasma PAG level (≥3.25 μM) was not an independent predictor of the presence of high-risk plaques.

CONCLUSIONS

There was an independent association between plasma PAG levels and the coronary atherosclerotic burden among patients with suspected CAD.

Artificial intelligence in coronary computed tomography angiography

Coronary computed tomography angiography (CCTA) is recommended as a frontline diagnostic tool in the non-invasive assessment of patients with suspected coronary artery disease (CAD) and cardiovascular risk stratification. To date, artificial intelligence (AI) techniques have brought major changes in the way that we make individualized decisions for patients with CAD. Applications of AI in CCTA have produced improvements in many aspects, including assessment of stenosis degree, determination of plaque type, identification of high-risk plaque, quantification of coronary artery calcium score, diagnosis of myocardial infarction, estimation of computed tomography-derived fractional flow reserve, left ventricular myocardium analysis, perivascular adipose tissue analysis, prognosis of CAD, and so on. The purpose of this review is to provide a comprehensive overview of current status of AI in CCTA.

Proteoglycan 4 Modulates Osteogenic Smooth Muscle Cell Differentiation during Vascular Remodeling and Intimal Calcification

Calcification is a prominent feature of late-stage atherosclerosis, but the mechanisms driving this process are unclear. Using a biobank of carotid endarterectomies, we recently showed that Proteoglycan 4 (PRG4) is a key molecular signature of calcified plaques, expressed in smooth muscle cell (SMC) rich regions. Here, we aimed to unravel the PRG4 role in vascular remodeling and intimal calcification. PRG4 expression in human carotid endarterectomies correlated with calcification assessed by preoperative computed tomographies. PRG4 localized to SMCs in early intimal thickening, while in advanced lesions it was found in the extracellular matrix, surrounding macro-calcifications. In experimental models, Prg4 was upregulated in SMCs from partially ligated ApoE-/- mice and rat carotid intimal hyperplasia, correlating with osteogenic markers and TGFb1. Furthermore, PRG4 was enriched in cells positive for chondrogenic marker SOX9 and around plaque calcifications in ApoE-/- mice on warfarin. In vitro, PRG4 was induced in SMCs by IFNg, TGFb1 and calcifying medium, while SMC markers were repressed under calcifying conditions. Silencing experiments showed that PRG4 expression was driven by transcription factors SMAD3 and SOX9. Functionally, the addition of recombinant human PRG4 increased ectopic SMC calcification, while arresting cell migration and proliferation. Mechanistically, it suppressed endogenous PRG4, SMAD3 and SOX9, and restored SMC markers' expression. PRG4 modulates SMC function and osteogenic phenotype during intimal remodeling and macro-calcification in response to TGFb1 signaling, SMAD3 and SOX9 activation. The effects of PRG4 on SMC phenotype and calcification suggest its role in atherosclerotic plaque stability, warranting further investigations.

Artificial intelligence in computed tomography plaque characterization: A review

Cardiovascular disease (CVD) is associated with high mortality around the world. Prevention and early diagnosis are key targets in reducing the socio-economic burden of CVD. Artificial intelligence (AI) has experienced a steady growth due to technological innovations that have to lead to constant development. Several AI algorithms have been applied to various aspects of CVD in order to improve the quality of image acquisition and reconstruction and, at the same time adding information derived from the images to create strong predictive models. In computed tomography angiography (CTA), AI can offer solutions for several parts of plaque analysis, including an automatic assessment of the degree of stenosis and characterization of plaque morphology. A growing body of evidence demonstrates a correlation between some type of plaques, so-called high-risk plaque or vulnerable plaque, and cardiovascular events, independent of the degree of stenosis. The radiologist must apprehend and participate actively in developing and implementing AI in current clinical practice. In this current overview on the existing AI literature, we describe the strengths, limitations, recent applications, and promising developments of employing AI to plaque characterization with CT.

Virtual Transcriptomics: Noninvasive Phenotyping of Atherosclerosis by Decoding Plaque Biology From Computed Tomography Angiography Imaging

[Figure: see text].

Focal pericoronary adipose tissue attenuation is related to plaque presence, plaque type, and stenosis severity in coronary CTA

Objectives

To investigate the association of pericoronary adipose tissue mean attenuation (PCAT_MA) with coronary artery disease (CAD) characteristics on coronary computed tomography angiography (CCTA).

