Influence of Body Mass Index on Radiation Exposure Across Imaging Modalities in the Evaluation of Chest Pain.

BACKGROUND: Essential to a patient-centered approach to imaging individuals with chest pain is knowledge of differences in radiation effective dose across imaging modalities. Body mass index (BMI) is an important and underappreciated predictor of effective dose. This study evaluated the impact of BMI on estimated radiation exposure across imaging modalities. METHODS AND RESULTS: This was a retrospective analysis of patients with concern for cardiac ischemia undergoing positron emission tomography (PET)/computed tomography (CT), cadmium zinc telluride single-photon emission CT (SPECT) myocardial perfusion imaging, or coronary CT angiography (CCTA) using state-of-the-art imaging modalities and optimal radiation-sparing protocols. Radiation exposure was calculated across BMI categories based on established cardiac imaging-specific conversion factors. Among 9046 patients (mean±SD age, 64.3±13.1 years; 55% men; mean±SD BMI, 30.6±6.9 kg/m2), 4787 were imaged with PET/CT, 3092 were imaged with SPECT/CT, and 1167 were imaged with CCTA. Median (interquartile range) radiation effective doses were 4.4 (3.9-4.9) mSv for PET/CT, 4.9 (4.0-6.3) mSv for SPECT/CT, and 6.9 (4.0-11.2) mSv for CCTA. Patients at a BMI <20 kg/m2 had similar radiation effective dose with all 3 imaging modalities, whereas those with BMI ≥20 kg/m2 had the lowest effective dose with PET/CT. Radiation effective dose and variability increased dramatically with CCTA as BMI increased, and was 10 times higher in patients with BMI >45 kg/m2 compared with <20 kg/m2 (median, 26.9 versus 2.6 mSv). After multivariable adjustment, PET/CT offered the lowest effective dose, followed by SPECT/CT, and then CCTA (P<0.001). CONCLUSIONS: Although median radiation exposure is modest across state-of-the-art PET/CT, SPECT/CT, and CCTA systems using optimal radiation-sparing protocols, there are significant variations across modalities based on BMI. These data are important for making patient-centered decisions for ischemic testing.

Impact of cardiac size on diagnostic performance of single-photon emission computed tomography myocardial perfusion imaging: insights from the REgistry of Fast Myocardial Perfusion Imaging with NExt generation single-photon emission computed tomography.

AIMS: Variation in diagnostic performance of single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) has been observed, yet the impact of cardiac size has not been well characterized. We assessed whether low left ventricular volume influences SPECT MPI's ability to detect obstructive coronary artery disease (CAD) and its interaction with age and sex. METHODS AND RESULTS: A total of 2066 patients without known CAD (67% male, 64.7 ± 11.2 years) across nine institutions underwent SPECT MPI with solid-state scanners followed by coronary angiography as part of the REgistry of Fast Myocardial Perfusion Imaging with NExt Generation SPECT. Area under receiver-operating characteristic curve (AUC) analyses evaluated the performance of quantitative and visual assessments according to cardiac size [end-diastolic volume (EDV); <20th vs. ≥20th population or sex-specific percentiles], age (<75 vs. ≥75 years), and sex. Significantly decreased performance was observed in patients with low EDV compared with those without (AUC: population 0.72 vs. 0.78, P = 0.03; sex-specific 0.72 vs. 0.79, P = 0.01) and elderly patients compared with younger patients (AUC 0.72 vs. 0.78, P = 0.03), whereas males and females demonstrated similar AUC (0.77 vs. 0.76, P = 0.67). The reduction in accuracy attributed to lower volumes was primarily observed in males (sex-specific threshold: EDV 0.69 vs. 0.79, P = 0.01). Accordingly, a significant decrease in AUC, sensitivity, specificity, and negative predictive value for quantitative and visual assessments was noted in patients with at least two characteristics of low EDV, elderly age, or male sex. CONCLUSION: Detection of CAD with SPECT MPI is negatively impacted by small cardiac size, most notably in elderly and male patients.

AI-Defined Cardiac Anatomy Improves Risk Stratification of Hybrid Perfusion Imaging.

