Coronary CT angiography-derived plaque quantification with artificial intelligence CT fractional flow reserve for the identification of lesion-specific ischemia

Artificial intelligence driven plaque characterization and functional assessment from CCTA using OCT-based automation: A prospective study

BACKGROUND

We aimed to develop and validate an Artificial Intelligence (AI) model that leverages CCTA and optical coherence tomography (OCT) images for automated analysis of plaque characteristics and coronary function.

METHODS

A total of 100 patients who underwent invasive coronary angiography, OCT, and CCTA before discharge were included in this study. The data were randomly divided into a training set (80 %) and a test set (20 %). The training set, comprising 21,471 tomography images, was used to train a deep-learning convolutional neural network. Subsequently, the AI model was integrated with flow reserve score calculation software developed by Ruixin Medical.

RESULTS

The results from the test set demonstrated excellent agreement between the AI model and OCT analysis for calcified plaque (McNemar test, p = 0.683), non-calcified plaque (McNemar test, p = 0.752), mixed plaque (McNemar test, p = 1.000), and low-attenuation plaque (McNemar test, p = 1.000). Additionally, there was excellent agreement for deep learning-derived minimum lumen diameter (intraclass correlation coefficient [ICC] 0.91, p < 0.001), mean vessel diameter (ICC 0.88, p < 0.001), and percent diameter stenosis (ICC 0.82, p < 0.001). In diagnosing >50 % coronary stenosis, the diagnostic accuracy of the AI model surpassed that of conventional CCTA (AUC 0.98 vs. 0.76, p = 0.008). When compared with quantitative flow fraction, there was excellent agreement between QFR and AI-derived CT-FFR (ICC 0.745, p < 0.0001).

CONCLUSION

Our AI model effectively provides automated analysis of plaque characteristics from CCTA images, with the analysis results showing strong agreement with OCT findings. Moreover, the CT-FFR automatically analyzed by the AI model exhibits high consistency with QFR derived from coronary angiography.

Incremental diagnostic value of coronary computed tomography angiography derived fractional flow reserve to detect ischemia

Over the past decade, coronary computed tomographic angiography (CCTA) has been the most robust non-invasive method for evaluating significant coronary stenosis. Thanks to new technologies, it is now possible to determine the fractional flow reserve (FFR) non-invasively using computed tomographic (CT) images. The aim of this work was to evaluate the incremental diagnostic value of CT-derived FFR for ischemia detection. In this retrospective monocentric study, we investigated 421 patients who underwent CCTA and subsequent ischemia testing between 04/2009 and 06/2020. Endpoint was ischemia on a coronary vessel level assessed by CMR (n = 20), SPECT (n = 225), invasive angiography (stenosis ≥ 90%; n = 80) or invasive FFR (positive if ≤ 0.8; n = 96). CT-FFR was derived from CCTA images by a machine learning (ML) based software prototype. Patients averaged 66.5 [58.2-73.6] years of age and 72.7% (n = 306) were male. Overall, 52.5% (n = 221) had hypertension and 67.9% (n = 286) had hypercholesteremia. Logistic regression analysis on a per vessel base showed that the diagnostic model with CT-FFR plus CCTA had significantly better-fit criteria than the diagnostic model with CCTA alone (log-likelihood χ2 230.21 vs. 192.17; p for difference < 0.001). In particular, the area under curve (AUC) by receiver operating characteristics curve (ROC) analysis for CT-FFR plus CCTA (0.87) demonstrated greater discrimination of hemodynamic ischemia compared to CCTA alone (0.83; p for difference < 0.0001). Combined CCTA and CT-FFR have improved diagnostic accuracy compared to CCTA alone in detecting ischemia on the coronary vessel level and thus could reduce the use of invasive coronary angiography in the future.

Clinical Applications of Fractional Flow Reserve Derived from Computed Tomography in Coronary Artery Disease

Computer tomography-derived fractional flow reserve (CT-FFR) represents a significant advancement in noninvasive cardiac functional assessment. This technology uses computer simulation and anatomical information from computer tomography of coronary angiogram to calculate the CT-FFR value at each point within the coronary vasculature. These values serve as a critical reference for cardiologists in making informed treatment decisions and planning. Emerging evidence suggests that CT-FFR has the potential to enhance the specificity of computer tomography of coronary angiogram, thereby reducing the need for additional diagnostic examinations such as invasive coronary angiography and cardiac magnetic resonance imaging. This could result in savings in financial cost, time, and resources for both patients and health care providers. However, it is important to note that although CT-FFR holds great promise, there are limitations to this technology. Users should be cautious of common pitfalls associated with its use. A comprehensive understanding of these limitations is essential for effectively applying CT-FFR in clinical practice.

Artificial Intelligence Applications in Cardiac CT Imaging for Ischemic Disease Assessment

Artificial intelligence (AI) has transformed medical imaging by detecting insights and patterns often imperceptible to the human eye, enhancing diagnostic accuracy and efficiency. In cardiovascular imaging, numerous AI models have been developed for cardiac computed tomography (CCT), a primary tool for assessing coronary artery disease (CAD). CCT provides comprehensive, non-invasive assessment, including plaque burden, stenosis severity, and functional assessments such as CT-derived fractional flow reserve (FFRct). Its prognostic value in predicting major adverse cardiovascular events (MACE) has increased the demand for CCT, consequently adding to radiologists' workloads. This review aims to examine AI's role in CCT for ischemic heart disease, highlighting its potential to streamline workflows and improve the efficiency of cardiac care through machine learning and deep learning applications.

Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review

Background

The use of machine learning (ML) based coronary computed tomography angiography (CCTA) derived fractional flow reserve (ML-FFRCT), shortens the time of diagnosis of ischemia considerably and eliminates unnecessary invasive procedures, when compared to invasive coronary angiography with invasive FFR (iFFR). This systematic review aims to summarize the current evidence on the diagnostic accuracy of (ML-FFRCT) compared with iFFR for diagnosis of patient- and vessel-level coronary ischemia.

Methods

To identify suitable studies, comprehensive literature search was performed in PubMed, the Cochrane Library, Embase, up to August 2023. The index test was ML derived FFR and studies with diagnostic test accuracy data of ML-FFRCT at a threshold of 0.8 were included for the review and meta-analysis. Quality of evidence was assessed using QUADAS-2 checklist.

Results

After full text review of 230 identified studies, 17 were included for analysis, which encompassed 3255 participants (age 62.0 ± 3.7). 8 studies reported patient-level data; and 12, vessel-level data. With iFFR as the reference standard, the pooled patient-level sensitivity, specificity, and area-under-curve (AUC) of ML-FFRCT were 0.86 [95 % CI: 0.79, 0.91], 0.87 [95 % CI: 0.76, 0.94], and 0.92 [95 % CI: 0.89-0.94], respectively; and pooled vessel-level sensitivity, specificity, and AUC, 0.80 [95 % CI: 0.74-0.84], 0.84 [95 % CI: 0.77-0.89), and 0.88 [95 % CI: 0.85-0.91], respectively.

Conclusions

This systemic review demonstrated the favourable diagnostic performance of ML-FFRCT against standard iFFR, although heterogeneity exists, providing support for the use of ML-FFRCT as a triage tool for non-invasive screening of coronary ischemia in the clinical setting.

