Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health.

Objectives: This study introduces a method to calculate myocardium blood flow (MBF) and coronary flow reserve (CFR) using the relatively low-dose dynamic 320-row multi-detector computed tomography (MDCT), validates the method against 15 O-H 2 O positron-emission tomography (PET) and assesses the CFRs of coronary artery disease (CAD) patients.Methods: Thirty-two subjects underwent both dynamic CT perfusion (CTP) and PET perfusion imaging at rest and during pharmacological stress. In 12 normal subjects (pilot group), the calculation method for MBF and CFR was established. In the other 13 normal subjects (validation group), MBF and CFR obtained by dynamic CTP and PET were compared. Finally, the CFRs of CTP and PET obtained by dynamic CTP and PET were compared between the validation group and CAD patients (n = 7).Results: Correlation between MBF of MDCT and PET was strong (r = 0.95, p<0.0001).CFR showed good correlation between dynamic CTP and PET (r = 0.67, p = 0.0126).CFR CT in the CAD group (2.3 ± 0.8) was significantly lower than that of in the validation group (5.2 ± 1.8) (p = 0.0011).Conclusion: We established a method for measuring MBF and CFR with the relatively low-dose dynamic MDCT. Lower CFR was well demonstrated in CAD patients by dynamic CTP. Key Points MBF and CFR can be calculated using dynamic CTP with 320-row MDCT. MBF and CFR showed good correlation between dynamic CTP and PET. Lower CFR was well demonstrated in CAD patients by dynamic CTP.

No abstract