BACKGROUND: Computed tomography attenuation correction (CTAC) improves perfusion quantification of hybrid myocardial perfusion imaging by correcting for attenuation artifacts. Artificial intelligence (AI) can automatically measure coronary artery calcium (CAC) from CTAC to improve risk prediction but could potentially derive additional anatomic features. OBJECTIVES: The authors evaluated AI-based derivation of cardiac anatomy from CTAC and assessed its added prognostic utility. METHODS: The authors considered consecutive patients without known coronary artery disease who underwent single-photon emission computed tomography/computed tomography (CT) myocardial perfusion imaging at 3 separate centers. Previously validated AI models were used to segment CAC and cardiac structures (left atrium, left ventricle, right atrium, right ventricular volume, and left ventricular [LV] mass) from CTAC. They evaluated associations with major adverse cardiovascular events (MACEs), which included death, myocardial infarction, unstable angina, or revascularization. RESULTS: In total, 7,613 patients were included with a median age of 64 years. During a median follow-up of 2.4 years (IQR: 1.3-3.4 years), MACEs occurred in 1,045 (13.7%) patients. Fully automated AI processing took an average of 6.2 ± 0.2 seconds for CAC and 15.8 ± 3.2 seconds for cardiac volumes and LV mass. Patients in the highest quartile of LV mass and left atrium, LV, right atrium, and right ventricular volume were at significantly increased risk of MACEs compared to patients in the lowest quartile, with HR ranging from 1.46 to 3.31. The addition of all CT-based volumes and CT-based LV mass improved the continuous net reclassification index by 23.1%. CONCLUSIONS: AI can automatically derive LV mass and cardiac chamber volumes from CT attenuation imaging, significantly improving cardiovascular risk assessment for hybrid perfusion imaging.

Automated vessel-specific coronary artery calcification quantification with deep learning in a large multi-centre registry.

AIMS: Vessel-specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram (ECG) gated and attenuation correction (AC) computed tomography (CT) in a large multi-centre registry. METHODS AND RESULTS: Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX), and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated AC CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400, and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4 ± 1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and AC CT [0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing AC CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, P < 0.001) and AC CT (HR 4.21, 95% CI 3.48, 5.08, P < 0.001). CONCLUSION: Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and AC CT and provides important prognostic information.

Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study.

BACKGROUND: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. METHODS: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. FINDINGS: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64-8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53-3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40-2.36). INTERPRETATION: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. FUNDING: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].

Prevalence and Prognostic Importance of Abnormal Positron Emission Tomography Among Asymptomatic Patients With Diabetes Mellitus.

BACKGROUND: Ischemia and reduced global myocardial blood flow reserve (MBFR) are associated with high cardiovascular risk among symptomatic patients with diabetes mellitus (DM). OBJECTIVES: This study aimed to assess the prevalence and prognostic importance of silent ischemia and reduced MBFR among asymptomatic patients with DM. METHODS: This study included 2,730 consecutive patients with DM, without known coronary artery disease (CAD) or cardiomyopathy, who underwent rubidium-82 rest/stress positron emission tomography (PET) myocardial perfusion imaging (MPI) from 2010 to 2016. These patients were followed up for all-cause mortality (n = 461) for a median follow-up of 3 years. Patients were considered asymptomatic if neither chest pain nor dyspnea was elicited. Rates of ischemia, reduced MBFR, and coronary microvascular dysfunction on PET were assessed in both groups. Cox regression was used to define the independent association of abnormal MPI markers with mortality. RESULTS: One-quarter of patients with DM (23.7%; n = 647) were asymptomatic; ischemia was present in 30.5% (n = 197), reduced MBFR in 62.3% (n = 361), and coronary microvascular dysfunction in 32.7% (n = 200). In adjusted analyses, reduced MBFR (HR per 0.1 unit decrease in MBFR: 1.08 [95% CI: 1.03-1.12]; P = 0.001) and reduced ejection fraction (HR per 5% decrease: 1.10 [95% CI: 1.01-1.18]; P = 0.02) were independently prognostic of mortality among asymptomatic patients, but ischemia was not. This was comparable to DM patients with symptoms. Insulin use and older age were significant predictors of reduced MBFR among asymptomatic patients with DM. CONCLUSIONS: In both symptomatic and asymptomatic patients with DM, impairment in MBFR is common and associated with greater mortality risk.