Exploration of fractional flow reservation score based on artificial intelligence post-processing for coronary artery lesions in patients with diabetes and coronary heart disease

In order to evaluate the relationship between coronary heart disease (CHD) and fractional flow reservation (FFR) in patients with different levels of CHD and diabetes, this paper used AI (artificial intelligence) post-processing technology to detect CHD and FFR. In this paper, 94 patients suspected of CHD who underwent coronary arteriography (CAG) in a hospital between December 2022 and February 2023 were examined by coronary computed tomography angiography (CCTA) and FFR. Based on CCTA, AI software is used to process CCTA images, diagnose coronary plaques, coronary stenosis, corresponding stenosis of different types of plaques, and FFR values. The diagnostic performance of AI was evaluated using expert diagnosis, CAG diagnosis, and FFR examination results as the "gold standard". According to the diagnosis results, the relationship between FFR and CHD patients with diabetes at different levels was studied. The research results showed that AI image diagnosis has high sensitivity, specificity, and accuracy, and has good diagnostic effects on coronary plaques, coronary stenosis, stenosis corresponding to different types of plaques, and FFR values. The fasting blood glucose levels and FFR values of three groups of CHD patients were statistically significant, and correlation analysis revealed a negative correlation between the two. Using AI for CCTA diagnosis can efficiently, conveniently, and accurately obtain the required data, improving clinical diagnostic efficiency and accuracy. The analysis of AI recognition results found that in patients with CHD, the FFR value of patients with diabetes decreased, and the FFR value was negatively correlated with the fasting blood glucose concentration, indicating that CHD patients may lead to myocardial ischemia in the blood supply area due to the decline of their coronary blood flow reserve.

Analysis of the perivascular fat attenuation index and quantitative plaque parameters in relation to haemodynamically impaired myocardial ischaemia

To investigate the correlation between quantitative plaque parameters, the perivascular fat attenuation index, and myocardial ischaemia caused by haemodynamic impairment. Patients with stable angina who had invasive flow reserve fraction (FFR) assessment and coronary artery computed tomography (CT) angiography were retrospectively enrolled. A total of 138 patients were included in this study, which were categorized into the FFR < 0.75 group (n = 43), 0.75 ≤ FFR ≤ 0.8 group (n = 37), and FFR > 0.8 group (n = 58), depending on the range of FFR values. The perivascular FAI and CTA-derived parameters, including plaque length (PL), total plaque volume (TPV), minimum lumen area (MLA), and narrowest degree (ND), were recorded for the lesions. An FFR < 0.75 was defined as myocardial-specific ischaemia. The relationships between myocardial ischaemia and parameters such as the PL, TPV, MLA, ND, and FAI were analysed using a logistic regression model and receiver operating characteristic (ROC) curves to compare the diagnostic accuracy of various indicators for myocardial ischaemia. The PL, TPV, ND, and FAI were greater in the FFR < 0.75 group than in the grey area group and the FFR > 0.80 group (all p < 0.05). The MLA in the FFR < 0.75 group was lower than that in the grey area group and the FFR > 0.80 group (both P < 0.05). There were no significant differences in the PL, TPV, or ND between the grey area and the FFR > 0.80 group, but there was a significant difference in the FAI. The coronary artery lesions with FFRs ≤ 0.75 had the greatest FAI values. Multivariate analysis revealed that the perivascular FAI and PL density are significant predictors of myocardial ischaemia. The FAI has some predictive value for myocardial ischaemia (AUC = 0.781). After building a combination model using the FAI and plaque length, the predictive power increased (AUC, 0.781 vs. 0.918), and the change was statistically significant (P < 0.001). The combined model of PL + FAI demonstrated great diagnostic efficacy in identifying myocardial ischaemia caused by haemodynamic impairment; the lower the FFR was, the greater the FAI. Thus, the PL + FAI could be a combined measure to securely rule out myocardial ischaemia.

Stenosis Detection and Quantification of Coronary Artery Using Machine Learning and Deep Learning

The aim of this review is to introduce some applications of artificial intelligence (AI) algorithms for the detection and quantification of coronary stenosis using computed tomography angiography (CTA). The realization of automatic/semi-automatic stenosis detection and quantification includes the following steps: vessel central axis extraction, vessel segmentation, stenosis detection, and quantification. Many new AI techniques, such as machine learning and deep learning, have been widely used in medical image segmentation and stenosis detection. This review also summarizes the recent progress regarding coronary stenosis detection and quantification, and discusses the development trends in this field. Through evaluation and comparison, researchers can better understand the research frontier in related fields, compare the advantages and disadvantages of various methods, and better optimize the new technologies. Machine learning and deep learning will promote the process of automatic detection and quantification of coronary artery stenosis. However, the machine learning and the deep learning methods need a large amount of data, so they also face some challenges because of the lack of professional image annotations (manually add labels by experts).

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.

Nonobstructive epicardial coronary artery disease: an evolving concept in need of diagnostic and therapeutic guidance

For decades, we have been treating patients presenting with angina and concerning electrocardiographic changes indicative of ischemia or injury, in whom no culprit epicardial coronary stenosis was found during diagnostic coronary angiography. Unfortunately, the clinical outcomes of these patients were not better than those with recognized obstructive coronary disease. Improvements in technology have allowed us to better characterize these patients. Consequently, an increasing number of patients with ischemia and no obstructive coronary artery disease (INOCA) or myocardial infarction in the absence of coronary artery disease (MINOCA) have now gained formal recognition and are more commonly encountered in clinical practice. Although both entities might share functional similarities at their core, they pose significant diagnostic and therapeutic challenges. Unless we become more proficient in identifying these patients, particularly those at higher risk, morbidity and mortality outcomes will not improve. Though this field remains in constant flux, data continue to become available. Therefore, we thought it would be useful to highlight important milestones that have been recognized so we can all learn about these clinical entities. Despite all the progress made regarding INOCA and MINOCA, many important knowledge gaps continue to exist. For the time being, prompt identification and early diagnosis remain crucial in managing these patients. Even though we are still not clear whether intensive medical therapy alters clinical outcomes, we remain vigilant and wait for more data.

Artificial Intelligence in Cardiology and Atherosclerosis in the Context of Precision Medicine: A Scoping Review

Cardiovascular diseases remain the main cause of death worldwide which makes it essential to better understand, diagnose, and treat atherosclerosis. Artificial intelligence (AI) and novel technological solutions offer us new possibilities and enable the practice of individually tailored medicine. The study was performed using the PRISMA protocol. As of January 10, 2023, the analysis has been based on a review of 457 identified articles in PubMed and MEDLINE databases. The search covered reviews, original articles, meta-analyses, comments, and editorials published in the years 2009-2023. In total, 123 articles met inclusion criteria. The results were divided into the subsections presented in the review (genome-wide association studies, radiomics, and other studies). This paper presents actual knowledge concerning atherosclerosis, in silico, and big data analyses in cardiology that affect the way medicine is practiced in order to create an individual approach and adjust the therapy of atherosclerosis.

Imaging biomarkers in cardiac CT: moving beyond simple coronary anatomical assessment

Cardiac computed tomography angiography (CCTA) is considered the standard non-invasive tool to rule-out obstructive coronary artery disease (CAD). Moreover, several imaging biomarkers have been developed on cardiac-CT imaging to assess global CAD severity and atherosclerotic burden, including coronary calcium scoring, the segment involvement score, segment stenosis score and the Leaman-score. Myocardial perfusion imaging enables the diagnosis of myocardial ischemia and microvascular damage, and the CT-based fractional flow reserve quantification allows to evaluate non-invasively hemodynamic impact of the coronary stenosis. The texture and density of the epicardial and perivascular adipose tissue, the hypodense plaque burden, the radiomic phenotyping of coronary plaques or the fat radiomic profile are novel CT imaging features emerging as biomarkers of inflammation and plaque instability, which may implement the risk stratification strategies. The ability to perform myocardial tissue characterization by extracellular volume fraction and radiomic features appears promising in predicting arrhythmogenic risk and cardiovascular events. New imaging biomarkers are expanding the potential of cardiac CT for phenotyping the individual profile of CAD involvement and opening new frontiers for the practice of more personalized medicine.

Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries

Artificial intelligence (AI) is likely to revolutionize the way medical images are analysed and has the potential to improve the identification and analysis of vulnerable or high-risk atherosclerotic plaques in coronary arteries, leading to advances in the treatment of coronary artery disease. However, coronary plaque analysis is challenging owing to cardiac and respiratory motion, as well as the small size of cardiovascular structures. Moreover, the analysis of coronary imaging data is time-consuming, can be performed only by clinicians with dedicated cardiovascular imaging training, and is subject to considerable interreader and intrareader variability. AI has the potential to improve the assessment of images of vulnerable plaque in coronary arteries, but requires robust development, testing and validation. Combining human expertise with AI might facilitate the reliable and valid interpretation of images obtained using CT, MRI, PET, intravascular ultrasonography and optical coherence tomography. In this Roadmap, we review existing evidence on the application of AI to the imaging of vulnerable plaque in coronary arteries and provide consensus recommendations developed by an interdisciplinary group of experts on AI and non-invasive and invasive coronary imaging. We also outline future requirements of AI technology to address bias, uncertainty, explainability and generalizability, which are all essential for the acceptance of AI and its clinical utility in handling the anticipated growing volume of coronary imaging procedures.

Diagnostic Puzzles and Cause-Targeted Treatment Strategies in Myocardial Infarction with Non-Obstructive Coronary Arteries: An Updated Review

Myocardial infarction with nonobstructive coronary arteries (MINOCA) is a distinct subtype of myocardial infarction (MI), occurring in about 8-10% of spontaneous MI cases referred for coronary angiography. Unlike MI with obstructive coronary artery disease, MINOCA's pathogenesis is more intricate and heterogeneous, involving mechanisms such as coronary thromboembolism, coronary vasospasm, microvascular dysfunction, dissection, or plaque rupture. Diagnosing MINOCA presents challenges and includes invasive and non-invasive strategies aiming to differentiate it from alternative diagnoses and confirm the criteria of elevated cardiac biomarkers, non-obstructive coronary arteries, and the absence of alternate explanations for the acute presentation. Tailored management strategies for MINOCA hinge on identifying the underlying cause of the infarction, necessitating systematic diagnostic approaches. Furthermore, determining the optimal post-MINOCA medication regimen remains uncertain. This review aims to comprehensively address the current state of knowledge, encompassing diagnostic and therapeutic approaches, in the context of MINOCA while also highlighting the evolving landscape and future directions for advancing our understanding and management of this intricate myocardial infarction subtype.

Comparison of CT-derived Plaque Characteristic Index With CMR Perfusion for Ischemia Diagnosis in Stable CAD

BACKGROUND

Coronary computed tomography angiography (CCTA) and cardiac magnetic resonance (CMR) have been used to diagnose lesion-specific ischemia in patients with coronary artery disease. The aim of this study was to investigate the diagnostic performance of CCTA-derived plaque characteristic index compared with myocardial blood flow (MBF) and myocardial perfusion reserve (MPR) derived from CMR perfusion in the assessment of lesion-specific ischemia.

METHODS

Between October 2020 and March 2022, consecutive patients with suspected or known coronary artery disease, who were clinically referred for invasive coronary angiography were prospectively enrolled. All participants sequentially underwent CCTA and CMR and invasive fractional flow reserve within 2 weeks. The diagnostic performance of CCTA-derived plaque characteristics, CMR perfusion-derived stress MBF, and MPR were compared. Lesions with fractional flow reserve ≤0.80 were considered to be hemodynamically significant stenosis.

RESULTS

Nighty-two patients with 141 vessels were included in this study. Plaque length, minimum luminal area, plaque area, percent area stenosis, total atheroma volume, vessel volume, lipid-rich volume, spotty calcium, napkin-ring signs, stress MBF, and MPR in flow-limiting stenosis group were significantly different from nonflow-limiting group. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of lesion-specific ischemia diagnosis were 61.0%, 55.3%, 63.1%, 35.6%, and 79.3% for stress MBF, and 89.4%, 89.5%, 89.3%, 75.6%, 95.8% for MPR; meanwhile, 82.3%, 79.0%, 84.5%, 65.2%, and 91.6% for CCTA-derived plaque characteristic index.

CONCLUSIONS

In our prospective study, CCTA-derived plaque characteristics and MPR derived from CMR performed well in diagnosing lesion-specific myocardial ischemia and were significantly better than stress MBF in stable coronary artery disease.

P-Selectin mediates targeting of a self-assembling phototherapeutic nanovehicle enclosing dipyridamole for managing thromboses

Thrombotic vascular disorders, specifically thromboembolisms, have a significant detrimental effect on public health. Despite the numerous thrombolytic and antithrombotic drugs available, their efficacy in penetrating thrombus formations is limited, and they carry a high risk of promoting bleeding. Consequently, the current medication dosage protocols are inadequate for preventing thrombus formation, and higher doses are necessary to achieve sufficient prevention. By integrating phototherapy with antithrombotic therapy, this study addresses difficulties related to thrombus-targeted drug delivery. We developed self-assembling nanoparticles (NPs) through the optimization of a co-assembly engineering process. These NPs, called DIP-FU-PPy NPs, consist of polypyrrole (PPy), dipyridamole (DIP), and P-selectin-targeted fucoidan (FU) and are designed to be delivered directly to thrombi. DIP-FU-PPy NPs are proposed to offer various potentials, encompassing drug-loading capability, targeted accumulation in thrombus sites, near-infrared (NIR) photothermal-enhanced thrombus management with therapeutic efficacy, and prevention of rethrombosis. As predicted, DIP-FU-PPy NPs prevented thrombus recurrence and emitted visible fluorescence signals during thrombus clot penetration with no adverse effects. Our co-delivery nano-platform is a simple and versatile solution for NIR-phototherapeutic multimodal thrombus control.

Accuracy of intravascular ultrasound-derived virtual fractional flow reserve (FFR) and FFR derived from computed tomography for functional assessment of coronary artery disease

BACKGROUND

Coronary computed tomography-derived fractional flow reserve (CT-FFR) and intravascular ultrasound-derived fractional flow reserve (IVUS-FFR) are two functional assessment methods for coronary stenoses. However, the calculation algorithms for these methods differ significantly. This study aimed to compare the diagnostic performance of CT-FFR and IVUS-FFR using invasive fractional flow reserve (FFR) as the reference standard.

METHODS

Six hundred and seventy patients (698 lesions) with known or suspected coronary artery disease were screened for this retrospective analysis between January 2020 and July 2021. A total of 40 patients (41 lesions) underwent intravascular ultrasound (IVUS) and FFR evaluations within six months after completing coronary CT angiography were included. Two novel CFD-based models (AccuFFRct and AccuFFRivus) were used to compute the CT-FFR and IVUS-FFR values, respectively. The invasive FFR ≤ 0.80 was used as the reference standard for evaluating the diagnostic performance of CT-FFR and IVUS-FFR.

RESULTS

Both AccuFFRivus and AccuFFRct demonstrated a strong correlation with invasive FFR (R = 0.7913, P < 0.0001; and R = 0.6296, P < 0.0001), and both methods showed good agreement with FFR. The area under the receiver operating characteristic curve was 0.960 (P < 0.001) for AccuFFRivus and 0.897 (P < 0.001) for AccuFFRct in predicting FFR ≤ 0.80. FFR ≤ 0.80 were predicted with high sensitivity (96.6%), specificity (85.7%), and the Youden index (0.823) using the same cutoff value of 0.80 for AccuFFRivus. A good diagnostic performance (sensitivity 89.7%, specificity 85.7%, and Youden index 0.754) was also demonstrated by AccuFFRct.

