Deep Learning for Computational Hemodynamics: A Brief Review of Recent Advances

Computational fluid dynamics (CFD) modeling of blood flow plays an important role in better understanding various medical conditions, designing more effective drug delivery systems, and developing novel diagnostic methods treatments. However, despite significant advances computational technology resources, the expensive cost these simulations still hinders their transformation from a research interest to clinical tool. This bottleneck is even severe for image-based, patient-specific CFD with realistic boundary conditions complex domains, which make such excessively expensive. To address this issue, deep learning approaches have been recently explored accelerate hemodynamics simulations. In study, we review recent efforts integrate discuss applications approach solving problems, as behavior aorta cerebral arteries. We also potential future directions field. review, suggest that incorporating physiologic understandings underlying mechanics laws models will soon lead paradigm shift development non-invasive decisions.