Bibliogr. s. e365-e366

Purpose: Accurate quantification of coronary artery calcium (CAC) via computed tomography (CT) imaging is essential for effective cardiovascular risk assessment. This study investigates the impact of different iteration levels in the advanced model-based iterative reconstruction (ADMIRE) algorithm on artificial intelligence-driven CAC quantification and subsequent risk stratification, with filtered back projection (FBP) serving as the reference. Material and methods: For 254 patients undergoing coronary CT angiography (120 kVp, automated tube current), raw data were reconstructed using FBP and ADMIRE levels 1-5 (kernel Sa36, 3.0 mm slice thickness, 1.5 mm spacing). AI-derived CAC parameters (volume, mass, Agatston score) and risk stratification were compared across reconstruction groups. Statistical analysis employed the Friedman test, one-way analysis of variance, and c2 test. Results: Compared to FBP, ADMIRE 1-5 reduced image noise by 9.70% to 49.76% (noise: 14.95 ± 2.26 HU vs. 7.55 ± 1.40 HU, F = 455.105, p < 0.001). Maximum CAC CT values progressively decreased with higher ADMIRE levels (FBP: 458.50 [306.00-645.00] HU vs. ADMIRE 5: 432.50 [281.75-620.75] HU; c² = 455.105, p < 0.001). CAC volume, mass, and Agatston scores declined significantly (p < 0.001 for all): volume decreased by 8.56-32.55% (FBP: 47.56 ± 5.93 mm³ vs. ADMIRE 5: 21.77 ± 3.46 mm³; F = 32.310); mass decreased by 8.73-32.57% (F = 29.477); and Agatston scores decreased by 8.77-33.13% (F = 31.104). Risk stratification shifted in 24/161 patients (14.91%) with detectable CAC. The effective radiation dose was 0.61 ± 0.18 mSv. Conclusions: ADMIRE reconstruction reduces image noise but progressively lowers CAC quantification (volume, mass, Agatston score) and maximum CT values, leading to underestimation of cardiovascular risk in a subset of patients. Caution is warranted when applying ADMIRE iterative reconstruction for CAC scoring.