Abstract 16178: A Deep Learning Algorithm to Estimate Left Ventricular Mass From Coronary Calcium CT Scans: Association With Incident Heart Failure Events From the Dallas Heart Study

Abstract

Introduction: Coronary artery calcium CT (CAC-CT) scans used for ASCVD risk prediction may contain additional clinical information that is currently underexploited. We developed a novel deep-learning algorithm to estimate LV mass from CAC-CT (CT-LVM) and analyzed associations with cardiac biomarkers and incident CV outcomes in the Dallas Heart Study (DHS). Hypothesis: Higher CT-LVM will be associated with baseline cardiac biomarker elevations (hsTnT and NT-proBNP) and a higher risk of incident CVD (heart failure, MI, stroke, and all-cause death). Methods: We included 1841 DHS phase 2 participants (mean age 50, 59% female, 46% Black race) who were free of baseline CVD and underwent CAC-CT and cardiac MRI. Our novel deep-learning algorithm features automatic cardiac chamber segmentation via a 3D U-Net architecture on CAC-CT, followed by a 3D DenseNet model to predict LV mass, using concurrent cardiac MRI as gold standard. LV mass was indexed to BSA. Statistical analysis included multivariable logistic regression models for baseline biomarker elevation assessment (hs-cTnT > 5ng/L or NT-proBNP > 100pg/mL) and Cox proportional hazards models for clinical outcomes. Models were adjusted for age, sex, ethnicity, BMI, hypertension, blood pressure, diabetes, smoking, creatinine, and CAC score. Results: CT-LVM correlated strongly with MRI defined LV mass (R = 0.87). CT-LVM/BSA was associated with elevated hsTnT (adjusted OR 1.3, 95% CI 1.1-1.6) and NT-proBNP (adjusted OR 1.8, 95% CI 1.5-2.2). There were 172 CVD events over a median follow up of 12.5 years. Higher CT-LVM was associated with higher CVD risk (adjusted HR 1.4, 95% CI 1.2-1.6) and higher risk of incident heart failure (adjusted HR 2.1, 95% CI 1.5-2.9). Conclusions: A novel deep-learning method for estimating LV mass from CAC-CT provided independent risk information from traditional risk factors and CAC score. This represents a novel low-cost approach to improving the risk assessment opportunities from a CAC-CT.