Mariano Ezequiel Casciaro

Abdominal aortic aneurysm (AAA) is a critical condition with high rupture risk, and the maximum diameter alone is insufficient for prediction. Pulse wave velocity (PWV), a surrogate of aortic stiffness, can be estimated using 4D-Flow magnetic resonance imaging (MRI), but requires validation under dilated conditions. This in vitro study examined the relationship between PWV and stiffness by comparing healthy and aneurysmal compliant aortic models. Two latex phantoms were fabricated to represent normal and AAA geometries. A circulatory MRI-compatible system simulated physiological inlet flow, with flow rates measured across perpendicular planes using 4D- and 2D-Flow MRI. PWV was derived from transit times of the systolic upstroke and interplane distances. Complementary 1D numerical simulations and laboratory flowmeter measurements were performed. Although the wall elasticity and thickness were identical, PWV in the healthy model ranged from 6.2 to 7.7 m/s and in the aneurysmal model it ranged from 14.2 to 15 m/s. This increase was confirmed by temporal overlap of thoracic flow curves and reduced slope in the transit time–distance regression. Results were consistent across simulations, 2D-Flow, and flowmeter data. Findings highlight that indirect 4D-Flow assessment of thoracic stiffness in the presence of AAA must account for wave reflections introduced by dilation, which significantly alter PWV estimation.

Arterial calcification is an independent predictor of cardiovascular disease (CVD) events whereas thoracic aorta calcium (TAC) detection might anticipate extracoronary outcomes. In this work, we trained six convolutional neural networks (CNNs) to detect aortic calcifications and to automate the TAC score assessment in intermediate CVD risk patients. Cardiac computed tomography images from 1415 patients were analyzed together with their aortic geometry previously assessed. Orthogonal patches centered in each aortic candidate lesion were reconstructed and a dataset with 19,790 images (61% positives) was built. Three single-input 2D CNNs were trained using axial, coronal and sagittal patches together with two multi-input 2.5D CNNs combining the orthogonal patches and identifying their best regional combination (BRC) in terms of lesion location. Aortic calcifications were concentrated in the descending (66%) and aortic arch (26%) portions. The BRC of axial patches to detect ascending or aortic arch lesions and sagittal images for the descending portion had the best performance: 0.954 F1-Score, 98.4% sensitivity, 87% of the subjects correctly classified in their TAC category and an average false positive TAC score per patient of 30. A CNN that combined axial and sagittal patches depending on the candidate aortic location ensured an accurate TAC score prediction.