CONCLUSIONS

AccuFFRivus, computed from IVUS images, exhibited a high diagnostic performance for detecting myocardial ischemia. It demonstrated better diagnostic power than AccuFFRct, and could serve as an accurate computational tool for ischemia diagnosis and assist in clinical decision-making.

Does Coronary Plaque Morphology Matter Beyond Plaque Burden?

PURPOSE OF REVIEW

Imaging of adverse coronary plaque features by coronary computed tomography angiography (CCTA) has advanced greatly and at a fast pace. We aim to describe the evolution, present and future in plaque analysis, and its value in comparison to plaque burden.

RECENT FINDINGS

Recently, it has been demonstrated that in addition to plaque burden, quantitative and qualitative assessment of coronary plaque by CCTA can improve the prediction of future major adverse cardiovascular events in diverse coronary artery disease scenarios. The detection of high-risk non-obstructive coronary plaque can lead to higher use of preventive medical therapies such as statins and aspirin, help identify culprit plaque, and differentiate between myocardial infarction types. Even more, over traditional plaque burden, plaque analysis including pericoronary inflammation can potentially be useful tools for tracking disease progression and response to medical therapy. The identification of the higher risk phenotypes with plaque burden, plaque characteristics, or ideally both can allow the allocation of targeted therapies and potentially monitor response. Further observational data are now required to investigate these key issues in diverse populations, followed by rigorous randomized controlled trials.

Diagnostic performance of deep learning-based vessel extraction and stenosis detection on coronary computed tomography angiography for coronary artery disease: a multi-reader multi-case study

BACKGROUND

Post-processing and interpretation of coronary CT angiography (CCTA) imaging are time-consuming and dependent on the reader's experience. An automated deep learning (DL)-based imaging reconstruction and diagnosis system was developed to improve diagnostic accuracy and efficiency.

METHODS

Our study including 374 cases from five sites, inviting 12 radiologists, assessed the DL-based system in diagnosing obstructive coronary disease with regard to diagnostic performance, imaging post-processing and reporting time of radiologists, with invasive coronary angiography as a standard reference. The diagnostic performance of DL system and DL-assisted human readers was compared with the traditional method of human readers without DL system.

RESULTS

Comparing the diagnostic performance of human readers without DL system versus with DL system, the AUC was improved from 0.81 to 0.82 (p < 0.05) at patient level and from 0.79 to 0.81 (p < 0.05) at vessel level. An increase in AUC was observed in inexperienced radiologists (p < 0.05), but was absent in experienced radiologists. Regarding diagnostic efficiency, comparing the DL system versus human reader, the average post-processing and reporting time was decreased from 798.60 s to 189.12 s (p < 0.05). The sensitivity and specificity of using DL system alone were 93.55% and 59.57% at patient level and 83.23% and 79.97% at vessel level, respectively.

CONCLUSIONS

With the DL system serving as a concurrent reader, the overall post-processing and reading time was substantially reduced. The diagnostic accuracy of human readers, especially for inexperienced readers, was improved. DL-assisted human reader had the potential of being the reading mode of choice in clinical routine.

The Cost Effectiveness of Coronary CT Angiography and the Effective Utilization of CT-Fractional Flow Reserve in the Diagnosis of Coronary Artery Disease

Given the high global disease burden of coronary artery disease (CAD), a major problem facing healthcare economic policy is identifying the most cost-effective diagnostic strategy for patients with suspected CAD. The aim of this review is to assess the long-term cost-effectiveness of coronary computed tomography angiography (CCTA) when compared with other diagnostic modalities and to define the cost and effective diagnostic utilization of computed tomography-fractional flow reserve (CT-FFR). A search was conducted through the MEDLINE database using PubMed with 16 of 119 manuscripts fitting the inclusion and exclusion criteria for review. An analysis of the data included in this review suggests that CCTA is a cost-effective strategy for both low risk acute chest pain patients presenting to the emergency department (ED) and low-to-intermediate risk stable chest pain outpatients. For patients with intermediate-to-high risk, CT-FFR is superior to CCTA in identifying clinically significant stenosis. In low-to-intermediate risk patients, CCTA provides a cost-effective diagnostic strategy with the potential to reduce economic burden and improve long-term health outcomes. CT-FFR should be utilized in intermediate-to-high risk patients with stenosis of uncertain clinical significance. Long-term analysis of cost-effectiveness and diagnostic utility is needed to determine the optimal balance between the cost-effectiveness and diagnostic utility of CT-FFR.

Deep learning-based detection of functionally significant stenosis in coronary CT angiography

Patients with intermediate anatomical degree of coronary artery stenosis require determination of its functional significance. Currently, the reference standard for determining the functional significance of a stenosis is invasive measurement of the fractional flow reserve (FFR), which is associated with high cost and patient burden. To address these drawbacks, FFR can be predicted non-invasively from a coronary CT angiography (CCTA) scan. Hence, we propose a deep learning method for predicting the invasively measured FFR of an artery using a CCTA scan. The study includes CCTA scans of 569 patients from three hospitals. As reference for the functional significance of stenosis, FFR was measured in 514 arteries in 369 patients, and in the remaining 200 patients, obstructive coronary artery disease was ruled out by Coronary Artery Disease-Reporting and Data System (CAD-RADS) category 0 or 1. For prediction, the coronary tree is first extracted and used to reconstruct an MPR for the artery at hand. Thereafter, the coronary artery is characterized by its lumen, its attenuation and the area of the coronary artery calcium in each artery cross-section extracted from the MPR using a CNN. Additionally, characteristics indicating the presence of bifurcations and information indicating whether the artery is a main branch or a side-branch of a main artery are derived from the coronary artery tree. All characteristics are fed to a second network that predicts the FFR value and classifies the presence of functionally significant stenosis. The final result is obtained by merging the two predictions. Performance of our method is evaluated on held out test sets from multiple centers and vendors. The method achieves an area under the receiver operating characteristics curve (AUC) of 0.78, outperforming other works that do not require manual correction of the segmentation of the artery. This demonstrates that our method may reduce the number of patients that unnecessarily undergo invasive measurements.

Application of AI in cardiovascular multimodality imaging

Technical advances in artificial intelligence (AI) in cardiac imaging are rapidly improving the reproducibility of this approach and the possibility to reduce time necessary to generate a report. In cardiac computed tomography angiography (CCTA) the main application of AI in clinical practice is focused on detection of stenosis, characterization of coronary plaques, and detection of myocardial ischemia. In cardiac magnetic resonance (CMR) the application of AI is focused on post-processing and particularly on the segmentation of cardiac chambers during late gadolinium enhancement. In echocardiography, the application of AI is focused on segmentation of cardiac chambers and is helpful for valvular function and wall motion abnormalities. The common thread represented by all of these techniques aims to shorten the time of interpretation without loss of information compared to the standard approach. In this review we provide an overview of AI applications in multimodality cardiac imaging.

Using artificial intelligence in the development of diagnostic models of coronary artery disease with imaging markers: A scoping review

Background

Coronary artery disease (CAD) is a progressive disease of the blood vessels supplying the heart, which leads to coronary artery stenosis or obstruction and is life-threatening. Early diagnosis of CAD is essential for timely intervention. Imaging tests are widely used in diagnosing CAD, and artificial intelligence (AI) technology is used to shed light on the development of new imaging diagnostic markers.

Objective

We aim to investigate and summarize how AI algorithms are used in the development of diagnostic models of CAD with imaging markers.

Methods

This scoping review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guideline. Eligible articles were searched in PubMed and Embase. Based on the predefined included criteria, articles on coronary heart disease were selected for this scoping review. Data extraction was independently conducted by two reviewers, and a narrative synthesis approach was used in the analysis.

