Geometry and local wall thickness of abdominal aortic aneurysms using intravascular ultrasound

Currently, abdominal aortic aneurysms (AAAs) are treated based on the diameter of the aorta, however, a more robust patient-specific marker is needed. The mean thickness of the wall is a potential indicator for AAA rupture risk, which varies significantly within and between patients. So far, regional thickness has not been used in previous rupture risk analysis studies, since it is challenging to measure in CT, MRI, and non-invasive ultrasound (US). This study shows how to map locally varying wall thickness of AAAs using intravascular ultrasound (IVUS). Since no ground truth of AAA wall thickness can be obtained in vivo, a novel ex vivo dataset was created of porcine, phantom and simulated aortas, of which ground truth data are available. A U-net model was trained on the ex vivo data and results show that the predicted wall segmentation is in good agreement with the ground truth (DSC = 0.86, HD = 0.97 mm). Wall thickness and geometry plots show that the variation in wall thickness can be recognized. The in vivo demonstration in patients shows that the diseased wall can be segmented, a regionally varying wall thickness can be measured, and detailed maps of AAA geometries can be created. The measured local wall thickness could be used for better general understanding of AAA wall properties resulting in more advanced rupture risk assessment of AAAs. •Data-driven AI segmentation method in clinical practice.•Automatic wall segmentations for IVUS AAA images.•Map locally varying wall thickness of AAAs using IVUS.•A step towards better patient-specific rupture risk estimators.