Synthetic Database of Aortic Morphometry and Hemodynamics: Overcoming Medical Imaging Data Availability.

Modeling of hemodynamics and artificial intelligence have great potential to support clinical diagnosis and decision making. While hemodynamics modeling is extremely time- and resource-consuming, machine learning (ML) typically requires large training data that are often unavailable. The aim of this study was to develop and evaluate a novel methodology generating a large database of synthetic cases with characteristics similar to clinical cohorts of patients with coarctation of the aorta (CoA), a congenital heart disease associated with abnormal hemodynamics. Synthetic data allows use of ML approaches to investigate aortic morphometric pathology and its influence on hemodynamics. Magnetic resonance imaging data (154 patients as well as of healthy subjects) of aortic shape and flow were used to statistically characterize the clinical cohort. The methodology generating the synthetic cohort combined statistical shape modeling of aortic morphometry and aorta inlet flow fields and numerical flow simulations. Hierarchical clustering and non-linear regression analysis were successfully used to investigate the relationship between morphometry and hemodynamics and to demonstrate credibility of the synthetic cohort by comparison with a clinical cohort. A database of 2652 synthetic cases with realistic shape and hemodynamic properties was generated. Three shape clusters and respective differences in hemodynamics were identified. The novel model predicts the CoA pressure gradient with a root mean square error of 4.6 mmHg. In conclusion, synthetic data for anatomy and hemodynamics is a suitable means to address the lack of large datasets and provide a powerful basis for ML to gain new insights into cardiovascular diseases.

Personalized stent design for congenital heart defects using pulsatile blood flow simulations.

Stent size selection and placement are among the most challenging tasks in the treatment of pulmonary artery stenosis in congenital heart defects (CHD). Patient-specific 3D model from CT or MR improves the understanding of the patient's anatomy and information about the hemodynamics aid in patient risk assessment and treatment planning. This work presents a new approach for personalized stent design in pulmonary artery interventions combining personalized patient geometry and hemodynamic simulations. First, the stent position is initialized using a geometric approach. Second, the stent and artery expansion, including the foreshortening behavior of the stent is simulated. Two stent designs are considered, a regular stent and a Y-stent for bifurcations. Computational fluid dynamics (CFD) simulations of the blood flow in the initial and expanded artery models are performed using patient-specific boundary conditions in form of a pulsatile inflow waveform, 3-element Windkessel outflow conditions, and deformable vessel walls. The simulations have been applied to 16 patient cases with a large variability of anatomies. Finally, the simulations have been clinically validated using retrospective imaging from angiography and pressure measurements. The simulated pressure, volume flow and flow velocity values were on the same order of magnitude as the reference values obtained from clinical measurements, and the simulated stent placement showed a positive impact on the hemodynamic values. Simulation of geometric changes combined with CFD simulations offers the possibility to optimize stent type, size, and position by evaluating different configurations before the intervention, and eventually allow to test customized stent geometries and new deployment techniques in CHD.