.png){kind=icon}
.png){kind=icon}
Return
Enhanced vascular flow simulations in aortic aneurysm via physics-informed neural networks and deep operator networks
.png){kind=icon}
PRE
AI
O
V
B
DOI：10.1016/j.mechrescom.2026.104642.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the limited accuracy of 4D flow Magnetic Resonance Imaging (MRI) in identifying hemodynamics in cardiovascular diseases, the challenges in obtaining patient-specific flow boundary conditions, and the computationally demanding and time-consuming nature of Computational Fluid Dynamics (CFD) simulations, it is crucial to explore new data assimilation algorithms that offer possible alternatives to these limitations. In the present work, we study Physics-Informed Neural Networks (PINNs), Deep Operator Networks (DeepONets), and their Physics-Informed extensions (PI-DeepONets) in predicting vascular flow in the context of a 3D Abdominal Aortic Aneurysm (AAA) idealized model. PINN is a method that combines deep neural networks with the fundamental principles of physics, incorporating the physics laws, which are given as partial differential equations, directly into the loss functions used during the training process. On the other hand, (PI-)DeepONet is designed to learn nonlinear operators from data and is particularly useful in studying parametric partial differential equations (PDEs), e.g., families of PDEs with different source terms, boundary conditions, or initial conditions. Here, we adapt these approaches to address the particular AAA use case by integrating the 3D Navier-Stokes equations (NSE) as the physical laws governing fluid dynamics. The advantages and limitations of each approach are highlighted through a series of relevant application cases. We validate our results by comparing them with CFD simulations, demonstrating good agreements and emphasizing those cases where improvements in computational efficiency are observed. The proposed methodology advances the application of Deep Learning for cardiovascular disease modeling and offers a promising framework for simulation and monitoring of vascular flow in clinical settings.
Keywords:
Physics-informed neural networks (PINNs)
(physics-informed) deep operator networks (deepONets/PI-deepONets)
Vascular flow simulation
Abdominal aortic aneurysm (AAA) idealized model
Computational fluid dynamics (CFD)
Journal
M
IF:
2.3
Papers:
115
Citations:
3.9K
Organization
Cited Papers