Results

A total of 46 articles were included in the scoping review. The most common types of imaging methods complemented by AI included single-photon emission computed tomography (15/46, 32.6%) and coronary computed tomography angiography (15/46, 32.6%). Deep learning (DL) (41/46, 89.2%) algorithms were used more often than machine learning algorithms (5/46, 10.8%). The models yielded good model performance in terms of accuracy, sensitivity, specificity, and AUC. However, most of the primary studies used a relatively small sample (n < 500) in model development, and only few studies (4/46, 8.7%) carried out external validation of the AI model.

Conclusion

As non-invasive diagnostic methods, imaging markers integrated with AI have exhibited considerable potential in the diagnosis of CAD. External validation of model performance and evaluation of clinical use aid in the confirmation of the added value of markers in practice.

Systematic review registration

[https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022306638], identifier [CRD42022306638].

Automated Identification of Coronary Arteries in Assisting Inexperienced Readers: Comparison between Two Commercial Vendors

Background: to assess the performance and speed of two commercially available advanced cardiac software packages in the automated identification of coronary vessels as an aiding tool for inexperienced readers. Methods: Hundred and sixty patients undergoing coronary CT angiography (CCTA) were prospectively enrolled from February until September 2021 and randomized in two groups, each one composed by 80 patients. Patients in group 1 were scanned on Revolution EVO CT Scanner (GE Healthcare), while patients in group 2 had the CCTA performed on Brilliance iCT (Philips Healthcare); each examination was evaluated on the respective vendor proprietary advanced cardiac software (software 1 and 2, respectively). Two inexperienced readers in cardiac imaging verified the software performance in the automated identification of the three major coronary vessels: (RCA, LCx, and LAD) and in the number of identified coronary segments. Time of analysis was also recorded. Results: software 1 correctly and automatically nominated 202/240 (84.2%) of the three main coronary vessels, while software 2 correctly identified 191/240 (79.6%) (p = 0.191). Software 1 achieved greater performances in recognizing the LCx (81.2% versus 67.5%; p = 0.048), while no differences have been reported in detecting the RCA (p = 0.679), and the LAD (p = 0.618). On a per-segment analysis, software 1 outperformed software 2, automatically detecting 942/1062 (88.7%) coronary segments, while software 2 detected 797/1078 (73.9%) (p < 0.001). Average reconstruction and detection time was of 13.8 s for software 1 and 21.9 s for software 2 (p < 0.001). Conclusions: automated cardiac software packages are a reliable and time-saving tool for inexperienced reader. Software 1 outperforms software 2 and might therefore better assist inexperienced CCTA readers in automated identification of the three main vessels and coronaries segments, with a consistent time saving of the reading session.

Clinical Evaluation of the Automatic Coronary Artery Disease Reporting and Data System (CAD-RADS) in Coronary Computed Tomography Angiography Using Convolutional Neural Networks

RATIONALE AND OBJECTIVES

The coronary artery disease reporting and data system (CAD-RADS™) was recently introduced to standardise reporting. We aimed to evaluate the utility of an automatic postprocessing and reporting system based on CAD-RADS™ in suspected coronary artery disease (CAD) patients.

MATERIALS AND METHODS

Clinical evaluation was performed in 346 patients who underwent coronary computed tomography angiography (CCTA). We compared deep learning (DL)-based CCTA with human readers for evaluation of CAD-RADS™ with commercially-available automated segmentation and manual postprocessing in a retrospective validation cohort.

RESULTS

Compared with invasive coronary angiography, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the DL model for diagnosis of CAD were 79.02%, 86.52%, 89.50%, 73.94%, and 82.08%, respectively. There was no significant difference between the DL-based and the reader-based CAD-RADS™ grading of CCTA results. Consistency testing showed that the Kappa value between the model and the readers was 0.775 (95% confidence interval [CI]: 0.728-0.823, p < 0.001), 0.802 (95% CI: 0.756-0.847, p < 0.001), and 0.796 (95% CI: 0.750-0.843, p < 0.001), respectively. This system reduces the time taken from 14.97 ± 1.80 min to 5.02 ± 0.8 min (p < 0.001).

CONCLUSION

The standardised reporting of DL-based CAD-RADS™ in CCTA can accurately and rapidly evaluate suspected CAD patients, and has good consistency with grading by radiologists.

Optimization of FFR prediction algorithm for gray zone by hemodynamic features with synthetic model and biometric data

BACKGROUND

Recent attempts on adopting artificial intelligence algorithm on coronary diagnosis had limitations on data quantity and quality. While most of previous studies only used vessel image as input data, flow features and biometric features should be also considered. Moreover, the accuracy should be optimized within gray zone as the purpose is to decide stent insertion with estimated fractional flow reserve.

OBJECTIVES

The main purpose of this study is to develop an artificial intelligence-based coronary vascular diagnosis system focused on performance in the gray zone, from CT image extraction to FFR estimation. Three main issues should be considered for an algorithm to be used for pre-screening: algorithm optimization in the gray zone, minimization of labor during image processing, and consideration of flow and biometric features. This paper introduces a full FFR pre-screening system from automatic image extraction to an algorithm for estimating the FFR value.

METHOD

The main techniques used in this study are an automatic image extraction algorithm, lattice Boltzmann method based computational fluid dynamics analysis of a synthetic model and patient data, and an AI algorithm optimization. For feature extraction, this study focused on an automatic process to reduce manual labor. The algorithm consisted of two steps: the first algorithm calculates flow features from geometrical features, and the second algorithm estimates the FFR value from flow features and patient biometric features. Algorithm selection, outlier elimination, and k-fold selection were included to optimize the algorithm.

CONCLUSION

Eight types of algorithms including two neural network models and six machine learning models were optimized and tested. The random forest model shows the highest performance before optimization, whereas the multilayer perceptron regressor shows the highest gray zone accuracy after optimization.

Research Progress of Machine Learning and Deep Learning in Intelligent Diagnosis of the Coronary Atherosclerotic Heart Disease

The coronary atherosclerotic heart disease is a common cardiovascular disease with high morbidity, disability, and societal burden. Early, precise, and comprehensive diagnosis of the coronary atherosclerotic heart disease is of great significance. The rise of artificial intelligence technologies, represented by machine learning and deep learning, provides new methods to address the above issues. In recent years, artificial intelligence has achieved an extraordinary progress in multiple aspects of coronary atherosclerotic heart disease diagnosis, including the construction of intelligent diagnostic models based on artificial intelligence algorithms, applications of artificial intelligence algorithms in coronary angiography, coronary CT angiography, intravascular imaging, cardiac magnetic resonance, and functional parameters. This paper presents a comprehensive review of the technical background and current state of research on the application of artificial intelligence in the diagnosis of the coronary atherosclerotic heart disease and analyzes recent challenges and perspectives in this field.

