Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

Background Pericardial fat volume (PFV) and thoracic fat volume (TFV) can be routinely measured from noncontrast CT (NCT) performed for calculating coronary calcium score (CCS) and may predict major adverse cardiovascular event (MACE) risk. Methods From a registry of 2751 asymptomatic patients without known CAD and 4-year follow-up for MACE (cardiac death, myocardial infarction, stroke, late revascularization) after NCT, we compared 58 patients with MACE (“EVENTS”) to 174 same-sex event-free controls matched by a propensity score to account for age, risk factors, and CCS. TFV was automatically calculated, and PFV was calculated with manual assistance in defining the pericardial contour, within which fat voxels were automatically identified. Independent relationships of PFV and TFV to MACE were evaluated using conditional multivariable logistic regression. Results EVENTS had higher mean PFV (101.8±49.2 cm3 vs. 84.9±37.7 cm3, p=0.007) and TFV (204.7±90.3 cm3 vs. 177±80.3 cm3, p=0.029) and higher frequencies of PFV>125 cm3 (33% vs. 14%, p=0.002) and TFV>250 cm3 (31% vs. 17%, p=0.025). After adjusting for Framingham Risk Score, CCS, and body-mass-index, PFV and TFV were significantly associated with MACE (odds ratio (OR) 1.74, 95%CI 1.03–2.95 for each doubling of PFV; OR 1.78, 95%CI 1.01–3.14 for TFV). Areas-under-the-curve from receiver operating characteristic analyses showed a trend of improved MACE prediction when PFV was added to FRS and CCS (0.73 vs 0.68, p=0.058). Addition of PFV, but not TFV, to FRS and CCS improved estimated specificity (0.72 vs 0.66, p=0.008) and overall accuracy (0.70 vs 0.65, p=0.009) in predicting MACE. Conclusion Asymptomatic patients who experience MACE exhibit greater PFV on pre-MACE NCT when compared to event-free controls with similar cardiovascular risk profiles. Our preliminary findings suggest that PFV may help improve prediction of MACE.

AimsCoronary plaque characteristics are associated with ischaemia. Differences in plaque volumes and composition may explain the discordance between coronary stenosis severity and ischaemia. We evaluated the association between coronary stenosis severity, plaque characteristics, coronary computed tomography angiography (CTA)-derived fractional flow reserve (FFRCT), and lesion-specific ischaemia identified by FFR in a substudy of the NXT trial (Analysis of Coronary Blood Flow Using CT Angiography: Next Steps).Methods and resultsCoronary CTA stenosis, plaque volumes, FFRCT, and FFR were assessed in 484 vessels from 254 patients. Stenosis >50% was considered obstructive. Plaque volumes (non-calcified plaque [NCP], low-density NCP [LD-NCP], and calcified plaque [CP]) were quantified using semi-automated software. Optimal thresholds of quantitative plaque variables were defined by area under the receiver-operating characteristics curve (AUC) analysis. Ischaemia was defined by FFR or FFRCT ≤0.80. Plaque volumes were inversely related to FFR irrespective of stenosis severity. Relative risk (95% confidence interval) for prediction of ischaemia for stenosis >50%, NCP ≥185 mm3, LD-NCP ≥30 mm3, CP ≥9 mm3, and FFRCT ≤0.80 were 5.0 (3.0–8.3), 3.7 (2.4–5.6), 4.6 (2.9–7.4), 1.4 (1.0–2.0), and 13.6 (8.4–21.9), respectively. Low-density NCP predicted ischaemia independent of other plaque characteristics. Low-density NCP and FFRCT yielded diagnostic improvement over stenosis assessment with AUCs increasing from 0.71 by stenosis >50% to 0.79 and 0.90 when adding LD-NCP ≥30 mm3 and LD-NCP ≥30 mm3 + FFRCT ≤0.80, respectively.ConclusionStenosis severity, plaque characteristics, and FFRCT predict lesion-specific ischaemia. Plaque assessment and FFRCT provide improved discrimination of ischaemia compared with stenosis assessment alone.