Flurpiridaz F-18 PET Myocardial Perfusion Imaging in Patients With Suspected Coronary Artery Disease.

BACKGROUND: Flurpiridaz F-18 (flurpiridaz) is a novel positron emission tomography (PET) myocardial perfusion imaging tracer. OBJECTIVES: The purpose of this study was to further assess the diagnostic efficacy and safety of flurpiridaz for the detection and evaluation of coronary artery disease (CAD) defined as ≥50% stenosis by quantitative invasive coronary angiography (ICA). METHODS: In this second phase 3 prospective multicenter clinical study, 730 patients with suspected CAD from 48 clinical sites in the United States, Canada, and Europe were enrolled. Patients underwent 1-day rest/stress flurpiridaz PET and 1- or 2-day rest-stress Tc-99m-labeled single photon emission computed tomography (SPECT) before ICA. PET and SPECT images were read by 3 experts blinded to clinical and ICA data. RESULTS: A total of 578 patients (age 63.7 ± 9.5 years) were evaluable; 32.5% were women, 52.3% had body mass index ≥30 kg/m2, and 33.6% had diabetes. Flurpiridaz PET met the efficacy endpoints of the study; its sensitivity and specificity were significantly higher than the prespecified threshold value by 2 of the 3 readers. The sensitivity of flurpiridaz PET was higher than SPECT (80.3% vs 68.7%; P = 0.0003) and its specificity was noninferior to SPECT (63.8% vs 61.7%; P = 0.0004). PET area under the receiver-operating characteristic curves were higher than SPECT in the overall population (0.80 vs 0.68; P < 0.001), women, and obese patients (P < 0.001 for both). Flurpiridaz PET was superior to SPECT (P < 0.001) for perfusion defect size/severity evaluation, image quality, diagnostic certainty, and radiation exposure. Flurpiridaz PET was safe and well tolerated. CONCLUSIONS: This second flurpiridaz PET myocardial perfusion imaging trial shows that flurpiridaz has utility as a new tracer for CAD detection, specifically in women and obese patients. (An International Study to Evaluate Diagnostic Efficacy of Flurpiridaz [18F] Injection PET MPI in the Detection of Coronary Artery Disease [CAD]; NCT03354273).

Impact of Positron Emission Tomographic Myocardial Perfusion Imaging on Patient Selection for Revascularization.

BACKGROUND: Positron emission tomography (PET) myocardial perfusion imaging (MPI) quantifies left ventricular ejection fraction (LVEF) at peak stress. PET LVEF reserve (LVEF-R = stress LVEF - rest LVEF) offers diagnostic and prognostic value. OBJECTIVES: The purpose of this study was to determine if PET LVEF-R identifies patients with survival benefit postrevascularization. METHODS: We followed 14,649 unique consecutive patients undergoing 82Rb rest/stress PET MPI from January 2010 to January 2016 (excluding known cardiomyopathy). Adjusted Cox models were built to predict all-cause death, and the 3-way interaction of known coronary artery disease (CAD) (prior myocardial infarction/revascularization), LVEF-R, and 90-day revascularization was tested. RESULTS: Known CAD was present in 4,982 (34.0%). Ischemia was detected in 5,396 (36.8%; ≥10% in 1,909 [13%]). Mean LVEF-R was 4.2% ± 5.7%, and was ≤0, 1 to 5, and >5 in 3,349 (22.9%), 5,266 (35.9%), and 6,034 (41.2%). Over median follow-up of 3.4 years (IQR: 1.9-5.2 years), 1,324 (8.1%) had 90-day revascularization, and there were 2,192 (15.0%) deaths. In multivariable modeling, there was a significant 3-way interaction among known CAD, LVEF-R, and 90-day revascularization (P = 0.025), such that LVEF-R ≤0 identified patients with survival benefit with 90-day revascularization in those without prior CAD (interaction P = 0.005), independently beyond percent ischemia and myocardial flow reserve. Among patients with known CAD, LVEF-R was not prognostic of death (HR: 0.99; 95% CI: 0.98-1.02; P = 0.98). CONCLUSIONS: A lack of augmentation or drop in LVEF with vasodilator stress on PET MPI independently identifies patients who have better survival with revascularization within 90 days post-MPI compared with medical therapy, in absence of prior myocardial infarction or revascularization. Multiparametric assessment of ischemia with PET can optimize post-test management.

