Motivation: Aortic disease leads to severe complications. Clinical decision-making relies on contrast-enhanced MR angiography (CEMRA) for manual diameter measurement, which lacks automation and reproducibility. We set to address this by developing an automated measurement method. Goal(s): To automatically measure aortic diameters with reliable accuracy. Approach: In CEMRA scans, the thoracic aorta was manually segmented to train and test an AI segmentation model. Segmentations were used to calculate a centerline and position planes perpendicular to the lumen. Diameters were extracted and compared to manually-processed data. Results: AI-driven analysis was successfully performed in 78% of test set cases and resulted in moderate agreement with ground truth. Impact: Aortic disease risk assessment relies on imaging-based aortic diameter surveillance. We have developed an automated, AI-driven diameter quantification pipeline, aiming to improve manual processing speed and reproducibility. We have achieved moderate agreement with manual ground truth.
Apostolidis et al. (Tue,) studied this question.