Diagnostic Performance of CT FFR With a New Parameter Optimized Computational Fluid Dynamics Algorithm From the CT-FFR-CHINA Trial: Characteristic Analysis of Gray Zone Lesions and Misdiagnosed Lesions

To assess the diagnostic performance of fractional flow reserve (FFR) derived from coronary computed tomography angiography (CTA) (CT-FFR) obtained by a new computational fluid dynamics (CFD) algorithm to detect ischemia, using FFR as a reference, and analyze the characteristics of “gray zone” and misdiagnosed lesions. This prospective multicenter clinical trial (NCT03692936, https://clinicaltrials.gov/) analyzed 317 patients with coronary stenosis between 30 and 90% in 366 vessels from five centers undergoing CTA and FFR between November 2018 and March 2020. CT-FFR were obtained from a CFD algorithm (Heartcentury Co., Ltd., Beijing, China). Diagnostic performance of CT-FFR and CTA in detecting ischemia was assessed. Coronary atherosclerosis characteristics of gray zone and misdiagnosed lesions were analyzed. Per-vessel sensitivity, specificity and accuracy for CT-FFR and CTA were 89.9, 87.8, 88.8% and 89.3, 35.5, 60.4%, respectively. Accuracy of CT-FFR was 80.0% in gray zone lesions. In gray zone lesions, lumen area and diameter were significantly larger than lesions with FFR < 0.76 (both p < 0.001), lesion length, non-calcified and calcified plaque volume were all significantly higher than non-ischemic lesions (all p < 0.05). In gray zone lesions, Agatston score (OR = 1.009, p = 0.044) was the risk factor of false negative results of CT-FFR. In non-ischemia lesions, coronary stenosis >50% (OR = 2.684, p = 0.03) was the risk factor of false positive results. Lumen area (OR = 0.567, p = 0.02) and diameter (OR = 0.296, p = 0.03) had a significant negative effect on the risk of false positive results of CT-FFR. In conclusion, CT-FFR based on the new parameter-optimized CFD model provides better diagnostic performance for lesion-specific ischemia than CTA. For gray zone lesions, stenosis degree was less than those with FFR < 0.76, and plaque load was heavier than non-ischemic lesions.

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.

Role of cardiac CT in the diagnostic evaluation and risk stratification of patients with myocardial infarction and non-obstructive coronary arteries (MINOCA): rationale and design of the MINOCA-GR study

INTRODUCTION

Myocardial infarction with non-obstructive coronary arteries (MINOCA) occurs in 5%-15% of all patients with acute myocardial infarction. Cardiac MR (CMR) and optical coherence tomography have been used to identify the underlying pathophysiological mechanism in MINOCA. The role of cardiac CT angiography (CCTA) in patients with MINOCA, however, has not been well studied so far. CCTA can be used to assess atherosclerotic plaque volume, vulnerable plaque characteristics as well as pericoronary fat tissue attenuation, which has not been yet studied in MINOCA.

METHODS AND ANALYSIS

MINOCA-GR is a prospective, multicentre, observational cohort study based on a national registry that will use CCTA in combination with CMR and invasive coronary angiography (ICA) to evaluate the extent and characteristics of coronary atherosclerosis and its correlation with pericoronary fat attenuation in patients with MINOCA. A total of 60 consecutive adult patients across 4 participating study sites are expected to be enrolled. Following ICA and CMR, patients will undergo CCTA during index hospitalisation. The primary endpoints are quantification of extent and severity of coronary atherosclerosis, description of high-risk plaque features and attenuation profiling of pericoronary fat tissue around all three major epicardial coronary arteries in relation to CMR. Follow-up CCTA for the evaluation of changes in pericoronary fat attenuation will also be performed. MINOCA-GR aims to be the first study to explore the role of CCTA in combination with CMR and ICA in the underlying pathophysiological mechanisms and assisting in diagnostic evaluation and prognosis of patients with MINOCA.

ETHICS AND DISSEMINATION

The study protocol has been approved by the institutional review board/independent ethics committee at each site prior to study commencement. All patients will provide written informed consent. Results will be disseminated at national meetings and published in peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NCT4186676.

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

Additive value of epicardial adipose tissue quantification to coronary CT angiography-derived plaque characterization and CT fractional flow reserve for the prediction of lesion-specific ischemia

OBJECTIVES

Epicardial adipose tissue (EAT) from coronary CT angiography (CCTA) is strongly associated with coronary artery disease (CAD). We investigated the additive value of EAT volume to coronary plaque quantification and CT-derived fractional flow reserve (CT-FFR) to predict lesion-specific ischemia.

METHODS

Patients (n = 128, 60.6 ± 10.5 years, 61% male) with suspected CAD who had undergone invasive coronary angiography (ICA) and CCTA were retrospectively analyzed. EAT volume and plaque measures were derived from CCTA using a semi-automatic software approach, while CT-FFR was calculated using a machine learning algorithm. The predictive value and discriminatory power of EAT volume, plaque measures, and CT-FFR to identify ischemic CAD were assessed using invasive FFR as the reference standard.

RESULTS

Fifty-five of 152 lesions showed ischemic CAD by invasive FFR. EAT volume, CCTA ≥ 50% stenosis, and CT-FFR were significantly different in lesions with and without hemodynamic significance (all p < 0.05). Multivariate analysis revealed predictive value for lesion-specific ischemia of these parameters: EAT volume (OR 2.93, p = 0.021), CCTA ≥ 50% (OR 4.56, p = 0.002), and CT-FFR (OR 6.74, p < 0.001). ROC analysis demonstrated incremental discriminatory value with the addition of EAT volume to plaque measures alone (AUC 0.84 vs. 0.62, p < 0.05). CT-FFR (AUC 0.89) showed slightly superior performance over EAT volume with plaque measures (AUC 0.84), however without significant difference (p > 0.05).

CONCLUSIONS

EAT volume is significantly associated with ischemic CAD. The combination of EAT volume with plaque quantification demonstrates a predictive value for lesion-specific ischemia similar to that of CT-FFR. Thus, EAT may aid in the identification of hemodynamically significant coronary stenosis.

KEY POINTS

• CT-derived EAT volume quantification demonstrates high discriminatory power to identify lesion-specific ischemia. • EAT volume shows incremental diagnostic performance over CCTA-derived plaque measures in detecting lesion-specific ischemia. • A combination of plaque measures with EAT volume provides a similar discriminatory value for detecting lesion-specific ischemia compared to CT-FFR.

Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review

The risk of coronary heart disease (CHD) clinical manifestations and patient management is estimated according to risk scores accounting multifactorial risk factors, thus failing to cover the individual cardiovascular risk. Technological improvements in the field of medical imaging, in particular, in cardiac computed tomography angiography and cardiac magnetic resonance protocols, laid the development of radiogenomics. Radiogenomics aims to integrate a huge number of imaging features and molecular profiles to identify optimal radiomic/biomarker signatures. In addition, supervised and unsupervised artificial intelligence algorithms have the potential to combine different layers of data (imaging parameters and features, clinical variables and biomarkers) and elaborate complex and specific CHD risk models allowing more accurate diagnosis and reliable prognosis prediction. Literature from the past 5 years was systematically collected from PubMed and Scopus databases, and 60 studies were selected. We speculated the applicability of radiogenomics and artificial intelligence through the application of machine learning algorithms to identify CHD and characterize atherosclerotic lesions and myocardial abnormalities. Radiomic features extracted by cardiac computed tomography angiography and cardiac magnetic resonance showed good diagnostic accuracy for the identification of coronary plaques and myocardium structure; on the other hand, few studies exploited radiogenomics integration, thus suggesting further research efforts in this field. Cardiac computed tomography angiography resulted the most used noninvasive imaging modality for artificial intelligence applications. Several studies provided high performance for CHD diagnosis, classification, and prognostic assessment even though several efforts are still needed to validate and standardize algorithms for CHD patient routine according to good medical practice.

Computed Tomography Coronary Plaque Characteristics Predict Ischemia Detected by Invasive Fractional Flow Reserve

PURPOSE

Coronary computed tomography angiography (CCTA) plaque quantification has been proposed to be of incremental value in the prediction of ischemia, although prior studies have shown conflicting results. We aimed to determine whether CCTA plaque features assessed on a commercial vendor platform predict invasive fractional flow reserve (FFR)/instantaneous wave-free ratio (IFR).

METHODS

Consecutive patients who underwent CCTA for evaluation of suspected stable coronary artery disease followed by invasive coronary physiology testing within 60 days at a single academic center were identified retrospectively. Semiautomated plaque quantification of the vessel proximal to the location of FFR/IFR measurement was carried out in TeraRecon, along with simple visual assessment for high-risk plaque features of positive remodeling, spotty calcification, low-attenuation plaque (LAP), and lesion length. Ischemia was defined by FFR ≤0.80 or IFR ≤0.89.