No abstract

Automated scan-specific threshold level-based quantification of plaque components from coronary CT angiography allows rapid, accurate measurement of noncalcified plaque volumes, compared with intravascular US, and requires a fraction of the time needed for manual analysis.

Introduction-Pericardial fat is emerging as an important parameter for cardiovascular risk stratification. We extended previously developed quantitation of thoracic fat volume (TFV) from non-contrast coronary calcium (CC) CT scans to also quantify pericardial fat volume (PFV) and investigated the associations of PFV and TFV with CC and the Metabolic Syndrome (METS).

Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Fully automated quantification of EAT volume in clinical routine could be a timesaving and reliable tool for cardiovascular risk assessment. We propose a new fully automated deep learning framework for EAT and thoracic adipose tissue (TAT) quantification from non-contrast coronary artery calcium computed tomography (CT) scans. The first multi-task convolutional neural network (ConvNet) is used to determine heart limits and perform segmentation of heart and adipose tissues. The second ConvNet, combined with a statistical shape model, allows for pericardium detection. EAT and TAT segmentations are then obtained from outputs of both ConvNets. We evaluate the performance of the method on CT data sets from 250 asymptomatic individuals. Strong agreement between automatic and expert manual quantification is obtained for both EAT and TAT with median Dice score coefficients of 0.823 (inter-quartile range (IQR): 0.779-0.860) and 0.905 (IQR: 0.862-0.928), respectively; with excellent correlations of 0.924 and 0.945 for EAT and TAT volumes. Computations are performed in <6 s on a standard personal computer for one CT scan. Therefore, the proposed method represents a tool for rapid fully automated quantification of adipose tissue and may improve cardiovascular risk stratification in patients referred for routine CT calcium scans.

OBJECTIVES We evaluated the association between pericardial fat and myocardial ischemia for risk stratification. BACK GROUND Pericardial fat volume (PFV) and thoracic fat volume (TFV) measured from noncontrast computed tomography (CT) performed for calculating coronary calcium score (CCS) are associated with increased CCS and risk for major adverse cardiovascular events. METHODS From a cohort of 1,777 consecutive patients without previously known coronary artery disease (CAD) with noncontrast CT performed within 6 months of single photon emission computed tomography (SPECT), we compared 73 patients with ischemia by SPECT (cases) with 146 patients with normal SPECT (controls) matched by age, gender, CCS category, and symptoms and risk factors for CAD. TFV was automatically measured. Pericardial contours were manually defined within which fat voxels were automatically identified to compute PFV. Computer-assisted visual interpretation of SPECT was performed using standard 17-segment and 5-point score model; perfusion defect was quantified as summed stress score (SSS) and summed rest score (SRS). Ischemia was defined by: SSS – SRS ≥4. Independent relationships of PFV and TFV to ischemia were examined. RESULTS Cases had higher mean PFV (99.1 ± 42.9 cm3 vs. 80.1 ± 31.8 cm3, p = 0.0003) and TFV (196.1 ± 82.7 cm3 vs. 160.8 ± 72.1 cm3, p = 0.001) and higher frequencies of PFV >125 cm3 (22% vs. 8%, p = 0.004) and TFV >200 cm3 (40% vs. 19%, p = 0.001) than controls. After adjustment for CCS, PFV and TFV remained the strongest predictors of ischemia (odds ratio [OR]: 2.91, 95% confidence interval [CI]: 1.53 to 5.52, p = 0.001 for each doubling of PFV; OR: 2.64, 95% CI: 1.48 to 4.72, p = 0.001 for TFV. Receiver operating characteristic analysis showed that prediction of ischemia, as indicated by receiver-operator characteristic area under the curve, improved significantly when PFV or TFV was added to CCS (0.75 vs. 0.68, p = 0.04 for both). CONCLUSIONS Pericardial fat was significantly associated with myocardial ischemia in patients without known CAD and may help improve risk assessment.