Accurate and efficient rapid acquisition early post-injection stress-first CZT SPECT myocardial perfusion imaging with tetrofosmin and attenuation correction.

INTRODUCTION: Myocardial perfusion imaging (MPI) protocols have not changed significantly despite advances in instrumentation and software. We compared an early post-injection, stress-first SPECT protocol to standard delayed imaging. METHODS: 95 patients referred for SPECT MPI were imaged upright and supine on a Spectrum Dynamics D-SPECT CZT system with CT attenuation correction. Patients received injection of 99mTc tetrofosmin at peak of regadenoson stress and were imaged. Early post-stress (mean 17 ± 2 minutes) and Standard 1-h delay (mean 61 ± 13 min). Three blinded readers evaluated images for overall interpretation, perceived need for rest imaging, image quality, and reader confidence. Laboratory efficiency was also evaluated. RESULTS: Blinded readers had the same response for the need for rest in 77.9% of studies. Studies also had the same interpretation in 89.5% of studies. Reader confidence was high (86.0% (Early) and 90.3% (Standard p = 0.52. Image quality was good or excellent in 87.4% Early vs 96.8% Standard (p = 0.09). Time between patient check-in and end of stress imaging was 104 ± (Standard) to 60 ± 18 minutes (Early) (p < 0.001). CONCLUSION: Early post-injection stress-only imaging using CZT SPECT/CT appears promising with Tc-99m tetrofosmin with similar image quality, reader confidence, diagnosis, and need for a rest scan.

Coronary vascular dysfunction is associated with increased risk of death in patients with peripheral artery disease.

BACKGROUND: Peripheral artery disease (PAD) and coronary vascular dysfunction are common in patients with cardiometabolic disease. Neither the prevalence of coronary vascular dysfunction among patients with PAD nor the prognostic impact with these two conditions present together has been well studied. METHODS: Consecutive patients who underwent PET MPI were analyzed for presence of coronary vascular dysfunction [myocardial blood flow reserve (MBFR) < 2]. Cox regression was used to examine the association of reduced MBFR with mortality in patients with PAD, as well as the association of comorbid MBFR < 2 and PAD with all-cause death. RESULTS: Among 13,940 patients, 1936 (14%) had PAD, 7782 (56%) had MBFR < 2 and 1346 (10%) had both PAD and MBFR < 2. Reduced MBFR was very common (69.5%) and was associated with increased risk of all-cause death (HR 1.69, 95%CI 1.32, 2.16, p < 0.01) in patients with PAD. Patients with both PAD and MBFR < 2, and those with either PAD or reduced MBFR had increased risk of death compared to those with neither condition: PAD + MBFR < 2 [(HR 95%CI), 2.30; 1.97-2.68], PAD + MBFR ≥ 2 (1.37; (1.08-1.72), PAD - MBFR < 2 (1.98; 1.75-2.25), p < 0.001 for all). CONCLUSION: Coronary vascular dysfunction was common in patients with PAD and was associated with increased risk of death.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging.

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.

Unsupervised learning to characterize patients with known coronary artery disease undergoing myocardial perfusion imaging.

PURPOSE: Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%). RESULTS: Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference). CONCLUSIONS: Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.

Myocardial Perfusion PET for the Detection and Reporting of Coronary Microvascular Dysfunction: A JACC: Cardiovascular Imaging Expert Panel Statement.

