Background: Traditional CFD analyses often rely on static (rigid) vascular geometries, which neglect the physiologically relevant motion of the aortic wall. This simplification can lead to inaccuracies in estimating key hemodynamic biomarkers, such as wall shear stress (WSS) and oscillatory shear index (OSI). Methods: This study introduces the Large Deformation Diffeomorphic Metric Mapping (LDDMM) method to enable computationally efficient simulations of transient blood flow in compliant, subject- and patient-specific aortas derived from 4D Flow MRI data. The proposed framework simplifies CFD pre-processing, improves morphing accuracy, and enables physiologically realistic motion of the thoracic aorta, including its side-branches. The method was applied to two aortic geometries: a healthy case (HC) and a case with thoracic aortic aneurysm (TAA) located in the ascending region. Results: The results were compared with those obtained from fixed aortic geometries extracted at peak systole. Hemodynamic biomarkers showed significant differences between static and moving geometries. For the healthy case (HC), the differences were 18% for the time-averaged wall shear stress (TAWSS) and 46% for the oscillatory shear index (OSI). For the thoracic aorta aneurysm (TAA) case, the corresponding values were 14% and 47%, respectively. Conclusion: These findings highlight the importance of incorporating aortic wall motion in hemodynamic simulations. The developed LDDMM-based framework can be readily extended to other imaging modalities, such as ultrasound or computed tomography, and is recommended for future CFD analyses of compliant aortas.

In this work, we developed deep neural networks for the fast and comprehensive estimation of the most salient features of aortic blood flow. These features include velocity magnitude and direction, 3D pressure, and wall shear stress. Starting from 40 subject-specific aortic geometries obtained from 4D Flow MRI, we applied statistical shape modeling to generate 1,000 synthetic aorta geometries. Complete computational fluid dynamics (CFD) simulations of these geometries were performed to obtain ground-truth values. We then trained deep neural networks for each characteristic flow feature using 900 randomly selected aorta geometries. Testing on remaining 100 geometries resulted in average errors of 3.11% for velocity and 4.48% for pressure. For wall shear stress predictions, we applied two approaches: (i) directly derived from the neural network-predicted velocity, and, (ii) predicted from a separate neural network. Both approaches yielded similar accuracy, with average error of 4.8 and 4.7% compared to complete 3D CFD results, respectively. We recommend the second approach for potential clinical use due to its significantly simplified workflow. In conclusion, this proof-of-concept analysis demonstrates the numerical robustness, rapid calculation speed (less than seconds), and good accuracy of the CFD-based machine learning approach in predicting velocity, pressure, and wall shear stress distributions in subject-specific aortic flows.