Search

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., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2020 Giuseppe Muscogiuri et al.)

Objectives: The aims of the study were to test the diagnostic accuracy of integrated evaluation of dynamic myocardial computed tomography perfusion (CTP) on top of coronary computed tomography angiography (cCTA) plus fractional flow reserve computed tomography derived (FFR CT ) by using a whole-heart coverage computed tomography (CT) scanner as compared with clinically indicated invasive coronary angiography (ICA) and invasive fractional flow reserve (FFR)., Background: Recently, new techniques such as dynamic stress computed tomography perfusion (stress-CTP) emerged as potential strategies to combine anatomical and functional evaluation in a one-shot scan. However, previous experiences with this technique were associated with high radiation exposure., Methods: Eighty-five consecutive symptomatic patients scheduled for ICA were prospectively enrolled. All patients underwent rest cCTA followed by stress dynamic CTP with a whole-heart coverage CT scanner (Revolution CT, GE Healthcare, Milwaukee, Wisconsin). FFR CT was also measured by using the rest cCTA dataset. The diagnostic accuracy to detect functionally significant coronary artery disease (CAD) in a vessel-based model of cCTA alone, cCTA+FFR CT , cCTA+CTP, or cCTA+FFR CT +CTP were assessed and compared by using ICA and invasive FFR as reference. The overall effective dose of dynamic CTP was also measured., Results: The prevalence of obstructive CAD and functionally significant CAD was 77% and 57%, respectively. The sensitivity and specificity of cCTA alone, cCTA+FFR CT , and cCTA+CTP were 83% and 66%, 86% and 75%, and 73% and 86%, respectively. Both the addition of FFR CT and CTP improves the area under the curve (AUC: 0.876 and 0.878, respectively) as compared with cCTA alone (0.826; p < 0.05). The sequential strategy of cCTA+FFR CT +CTP showed the highest AUC (0.919; p < 0.05) as compared with all other strategies. The mean effective radiation dose (ED) for cCTA and stress CTP was 2.8 ± 1.2 mSv and 5.3 ± 0.7 mSv, respectively., Conclusions: The addition of dynamic stress CTP on top of cCTA and FFR CT provides additional diagnostic accuracy with acceptable radiation exposure., (Copyright © 2019 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Objectives: This study sought to compare the diagnostic accuracy of coronary computed tomography angiography (cCTA) with that of cCTA+fractional flow reserve derived from cCTA datasets (FFR CT ) and that of cCTA+static stress-computed tomography perfusion (stress-CTP) in detecting functionally significant coronary artery lesions using invasive coronary angiography (ICA) plus invasive FFR as the reference standard., Background: FFR CT and static stress-CTP are new techniques that combine anatomy and functional evaluation to improve assessment of coronary artery disease (CAD) using cCTA., Methods: A total of 147 consecutive symptomatic patients scheduled for clinically indicated ICA+invasive FFR were evaluated with cCTA, FFR CT , and stress-CTP., Results: Vessel-based and patient-based sensitivity, specificity, and negative predictive values, and positive predictive values, and accuracy rates of cCTA were 99%, 76%, 100%, 61%, 82%, and 95%, 54%, 94%, 63%, 73%, respectively. cCTA+FFR CT showed vessel-based and patient-based sensitivity, specificity, and negative predictive values, and positive predictive values and accuracy rates of 88%, 94%, 95%, 84%, 92%, and 90%, 85%, 92%, 83%, 87%, respectively. Finally, cCTA+stress-CTP showed vessel-based and patient-based sensitivity, specificity, and negative predictive values, and positive predictive values and accuracy rates of 92%, 95%, 97%, 87%, 94% and 98%, 87%, 99%, 86%, 92%, respectively. Both FFR CT and stress-CTP significantly improved specificity and positive predictive values compared to those of cCTA alone. The area under the curve to detect flow-limiting stenoses of cCTA, cCTA+FFR CT , and cCTA+CTP were 0.89, 0.93, 0.92, and 0.90, 0.94, and 0.93 in a vessel-based and patient-based model, respectively, with significant additional values for both cCTA+FFR CT and cCTA+CTP versus cCTA alone (p < 0.001) but no differences between cCTA+FFR CT versus cCTA+CTP., Conclusions: FFR CT and stress-CTP in addition to cCTA are valid and comparable tools to evaluate the functional relevance of CAD., (Copyright © 2019 