Search

Background: The difference between expert level (L3) reader and artificial intelligence (AI) performance for quantifying coronary plaque and plaque components is unknown. Objective: This study evaluates the interobserver variability among expert readers for quantifying the volume of coronary plaque and plaque components on coronary computed tomographic angiography (CCTA) using an artificial intelligence enabled quantitative CCTA analysis software as a reference (AI-QCT). Methods: This study uses CCTA imaging obtained from 232 patients enrolled in the CLARIFY (CT EvaLuation by ARtificial Intelligence For Atherosclerosis, Stenosis and Vascular MorphologY) study. Readers quantified overall plaque volume and the % breakdown of noncalcified plaque (NCP) and calcified plaque (CP) on a per vessel basis. Readers categorized high risk plaque (HRP) based on the presence of low-attenuation-noncalcified plaque (LA-NCP) and positive remodeling (PR; ≥1.10). All CCTAs were analyzed by an FDA-cleared software service that performs AI-driven plaque characterization and quantification (AI-QCT) for comparison to L3 readers. Reader generated analyses were compared among readers and to AI-QCT generated analyses. Results: When evaluating plaque volume on a per vessel basis, expert readers achieved moderate to high interobserver consistency with an intra-class correlation coefficient of 0.78 for a single reader score and 0.91 for mean scores. There was a moderate trend between readers 1, 2, and 3 and AI with spearman coefficients of 0.70, 0.68 and 0.74, respectively. There was high discordance between readers and AI plaque component analyses. When quantifying %NCP v. %CP, readers 1, 2, and 3 achieved a weighted kappa coefficient of 0.23, 0.34 and 0.24, respectively, compared to AI with a spearman coefficient of 0.38, 0.51, and 0.60, respectively. The intra-class correlation coefficient among readers for plaque composition assessment was 0.68. With respect to HRP, readers 1, 2, and 3 achie

Objectives: To determine whether coronary computed tomography angiography (CCTA) scanning, scan preparation, contrast, and patient based parameters influence the diagnostic performance of an artificial intelligence (AI) based analysis software for identifying coronary lesions with ≥50% stenosis. Background: CCTA is a noninvasive imaging modality that provides diagnostic and prognostic benefit to patients with coronary artery disease (CAD). The use of AI enabled quantitative CCTA (AI-QCT) analysis software enhances our diagnostic and prognostic ability, however, it is currently unclear whether software performance is influenced by CCTA scanning parameters. Methods: CCTA and quantitative coronary CT (QCT) data from 303 stable patients (64 ± 10 years, 71% male) from the derivation arm of the CREDENCE Trial were retrospectively analyzed using an FDA-cleared cloud-based software that performs AI-enabled coronary segmentation, lumen and vessel wall determination, plaque quantification and characterization, and stenosis determination. The algorithm's diagnostic performance measures (sensitivity, specificity, and accuracy) for detecting coronary lesions of ≥50% stenosis were determined based on concordance with QCA measurements and subsequently compared across scanning parameters (including scanner vendor, model, single vs dual source, tube voltage, dose length product, gating technique, timing method), scan preparation technique (use of beta blocker, use and dose of nitroglycerin), contrast administration parameters (contrast type, infusion rate, iodine concentration, contrast volume) and patient parameters (heart rate and BMI). Results: Within the patient cohort, 13% demonstrated ≥50% stenosis in 3 vessel territories, 21% in 2 vessel territories, 35% in 1 vessel territory while 32% had <50% stenosis in all vessel territories evaluated by QCA. Average AI analysis time was 10.3 ± 2.7 min. On a per vessel basis, there were significant differences only in sensitivity for ≥50%