Methods

We retrospectively investigated 165 symptomatic patients who underwent third-generation dual-source CCTA at 70kVp: 93 with and 72 without CAD (204 arteries with plaque, 291 without plaque). CCTA was evaluated for presence and characteristics of CAD per artery. PCAT_MA was measured proximally and across the most severe stenosis. Patient-level, proximal PCAT_MA was defined as the mean of the proximal PCAT_MA of the three main coronary arteries. Analyses were performed on patient and vessel level.

Results

Mean proximal PCAT_MA was −96.2 ± 7.1 HU and −95.6 ± 7.8HU for patients with and without CAD (p = 0.644). In arteries with plaque, proximal and lesion-specific PCAT_MA was similar (−96.1 ± 9.6 HU, −95.9 ± 11.2 HU, p = 0.608). Lesion-specific PCAT_MA of arteries with plaque (−94.7 HU) differed from proximal PCAT_MA of arteries without plaque (−97.2 HU, p = 0.015). Minimal stenosis showed higher lesion-specific PCAT_MA (−94.0 HU) than severe stenosis (−98.5 HU, p = 0.030). Lesion-specific PCAT_MA of non-calcified, mixed, and calcified plaque was −96.5 HU, −94.6 HU, and −89.9 HU (p = 0.004). Vessel-based total plaque, lipid-rich necrotic core, and calcified plaque burden showed a very weak to moderate correlation with proximal PCAT_MA.

Conclusions

Lesion-specific PCAT_MA was higher in arteries with plaque than proximal PCAT_MA in arteries without plaque. Lesion-specific PCAT_MA was higher in non-calcified and mixed plaques compared to calcified plaques, and in minimal stenosis compared to severe; proximal PCAT_MA did not show these relationships. This suggests that lesion-specific PCAT_MA is related to plaque development and vulnerability.

Key Points

• In symptomatic patients undergoing CCTA at 70 kVp, PCAT_MAwas higher in coronary arteries with plaque than those without plaque.

• PCAT_MAwas higher for non-calcified and mixed plaques compared to calcified plaques, and for minimal stenosis compared to severe stenosis.

• In contrast to PCAT_MAmeasurement of the proximal vessels, lesion-specific PCAT_MAshowed clear relationships with plaque presence and stenosis degree.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07882-1.

Treatment of Psoriasis With Biologic Therapy Is Associated With Improvement of Coronary Artery Plaque Lipid-Rich Necrotic Core: Results From a Prospective, Observational Study

BACKGROUND

Lipid-rich necrotic core (LRNC), a high-risk coronary plaque feature assessed by coronary computed tomography angiography, is associated with increased risk of future cardiovascular events in patients with subclinical, nonobstructive coronary artery disease. Psoriasis is a chronic inflammatory condition that is associated with increased prevalence of high-risk coronary plaque and risk of cardiovascular events. This study characterized LRNC in psoriasis and how LRNC modulates in response to biologic therapy.

METHODS

Consecutive biologic naïve psoriasis patients (n=209) underwent coronary computed tomography angiography at baseline and 1-year to assess changes in LRNC using a novel histopathologically validated software (vascuCAP Elucid Bioimaging, Boston, MA) before and after biologic therapy over 1 year.

RESULTS

Study participants were middle-aged, predominantly male with similar cardiometabolic and psoriasis status between treatment groups. In all participants at baseline, LRNC was associated with Framingham risk score (β [standardized β]=0.12 [95% CI, 0.00-0.15]; P=0.045), and psoriasis severity (β=0.13 [95% CI, 0.01-0.26]; P=0.029). At 1-year, participants receiving biologic therapy had a reduction in LRNC (mm²; 3.12 [1.99-4.66] versus 2.97 [1.84-4.35]; P=0.028), while those who did not receive biologic therapy over 1 year demonstrated no significant change with nominally higher LRNC (3.12 [1.82-4.60] versus 3.34 [2.04-4.74]; P=0.06). The change in LRNC was significant compared with that of the nonbiologic treated group (ΔLRNC, -0.22 mm² versus 0.14 mm², P=0.004) and remained significant after adjusting for cardiovascular risk factors and psoriasis severity (β=-0.09 [95% CI, -0.01 to -0.18]; P=0.033).