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Background: We assessed whether the non-invasive measure of peak diastolic-systolic velocity ratio (rDSVR) at rest on the left anterior descending artery (LAD) using Doppler transthoracic echocardiography is associated with obstructive coronary artery disease (CAD) on the LAD and left main (LM) arteries. We compared rDSVR diagnostic accuracy with stress wall motion (WM) and coronary flow reserve (CFR-LAD), in a group of subjects who underwent contrast stress-echocardiography (cSE) and coronary angiography within 3 months., Methods: 286 patients selected with a clinical indication to cSE, in which CFR-LAD was measured during the test who also underwent coronary angiography within 3 months were selected and diagnostic performance compared., Results: Demographics and clinical variables were univariate predictors of LAD or LM >50% stenosis, but rDSVR < 1.7 outperformed other variables (OR 11.18, 95% CI 5.82-21.49, p < 0.001), comprising cSE variables such as reversible WM abnormalities (OR 1.53, 95% CI 0.94-2.49, p = 0.087) or CFR-LAD < 2 (OR 2.88, 95% CI 21.74-4.77, p < 0.001). The addition of rDSVR to multivariate logistic regression models (clinical or clinical + cSE variables) led to a marked increase in C-index (0.82, 95%CI 0.78-0.87) with significant improvement compared to all prior models (p < 0.001)., Conclusions: Our data suggest a strict association of reduced rDSVR with >50% coronary artery stenosis on the LM/LAD, superior to other standard clinical or cSE related indexes, such as WM assessment or CFR-LAD, and builds incrementally to them and clinical variables in multivariable logistic models for the prediction of CAD on LM and LAD coronaries., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Objectives: The goal of this study was to evaluate the diagnostic accuracy of stress computed tomography myocardial perfusion (CTP) for the detection of functionally significant coronary artery disease (CAD) by using invasive coronary angiography (ICA) plus invasive fractional flow reserve (FFR) as the reference standard in consecutive intermediate- to high-risk symptomatic patients., Background: Stress CTP recently emerged as a potential strategy to combine the anatomic and functional evaluation of CAD in a single scan., Methods: A total of 100 consecutive symptomatic patients scheduled for ICA were prospectively enrolled. All patients underwent rest coronary computed tomography angiography (CTA) followed by stress static CTP with a whole-heart coverage CT scanner (Revolution CT, GE Healthcare, Milwaukee, Wisconsin). Diagnostic accuracy and overall effective dose were assessed and compared versus those of ICA and invasive FFR., Results: The prevalence of obstructive CAD and functionally significant CAD were 69% and 44%, respectively. Coronary CTA alone demonstrated a per-vessel and per-patient sensitivity, specificity, negative predictive value, positive predictive value, and accuracy of 98%, 76%, 99%, 63%, and 83% and of 98%, 54%, 96%, 68%, and 76%, respectively. Combining coronary CTA with stress CTP, per-vessel and per-patient sensitivity, specificity, negative predictive value, positive predictive value, and accuracy were 91%, 94%, 96%, 86%, and 93% and 98%, 83%, 98%, 86%, and 91%, with a significant improvement in specificity, positive predictive value, and accuracy in both models. The mean effective dose for coronary CTA and stress CTP were 2.8 ± 1.4 mSv and 2.5 ± 1.1 mSv., Conclusions: The inclusion of stress CTP for the evaluation of patients with an intermediate to high risk for CAD is feasible and improved the diagnostic performance of coronary CTA for detecting functionally significant CAD., (Copyright © 2019 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Background: Coronary computed tomography angiography (cCTA) has limited diagnostic accuracy in patients with intermediate to high pre-test likelihood of coronary artery disease (CAD) that may have large amounts of coronary calcium. Stress computed tomography myocardial perfusion (CTP) has emerged as a valuable strategy, combining anatomical and functional assessment of CAD. Purpose of the study is to evaluate the diagnostic accuracy of combining coronary artery imaging and myocardial perfusion in a single stress dataset versus invasive coronary angiography (ICA) and invasive fractional flow reserve (FFR) as reference standard., Methods: One-hundred-thirty consecutive symptomatic patients (age: 65 ± 9 years; men: 70%) scheduled for