RESULTS

A total of 134 patients (62% male, mean age 62±10 y) were included in this study. On univariate logistic regression, the following visual plaque analysis parameters were predictive of ischemia: positive remodeling (odds ratio [OR] with 95% confidence interval [CI]: 4.96; 2.25-10.95; P<0.001), lesion length (OR for every 1 mm with 95% CI: 1.24; 1.14-1.34; P<0.001), spotty calcification (OR with 95% CI: 6.67; 1.67-26.64; P=0.007), and LAP (OR with 95% CI: 30; 3.78-246; P=0.001). None of the semiautomated plaque quantification parameters, such as noncalcified plaque volume or LAP volume, were predictive of ischemia. On stepwise multivariable logistic regression, lesion length (OR with 95% CI: 1.25; 1.14-1.37; P<0.0001) and LAP (OR with 95% CI: 43; 4.4-438; P=0.001) were significant predictors of ischemia, improving the area under the curve of CCTA from 0.53 to 0.87.

CONCLUSIONS

Simple visual plaque assessment for high-risk plaque features improved the performance of CCTA to predict ischemia. Semiautomated plaque quantification performed on a commercial vendor platform was not predictive of ischemia.

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.

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.

Deep learning powered coronary CT angiography for detecting obstructive coronary artery disease: The effect of reader experience, calcification and image quality

OBJECTIVES

To investigate the effect of reader experience, calcification and image quality on the performance of deep learning (DL) powered coronary CT angiography (CCTA) in automatically detecting obstructive coronary artery disease (CAD) with invasive coronary angiography (ICA) as reference standard.

METHODS

A total of 165 patients (680 vessels and 1505 segments) were included in this study. Three sessions were performed in order: (1) The artificial intelligence (AI) software automatically processed CCTA images, stenosis degree and processing time were recorded for each case; (2) Six cardiovascular radiologists with different experiences (low/ intermediate/ high experience) independently performed image post-processing and interpretation of CCTA, (3) AI + human reading was performed. Luminal stenosis ≥50% was defined as obstructive CAD in ICA and CCTA. Diagnostic performances of AI, human reading and AI + human reading were evaluated and compared on a per-patient, per-vessel and per-segment basis with ICA as reference standard. The effects of calcification and image quality on the diagnostic performance were also studied.

RESULTS

The average post-processing and interpretation times of AI was 2.3 ± 0.6 min per case, reduced by 76%, 72%, 69% compared with low/ intermediate/ high experience readers (all P < 0.001), respectively. On a per-patient, per-vessel and per-segment basis, with ICA as reference method, the AI overall diagnostic sensitivity for detecting obstructive CAD were 90.5%, 81.4%, 72.9%, the specificity was 82.3%, 93.9%, 95.0%, with the corresponding areas under the curve (AUCs) of 0.90, 0.90, 0.87, respectively. Compared to human readers, the diagnostic performance of AI was higher than that of low experience readers (all P < 0.001). The diagnostic performance of AI + human reading was higher than human reading alone, and AI + human readers' ability to correctly reclassify obstructive CAD was also improved, especially for low experience readers (Per-patient, the net reclassification improvement (NRI) = 0.085; per-vessel, NRI = 0.070; and per-segment, NRI = 0.068, all P < 0.001). The diagnostic performance of AI was not significantly affected by calcification and image quality (all P > 0.05).

CONCLUSIONS

AI can substantially shorten the post-processing time, while AI + human reading model can significantly improve the diagnostic performance compared with human readers, especially for inexperienced readers, regardless of calcification severity and image quality.

Artificial intelligence in personalized cardiovascular medicine and cardiovascular imaging

The collection of large, heterogeneous electronic datasets and imaging from patients with cardiovascular disease (CVD) has lent itself to the use of sophisticated analysis using artificial intelligence (AI). AI techniques such as machine learning (ML) are able to identify relationships between data points by linking input to output variables using a combination of different functions, such as neural networks. In cardiovascular medicine, this is especially pertinent for classification, diagnosis, risk prediction and treatment guidance. Common cardiovascular data sources from patients include genomic data, cardiovascular imaging, wearable sensors and electronic health records (EHR). Leveraging AI in analysing such data points: (I) for clinicians: more accurate and streamlined image interpretation and diagnosis; (II) for health systems: improved workflow and reductions in medical errors; (III) for patients: promoting health with further education and promoting primary and secondary cardiovascular health prevention. This review addresses the need for AI in cardiovascular medicine by reviewing recent literature in different cardiovascular imaging modalities: electrocardiography, echocardiography, cardiac computed tomography, cardiac nuclear imaging, and cardiac magnetic resonance (CMR) imaging as well as the role of EHR. This review aims to conceptulise these studies in relation to their clinical applications, potential limitations and future opportunities and directions.

Radiomic features of plaques derived from coronary CT angiography to identify hemodynamically significant coronary stenosis, using invasive FFR as the reference standard

OBJECTIVE

This study aimed to investigate the diagnostic performance of radiomics features derived from coronary computed tomography angiography (CCTA) in the identification of ischemic coronary stenosis plaque using invasive fractional flow reserve (FFR) as the reference standard.

MATERIALS AND METHODS

174 plaques of 149 patients (age: 62.21 ± 8.47 years, 96 males) with at least one lesion stenosis degree between 30 % and 90 % were retrospectively included. Stenosis degree and plaque characteristics were recorded, and a conventional multivariate logistic model was established. Over 1000 radiomics features of the plaque were derived from CCTA images. The plaques were randomly divided into training set (n = 139) and validation set (n = 35). A random forest model was built. The area under the curve (AUC) of the models was compared.

RESULTS

Fifty-eight radiomics features were correlated with functionally significant stenosis (p <  0.05), wherein 56 features had an AUC of >0.6. NCP volume, NRS, remodeling index, and spotty calcification were included in the conventional model. Ultimately, 14 features were integrated to build the radiomics model. The AUC showed an improvement: 0.71 vs 0.82 for the training set and 0.70 vs 0.77 for the validation set (conventional model and radiomics model, respectively); however, it was not statistically significant (p =  0.58).

CONCLUSION

The radiomics analysis of plaques showed improvement compared with conventional plaques assessment in identifying hemodynamically significant coronary stenosis. The statistical advancement of machine learning for plaques to predict hemodynamic stenosis with a noninvasive approach still needs further studies on a large-scale dataset.

Clinical application of computed tomography angiography and fractional flow reserve computed tomography in patients with coronary artery disease: A meta-analysis based on pre- and post-test probability

PURPOSE

To assess the diagnostic role of coronary computed tomography angiography (CCTA) and fractional flow reserve computed tomography (FFRCT) in confirming or excluding ischemic coronary artery disease (CAD) and to provide a rational use of CCTA and FFRCT in different pre-test probability (PTP) of CAD.

METHODS

We searched the electronic databases from the earliest relevant literature to July 2020 comparing FFRCT or CCTA with FFR. The bivariate random-effects models and Bayes' theorem were used to investigate the diagnostic performance of CCTA and FFRCT with the sensitivity, specificity, pre- and post-test probability.

RESULTS

Fifty-three articles with 4817 patients and 7026 vessels finally met our inclusion criteria. At the patient level, the sensitivity and specificity of CCTA were (0.94, 0.89-0.97), and (0.50, 0.43-0.58), respectively. For FFRCT, the sensitivity and specificity were (0.90, 0.87-0.93) and (0.81, 0.73-0.87). CCTA or FFRCT could increase the post-test probability to >85 % in patients with a PTP > 74.9 % or 54.5 %; CCTA or FFRCT could decrease the post-test probability to <15 % in patients with a pre-test probability <61.3 % or 59.3 %.

