Artificial intelligence-derived coronary artery calcium scoring saves time and achieves close to radiologist-level...

Artificial Intelligence (AI) has been proposed to improve workflow for coronary artery calcium scoring (CACS), but simultaneous demonstration of improved efficiency, accuracy, and clinical stability have not been demonstrated. 148 sequential patients who underwent routine calcium-scoring computed tomography were retrospectively evaluated using a previously validated AI model (syngo. CT CaScoring VB60, Siemens Healthineers, Forscheim, Germany). CACS was performed by manual (Expert alone), semi-automatic (AI + expert review), and automatic (AI alone) methods. Time to complete and intraclass correlation coefficients were the primary endpoints. Secondary endpoints included differences in multiethnic study of atherosclerosis (MESA) percentiles and stratification by calcium severity. AI and expert CACS agreement was excellent (ICC = 0.951; 95% CI 0.933-0.964). The global median time was 15 ± 2 s for AI ("Automatic"), 38 ± 13 s for the AI + manual review ("Semiautomatic") and 45 ± 24 s for the manual segmentation. Automatic segmentation was faster than manual segmentation for all CACS severities (P < 0.001). AI computational time was independent of calcium burden. Global mean bias in Agatston score across all patients was 7.4 ± 102.6. The mean bias for global MESA score percentile was 2.1% ± 12%. 95% of error corresponded to a ± 10% difference in MESA score. The use of AI for CACS performs excellent accuracy, saves approximately 60% of time in comparison to manual review, and demonstrates low bias for clinical risk profiles. Time benefits are magnified for patients with high CACS. However, a semi-automatic approach is still recommended to minimize potential errors while maintaining efficiency.