clinically indicated ICA plus invasive FFR were prospectively enrolled. cCTA + CTP were simultaneously evaluated in a single stress-dataset by blinded readers and compared to ICA and invasive FFR findings., Results: CTP was successfully performed in all patients. The most common artifacts observed in the stress dataset for coronary artery imaging were blooming effect and motion effect related. Overall evaluability of coronary arteries by using cCTA stress dataset was 93%. In a vessel and patient-based model, stress cCTA + stress CTP showed sensitivity, specificity, negative predictive value, positive predictive value and diagnostic accuracy of 93%, 94%, 97%, 85%, 94%, and 98%, 86%, 98%, 85%, 92%, respectively. The overall effective dose (ED) of stress protocol acquisition alone was 2.5 ± 1.1 mSv., Conclusions: Simultaneous evaluation of coronary arteries and myocardial perfusion with single stress acquisition is feasible and it has diagnostic accuracy and low ED to identify functionally significant stenosis in patients with intermediate to high risk for CAD., (Copyright © 2018 Elsevier B.V. All rights reserved.)

The prognostic impact of diabetes mellitus (DM) on cardiovascular outcomes is well known. As a consequence of previous studies showing the high incidence of coronary artery disease (CAD) in diabetic patients and the relatively poor outcome compared to nondiabetic populations, DM is considered as CAD equivalent which means that diabetic patients are labeled as asymptomatic individuals at high cardiovascular risk. Lessons learned from the analysis of prognostic studies over the past decade have challenged this dogma and now support the idea that diabetic population is not uniformly distributed in the highest risk box. Detecting CAD in asymptomatic high risk individuals is controversial and, what is more, in patients with diabetes is challenging, and that is why the reliability of traditional cardiac stress tests for detecting myocardial ischemia is limited. Cardiac computed tomography angiography (CCTA) represents an emerging noninvasive technique able to explore the atherosclerotic involvement of the coronary arteries and, thus, to distinguish different risk categories tailoring this evaluation on each patient. The aim of the review is to provide a wide overview on the clinical meaning of CCTA in this field and to integrate the anatomical information with a reliable therapeutic approach.

Background: Computed tomography coronary angiography (cTCA) and stress cardiac magnetic resonance (stress-CMR) are suitable tools for diagnosing obstructive coronary artery disease in symptomatic patients with previous history of revascularization. However, performance appraisal of noninvasive tests must take in account the consequent diagnostic testing, invasive procedures, clinical outcomes, radiation exposure, and cumulative costs rather than their diagnostic accuracy only. We aimed to compare an anatomic (cTCA) versus a functional (stress-CMR) strategy in symptomatic patients with previous myocardial revascularization procedures., Methods and Results: Six hundred patients with chest pain and previous revascularization included in a prospective observational registry and evaluated by clinically indicated cTCA (n=300, mean age 68.2±9.7 years, male 255) or stress-CMR (n=300, mean age 67.6±9.7 years, male 263) were enrolled and followed-up in terms of subsequent noninvasive tests, invasive coronary angiography, revascularization procedures, cumulative effective radiation dose, major adverse cardiac events, defined as a composite end point of nonfatal myocardial infarction and cardiac death, and medical costs. The mean follow-up for cTCA and stress-CMR groups was similar (773.6±345 versus 752.8±291 days; P=0.21). Compared with stress-CMR, cTCA was associated with a higher rate of subsequent noninvasive tests (28% versus 17%; P=0.0009), invasive coronary angiography (31% versus 20%; P=0.0009), and revascularization procedures (24% versus 16%; P=0.007). Stress-CMR strategy was associated with a significant reduction of radiation exposure and cumulative costs (59% and 24%, respectively; P<0.001). Finally, patients undergoing stress-CMR showed a lower rate of major adverse cardiac events (5% versus 10%; P<0.010) and cost-effectiveness ratio (119.98±250.92 versus 218.12±298.45 Euro/y; P<0.001)., Conclusions: Compared with cTCA, stress-CMR is more cost-effective in symptomatic revascularized patients., (© 2016 American Heart Association, Inc.)