CONCLUSIONS

LRNC was associated with psoriasis severity and cardiovascular risk factors in psoriasis. Additionally, there was favorable modification of LRNC in those on biologic therapy. This study provides evidence of potential reduction in LRNC with treatment of systemic inflammation. Larger, longer follow-up prospective studies should be conducted to understand how changes in LRNC may translate into a reduction in future cardiovascular events in psoriasis.

Coronary Computed Tomography Angiography From Clinical Uses to Emerging Technologies: JACC State-of-the-Art Review

Evaluation of coronary artery disease (CAD) using coronary computed tomography angiography (CCTA) has seen a paradigm shift in the last decade. Evidence increasingly supports the clinical utility of CCTA across various stages of CAD, from the detection of early subclinical disease to the assessment of acute chest pain. Additionally, CCTA can be used to noninvasively quantify plaque burden and identify high-risk plaque, aiding in diagnosis, prognosis, and treatment. This is especially important in the evaluation of CAD in immune-driven conditions with increased cardiovascular disease prevalence. Emerging applications of CCTA based on hemodynamic indices and plaque characterization may provide personalized risk assessment, affect disease detection, and further guide therapy. This review provides an update on the evidence, clinical applications, and emerging technologies surrounding CCTA as highlighted at the 2019 National Heart, Lung and Blood Institute CCTA Summit.

Development and application of artificial intelligence in cardiac imaging

In this review, we describe the technical aspects of artificial intelligence (AI) in cardiac imaging, starting with radiomics, basic algorithms of deep learning and application tasks of algorithms, until recently the availability of the public database. Subsequently, we conducted a systematic literature search for recently published clinically relevant studies on AI in cardiac imaging. As a result, 24 and 14 studies using CT and MRI, respectively, were included and summarized. From these studies, it can be concluded that AI is widely applied in cardiac applications in the clinic, including coronary calcium scoring, coronary CT angiography, fractional flow reserve CT, plaque analysis, left ventricular myocardium analysis, diagnosis of myocardial infarction, prognosis of coronary artery disease, assessment of cardiac function, and diagnosis and prognosis of cardiomyopathy. These advancements show that AI has a promising prospect in cardiac imaging.

Plaque imaging volume analysis: technique and application

The prevention and management of atherosclerosis poses a tough challenge to public health organizations worldwide. Together with myocardial infarction, stroke represents its main manifestation, with up to 25% of all ischemic strokes being caused by thromboembolism arising from the carotid arteries. Therefore, a vast number of publications have focused on the characterization of the culprit lesion, the atherosclerotic plaque. A paradigm shift appears to be taking place at the current state of research, as the attention is gradually moving from the classically defined degree of stenosis to the identification of features of plaque vulnerability, which appear to be more reliable predictors of recurrent cerebrovascular events. The present review will offer a perspective on the present state of research in the field of carotid atherosclerotic disease, focusing on the imaging modalities currently used in the study of the carotid plaque and the impact that such diagnostic means are having in the clinical setting.

Prognostic Value of Coronary Computed Tomography Angiography-derived Morphologic and Quantitative Plaque Markers Using Semiautomated Plaque Software

PURPOSE

In this study, we analyzed the prognostic value of coronary computed tomography angiography-derived morphologic and quantitative plaque markers and plaque scores for major adverse cardiovascular events (MACEs).

MATERIALS AND METHODS

We analyzed the data of patients with suspected coronary artery disease (CAD). Various plaque markers were obtained using a semiautomated software prototype or derived from the results of the software analysis. Several risk scores were calculated, and follow-up data concerning MACE were collected from all patients.

RESULTS

A total of 131 patients (65±12 y, 73% male) were included in our study. MACE occurred in 11 patients within the follow-up period of 34±25 months.CAD-Reporting and Data System score (odds ratio [OR]=11.62), SYNTAX score (SS) (OR=1.11), Leiden-risk score (OR=1.37), segment involvement score (OR=1.76), total plaque volume (OR=1.20), and percentage aggregated plaque volume (OR=1.32) were significant predictors for MACE (all P≤0.05). Moreover, the difference of the corrected coronary opacification (ΔCCO) correlated significantly with the occurrence of MACE (P<0.0001). The CAD-Reporting and Data System score, SS, and Leiden-risk score showed substantial sensitivity for predicting MACE (90.9%). The SS and Leiden-risk score displayed high specificities of 80.8% and 77.5%, respectively. These plaque markers and risk scores all provided high negative predictive value (>90%).