Angina pectoris and dyspnea in patients with normal or nonobstructive coronary vessels remains a diagnostic challenge. Invasive coronary angiography may identify up to 60% of patients with nonobstructive coronary artery disease (CAD), of whom nearly two-thirds may, in fact, have coronary microvascular dysfunction (CMD) that may account for their symptoms. Positron emission tomography (PET) determined absolute quantitative myocardial blood flow (MBF) at rest and during hyperemic vasodilation with subsequent derivation of myocardial flow reserve (MFR) affords the noninvasive detection and delineation of CMD. Individualized or intensified medical therapies with nitrates, calcium-channel blockers, statins, angiotensin-converting enzyme inhibitors, angiotensin II type 1-receptor blockers, beta-blockers, ivabradine, or ranolazine may improve symptoms, quality of life, and outcome in these patients. Standardized diagnosis and reporting criteria for ischemic symptoms caused by CMD are critical for optimized and individualized treatment decisions in such patients. In this respect, it was proposed by the cardiovascular council leadership of the Society of Nuclear Medicine and Molecular Imaging to convene thoughtful leaders from around the world to serve as an independent expert panel to develop standardized diagnosis, nomenclature and nosology, and cardiac PET reporting criteria for CMD. This consensus document aims to provide an overview of the pathophysiology and clinical evidence of CMD, its invasive and noninvasive assessment, standardization of PET-determined MBFs and MFR into "classical" (predominantly related to hyperemic MBFs) and "endogen" (predominantly related to resting MBF) normal coronary microvascular function or CMD that may be critical for diagnosis of microvascular angina, subsequent patient care, and outcome of clinical CMD trials.

Similarities in biomass and energy reserves among coral colonies from contrasting reef environments.

Coral reefs are declining worldwide, yet some coral populations are better adapted to withstand reductions in pH and the rising frequency of marine heatwaves. The nearshore reef habitats of Palau, Micronesia are a proxy for a future of warmer, more acidic oceans. Coral populations in these habitats can resist, and recover from, episodes of thermal stress better than offshore conspecifics. To explore the physiological basis of this tolerance, we compared tissue biomass (ash-free dry weight cm-2), energy reserves (i.e., protein, total lipid, carbohydrate content), and several important lipid classes in six coral species living in both offshore and nearshore environments. In contrast to expectations, a trend emerged of many nearshore colonies exhibiting lower biomass and energy reserves than colonies from offshore sites, which may be explained by the increased metabolic demand of living in a warmer, acidic, environment. Despite hosting different dinoflagellate symbiont species and having access to contrasting prey abundances, total lipid and lipid class compositions were similar in colonies from each habitat. Ultimately, while the regulation of colony biomass and energy reserves may be influenced by factors, including the identity of the resident symbiont, kind of food consumed, and host genetic attributes, these independent processes converged to a similar homeostatic set point under different environmental conditions.

Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events.

BACKGROUND: Assessment of coronary artery calcium (CAC) by computed tomographic (CT) imaging provides an accurate measure of atherosclerotic burden. CAC is also visible in computed tomographic attenuation correction (CTAC) scans, always acquired with cardiac positron emission tomographic (PET) imaging. OBJECTIVES: The aim of this study was to develop a deep-learning (DL) model capable of fully automated CAC definition from PET CTAC scans. METHODS: The novel DL model, originally developed for video applications, was adapted to rapidly quantify CAC. The model was trained using 9,543 expert-annotated CT scans and was tested in 4,331 patients from an external cohort undergoing PET/CT imaging with major adverse cardiac events (MACEs) (follow-up 4.3 years), including same-day paired electrocardiographically gated CAC scans available in 2,737 patients. MACE risk stratification in 4 CAC score categories (0, 1-100, 101-400, and >400) was analyzed and CAC scores derived from electrocardiographically gated CT scans (standard scores) by expert observers were compared with automatic DL scores from CTAC scans. RESULTS: Automatic DL scoring required <6 seconds per scan. DL CTAC scores provided stepwise increase in the risk for MACE across the CAC score categories (HR up to 3.2; P < 0.001). Net reclassification improvement of standard CAC scores over DL CTAC scores was nonsignificant (-0.02; 95% CI: -0.11 to 0.07). The negative predictive values for MACE of zero CAC with standard (85%) and DL CTAC (83%) CAC scores were similar (P = 0.19). CONCLUSIONS: DL CTAC scores predict cardiovascular risk similarly to standard CAC scores quantified manually by experienced operators from dedicated electrocardiographically gated CAC scans and can be obtained almost instantly, with no changes to PET/CT scanning protocol.