Background: Non-invasive stress tests are commonly used as gatekeepers to invasive coronary angiography (ICA) in patients with suspected coronary artery disease (CAD). New computed tomography angiography (CTA) techniques such as fractional flow reserve calculated by CTA (FFRCT) and stress myocardial computed tomography perfusion (CTP) have emerged as potential strategies to combine anatomical and functional evaluation of CAD in one technique. The aim of this study is to compare per-vessel diagnostic accuracy of FFRCT versus stress myocardial CTP for the detection of functionally significant coronary artery disease (CAD), using invasive FFR as the reference standard., Methods: Subjects with suspected CAD due to chest pain who have no contra-indications to FFRCT or stress myocardial CTP and who are referred for non-emergent, clinically indicated invasive coronary angiography (ICA), will be enrolled. A total of 300 subjects will be enrolled within 24 months., Results: The primary study endpoint will be the comparison of per-vessel diagnostic accuracy of CTA versus FFRCT versus stress myocardial CTP for the diagnosis of hemodynamically significant stenosis as defined by invasive FFR ≤0.80., Conclusions: In the PERFECTION study, the comparison between FFRCT and stress myocardial CTP will provide understanding about which technology is more accurate for the diagnosis of functionally significant CAD., (Copyright © 2016 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.)

Objectives: The aim of this study was to evaluate the impact of a novel intra-cycle motion correction algorithm (MCA) on overall evaluability and diagnostic accuracy of cardiac computed tomography coronary angiography (CCT)., Methods: From a cohort of 900 consecutive patients referred for CCT for suspected coronary artery disease (CAD), we enrolled 160 (18 %) patients (mean age 65.3 ± 11.7 years, 101 male) with at least one coronary segment classified as non-evaluable for motion artefacts. The CCT data sets were evaluated using a standard reconstruction algorithm (SRA) and MCA and compared in terms of subjective image quality, evaluability and diagnostic accuracy., Results: The mean heart rate during the examination was 68.3 ± 9.4 bpm. The MCA showed a higher Likert score (3.1 ± 0.9 vs. 2.5 ± 1.1, p < 0.001) and evaluability (94%vs.79 %, p < 0.001) than the SRA. In a 45-patient subgroup studied by clinically indicated invasive coronary angiography, specificity, positive predictive value and accuracy were higher in MCA vs. SRA in segment-based and vessel-based models, respectively (87%vs.73 %, 50%vs.34 %, 85%vs.73 %, p < 0.001 and 62%vs.28 %, 66%vs.51 % and 75%vs.57 %, p < 0.001). In a patient-based model, MCA showed higher accuracy vs. SCA (93%vs.76 %, p < 0.05)., Conclusions: MCA can significantly improve subjective image quality, overall evaluability and diagnostic accuracy of CCT., Key Points: Cardiac computed tomographic coronary angiography (CCT) allows non-invasive evaluation of coronary arteries. Intra-cycle motion correction algorithm (MCA) allows for compensation of coronary motion. An MCA improves image quality, CCT evaluability and diagnostic accuracy.