Validation of an AI-based algorithm for measurement of the thoracic aortic diameter in low-dose chest CT

Objectives: To evaluate the performance of artificial intelligence (AI) software for automatic thoracic aortic diameter assessment in a heterogeneous cohort with low-dose, non-contrast chest computed tomography (CT). Materials and methods: Participants of the Imaging in Lifelines (ImaLife) study who underwent low-dose, non-contrast chest CT (August 2017-May 2022) were included using random samples of 80 participants <50y, >= 80y, and with thoracic aortic diameter >= 40 mm. AI-based aortic diameters at eight guideline compliant positions were compared with manual measurements. In 90 examinations (30 per group) diameters were reassessed for intra- and inter-reader variability, which was compared to discrepancy of the AI system using Bland-Altman analysis, paired samples t-testing and linear mixed models. Results: We analyzed 240 participants (63 +/- 16 years; 50 % men). AI evaluation failed in 11 cases due to incorrect segmentation (4.6 %), leaving 229 cases for analysis. No difference was found in aortic diameter between manual and automatic measurements (32.7 +/- 6.4 mm vs 32.7 +/- 6.0 mm, p = 0.70). Bland-Altman analysis yielded no systematic bias and a repeatability coefficient of 4.0 mm for AI. Mean discrepancy of AI (1.3 +/- 1.6 mm) was comparable to inter-reader variability (1.4 +/- 1.4 mm); only at the proximal aortic arch showed AI higher discrepancy (2.0 +/- 1.8 mm vs 0.9 +/- 0.9 mm, p < 0.001). No difference between AI discrepancy and inter-reader variability was found for any subgroup (all: p > 0.05). Conclusion: The AI software can accurately measure thoracic aortic diameters, with discrepancy to a human reader similar to inter-reader variability in a range from normal to dilated aortas.