CONCLUSIONS

In patients with low to intermediate PTP, CCTA is suggested to exclude CAD, while the time-consuming calculation of FFRCT may be unnecessary. If CCTA detects significant or uncertain stenosis with intermediate to high PTP of CAD, further FFRCT is suggested. The advantages of FFRCT for guiding CAD treatment have sufficiently been demonstrated.

Machine Learning Quantitation of Cardiovascular and Cerebrovascular Disease: A Systematic Review of Clinical Applications

Research into machine learning (ML) for clinical vascular analysis, such as those useful for stroke and coronary artery disease, varies greatly between imaging modalities and vascular regions. Limited accessibility to large diverse patient imaging datasets, as well as a lack of transparency in specific methods, are obstacles to further development. This paper reviews the current status of quantitative vascular ML, identifying advantages and disadvantages common to all imaging modalities. Literature from the past 8 years was systematically collected from MEDLINE^® and Scopus database searches in January 2021. Papers satisfying all search criteria, including a minimum of 50 patients, were further analysed and extracted of relevant data, for a total of 47 publications. Current ML image segmentation, disease risk prediction, and pathology quantitation methods have shown sensitivities and specificities over 70%, compared to expert manual analysis or invasive quantitation. Despite this, inconsistencies in methodology and the reporting of results have prevented inter-model comparison, impeding the identification of approaches with the greatest potential. The clinical potential of this technology has been well demonstrated in Computed Tomography of coronary artery disease, but remains practically limited in other modalities and body regions, particularly due to a lack of routine invasive reference measurements and patient datasets.

Serial coronary CT angiography-derived fractional flow reserve and plaque progression can predict long-term outcomes of coronary artery disease

OBJECTIVE

To investigate the utility of coronary CT angiography-derived fractional flow reserve (FFR_CT) and plaque progression in patients undergoing serial coronary CT angiography for predicting major adverse cardiovascular events (MACE).

METHODS

This retrospective study evaluated patients suspected or known coronary artery disease who underwent serial coronary CT angiography examinations between January 2006 and December 2017 and followed up until June 2019. The primary endpoint was MACE, defined as acute coronary syndrome, rehospitalization due to progressive angina, percutaneous coronary intervention, or cardiac death. FFR_CT and plaque parameters were analyzed on a per-vessel and per-patient basis. Univariable and multivariable COX regression analysis determined predictors of MACE. The prognostic value of FFR_CT and plaque progression were assessed in nested models.

RESULTS

Two hundred eighty-four patients (median age, 61 years (interquartile range, 54-70); 202 males) were evaluated. MACE was observed in 45 patients (15.8%, 45/284). By Cox multivariable regression modeling, vessel-specific FFR_CT ≤ 0.80 was associated with a 2.4-fold increased risk of MACE (HR (95% CI): 2.4 (1.3-4.4); p = 0.005) and plaque progression was associated with a 9-fold increased risk of MACE (HR (95% CI): 9 (3.5-23); p < 0.001) after adjusting for clinical and imaging risk factors. FFR_CT and plaque progression improved the prediction of events over coronary artery calcium (CAC) score and high-risk plaques (HRP) in the receiver operating characteristics analysis (area under the curve: 0.70 to 0.86; p = 0.002).

CONCLUSIONS

Fractional flow reserve and plaque progression assessed by serial coronary CT angiography predicted the risk of future MACE.

KEY POINTS

• Vessel-specific CT angiography-derived fractional flow reserve (FFR_CT) ≤ 0.80 and plaque progression improved the prediction of events over current risk factors. • Major adverse cardiovascular events (MACE) significantly increased with the presence of plaque progression at follow-up stratified by the FFR_CT change group.

[Artificial intelligence in cardiology : Relevance, current applications, and future developments]

Big data and applications of artificial intelligence (AI), such as machine learning or deep learning, will enrich healthcare in the future and become increasingly important. Among other things, they have the potential to avoid unnecessary examinations as well as diagnostic and therapeutic errors. They could enable improved, early and accelerated decision-making. In the article, the authors provide an overview of current AI-based applications in cardiology. The examples describe innovative solutions for risk assessment, diagnosis and therapy support up to patient self-management. Big data and AI serve as a basis for efficient, predictive, preventive and personalised medicine. However, the examples also show that research is needed to further develop the solutions for the benefit of the patient and the medical profession, to demonstrate the effectiveness and benefits in health care and to establish legal and ethical standards.

Artificial Intelligence in Coronary Computed Tomography Angiography: From Anatomy to Prognosis

Cardiac computed tomography angiography (CCTA) is widely used as a diagnostic tool for evaluation of coronary artery disease (CAD). Despite the excellent capability to rule-out CAD, CCTA may overestimate the degree of stenosis; furthermore, CCTA analysis can be time consuming, often requiring advanced postprocessing techniques. In consideration of the most recent ESC guidelines on CAD management, which will likely increase CCTA volume over the next years, new tools are necessary to shorten reporting time and improve the accuracy for the detection of ischemia-inducing coronary lesions. The application of artificial intelligence (AI) may provide a helpful tool in CCTA, improving the evaluation and quantification of coronary stenosis, plaque characterization, and assessment of myocardial ischemia. Furthermore, in comparison with existing risk scores, machine-learning algorithms can better predict the outcome utilizing both imaging findings and clinical parameters. Medical AI is moving from the research field to daily clinical practice, and with the increasing number of CCTA examinations, AI will be extensively utilized in cardiac imaging. This review is aimed at illustrating the state of the art in AI-based CCTA applications and future clinical scenarios.

CT Coronary Angiography Fractional Flow Reserve: New Advances in the Diagnosis and Treatment of Coronary Artery Disease

Coronary artery disease (CAD) remains the most common cardiovascular disease, accounting for 6% of all Emergency Department visits and 27% of all Emergency Department hospitalizations.¹ Invasive coronary angiography with fractional flow reserve (FFR) remains the gold standard to assess for hemodynamically stenosis in CAD patients. However, for low- and intermediate-risk patients, noninvasive modalities have started to gain favor as patients with stable CAD who received optimal medical therapy did as well as patients who underwent percutaneous coronary intervention.² This led to the incorporation of FFR_CT. cCTA provides good spatial resolution for evaluating stenosis. FFR provides additional information regarding whether the stenosis is hemodynamically significant. FFR is the ratio of maximum blood flow in a stenotic artery to the maximum blood flow through that artery without stenosis.³ Computational fluid dynamics involved in FFR_CT is based on Navier-Stokes equations, allowing the assessment of pressure and flow across coronary arteries. Limitations do exist with FFR_CT which includes false-positive results due to step artifact and left ventricular hypertrophy, as well as manual segmentation and ostial stenosis, which can cause false-negative results. However, there are improvements on the horizon including artificial intelligence-driven computation of FFR and the utilization of virtual stenting for surgical planning. The purpose of this review is to describe the clinical validation, underlying mechanism, and implementation of FFR_CT.

Artificial intelligence in cardiac radiology

Artificial intelligence (AI) is entering the clinical arena, and in the early stage, its implementation will be focused on the automatization tasks, improving diagnostic accuracy and reducing reading time. Many studies investigate the potential role of AI to support cardiac radiologist in their day-to-day tasks, assisting in segmentation, quantification, and reporting tasks. In addition, AI algorithms can be also utilized to optimize image reconstruction and image quality. Since these algorithms will play an important role in the field of cardiac radiology, it is increasingly important for radiologists to be familiar with the potential applications of AI. The main focus of this article is to provide an overview of cardiac-related AI applications for CT and MRI studies, as well as non-imaging-based applications for reporting and image optimization.