Automated Aortic Valve Calcification Scoring: Multicenter External Validation of a Deep Learning Algorithm.
Authors
Affiliations (6)
Affiliations (6)
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, California, USA. Electronic address: [email protected].
- Bunkerhill Health, Palo Alto, California, USA.
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, California, USA; Cardiology Section, Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA.
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, California, USA; Stanford Prevention Research Center, Department of Medicine, Stanford University, California, USA.
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, California, USA; Stanford Prevention Research Center, Department of Medicine, Stanford University, California, USA; Center for Digital Health, Department of Medicine, Stanford University, California, USA.
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, California, USA; Cardiology Section, Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA; Center for Digital Health, Department of Medicine, Stanford University, California, USA.
Abstract
Aortic valve calcification (AVC) quantification is a guideline-recommended imaging biomarker for aortic stenosis (AS) severity and progression yet remains underreported on routine chest computed tomography (CT). With nearly 20 million nongated chest CTs performed annually in the United States, automated AVC detection offers potential for opportunistic AS screening without added radiation or cost. This study evaluated whether deep learning can accurately quantify AVC from nongated, noncontrast chest CT, with performance comparable to expert assessment. We evaluated a convolutional neural network across a multicenter consortium of 33 sites spanning 8 health systems in the United States and Brazil. The algorithm was developed using training (n = 1,446) and validation (n = 361) sets and evaluated on a separate holdout test set (n = 239) acquired from 2021 to 2024. Reference standards were manual segmentations independently verified by at least 2 board-certified radiologists. Primary outcomes were Pearson correlation and Bland-Altman analysis of algorithm-estimated vs manual Agatston scores. Secondary outcomes were sensitivity and specificity for a high calcium burden associated with moderate-to-severe AS using validated sex-specific thresholds. The algorithm showed high correlation with expert reference standards (r = 0.99; 95% CI: 0.98-0.99; P < 0.001). Bland-Altman analysis showed minimal bias (mean difference: 5.2 AU; 95% CI: -7.6 to 17.9). For moderate-to-severe AS, sensitivity was 0.92 (95% CI: 0.80-0.97) and specificity 0.98 (95% CI: 0.95-0.99). Performance remained consistent across demographic subgroups and CT technical parameters. This automated deep learning algorithm quantifies AVC from routine chest CT with expert-comparable performance, potentially enabling opportunistic AS screening. Prospective studies are needed to determine whether it improves clinical outcomes.