CONCLUSION

The coronary computed tomography angiography-derived plaque markers of segment involvement score, total plaque volume, percentage aggregated plaque volume, and ΔCCO, and the risk scores exhibited predictive value for the occurrence of MACE and can likely aid in identifying patients at risk for future cardiac events.

Diagnostic performance of deep learning-based vascular extraction and stenosis detection technique for coronary artery disease

OBJECTIVE

To investigate the diagnostic performance of deep learning (DL)-based vascular extraction and stenosis detection technology in assessing coronary artery disease (CAD).

METHODS

The diagnostic performance of DL technology was evaluated by retrospective analysis of coronary computed tomography angiography in 124 suspected CAD patients, using invasive coronary angiography as reference standard. Lumen diameter stenosis ≥50% was considered obstructive, and the diagnostic performances were evaluated at per-patient, per-vessel and per-segment levels. The diagnostic performances between DL model and reader model were compared by the areas under the receiver operating characteristics curves (AUCs).

RESULTS

In patient-based analysis, AUC of 0.78 was obtained by DL model to detect obstructive CAD [sensitivity of 94%, specificity of 63%, positive predictive value of 94%, and negative predictive value of 59%], While AUC by reader model was 0.74 (sensitivity of 97%, specificity of 50%, positive predictive value of 93%, negative predictive value of 73%). In vessel-based analysis, the AUCs of DL model and reader model were 0.87 and 0.89 respectively. In segment-based analysis, the AUCs of 0.84 and 0.89 were obtained by DL model and reader model respectively. It took 0.47 min to analyze all segments per patient by DL model, which is significantly less than reader model (29.65 min) (p < 0.001).

CONCLUSION

The DL technology can accurately and effectively identify obstructive CAD, with less time-consuming, and it could be a reliable diagnostic tool to detect CAD.

ADVANCES IN KNOWLEDGE

The DL technology has valuable prospect with the diagnostic ability to detect CAD.

The value of quantified plaque analysis by dual-source coronary CT angiography to detect vulnerable plaques: a comparison study with intravascular ultrasound

Background

To investigate the diagnostic performance of quantified plaque analysis and high-risk plaque characterization by coronary computed tomography angiography (CCTA) for identifying thin-cap fibroatheroma (TCFA).

Methods

Patients who underwent both CCTA and intravascular ultrasound (IVUS) within 4 weeks were retrospectively included. CT-derived quantitative and qualitative parameters, including diameter stenosis, minimal lumen area (MLA), low attenuation plaque (LAP) volume napkin-ring sign (NRS), positive remodeling (PR) and spotty calcification, were recorded. TCFA lesions and non-TCFA lesions were determined by IVUS. Multivariate regression analysis was used to determine the independent predictors of TCFA lesions.

Results

Sixty-five patients (mean age: 69.8±9.2 years, 29 females) with 89 lesions were finally included. LAP and NRS were more frequently presented in the group of TCFA lesions. The mean LAP volume of TCFA lesions was significantly larger than that of non-TCFA lesions [16.5 (11.0-23.0) vs. 0 (0-1.5) mm³, P<0.001]. According to multivariate logistic regression analysis, LAP volume was the only significant predictor for IVUS-confirmed vulnerable plaques (odds ratio =3.294, 95% confidence interval: 1.177-9.223, P=0.023). LAP volume showed largest area under curve (AUC) for diagnosing TCFA lesions (AUC =0.901, 95% confidence interval: 0.819-0.954, P<0.0001). When using >8 mm³ as the best cutoff value, the diagnostic accuracy, sensitivity and specificity of LAP volume for predicting TCFA lesions were 91.0% (81/89), 84.6% (22/26) and 96.8% (61/63) respectively.

Conclusions

CT-derived LAP volume of TCFA lesions was significantly higher than those of non-TCFA lesions. LAP volume was the strongest predictor for TCFA lesions as validated by IVUS.