Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
Abstract
We present the development and application of a three-dimensional Physics-Informed Neural Network (PINN) framework for the investigation of haemodynamic behaviour in the human aorta. The model incorporates a time-resolved simulation of pulsatile blood flow over a two-minute interval, enabling the extraction of pressure and velocity fields with high temporal fidelity. The mechanical stress exerted on the aortic wall was quantified through Laplace's law, with temporal averaging applied to derive representative stress distributions. This approach circumvents the computational overhead associated with conventional computational fluid dynamics (CFD) methods by eliminating mesh generation and exploiting the automatic differentiation capabilities inherent to neural networks. The proposed methodology demonstrates that PINNs can serve as an efficient and accurate alternative for modelling complex vascular flow phenomena, offering significant advantages in scalability and computational cost reduction while maintaining physical consistency.
Related
- Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems
- PINNIES: An efficient physics-informed neural network framework for integral operator problems
- Universal Construction of Generalized Lyapunov Functions for Nonlinear Dynamical Systems Using Physics-Informed Neural Networks
- Comparison of a Parametric Physics-Informed Neural Network and a Tensorial Reduced-Order Model for the Shallow-Water Dam-Break Problem
- Reconstruction of Magnetic Fields with a Physics-Informed Neural Network
BibTeX
@misc{arques2026physics,
title = {{Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm}},
author = {Adrián Robles Arques and Martín Ruiz Fernandez and Javier Sanchis and Miguel A. Teruel and Juan Trujillo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15104},
eprint = {2609.15104},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15104},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
AU - Adrián Robles Arques
AU - Martín Ruiz Fernandez
AU - Javier Sanchis
AU - Miguel A. Teruel
AU - Juan Trujillo
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15104
UR - https://arxiv.org/abs/2609.15104
AB - We present the development and application of a three-dimensional Physics-Informed Neural Network (PINN) framework for the investigation of haemodynamic behaviour in the human aorta. The model incorporates a time-resolved simulation of pulsatile blood flow over a two-minute interval, enabling the extraction of pressure and velocity fields with high temporal fidelity. The mechanical stress exerted on the aortic wall was quantified through Laplace's law, with temporal averaging applied to derive representative stress distributions. This approach circumvents the computational overhead associated with conventional computational fluid dynamics (CFD) methods by eliminating mesh generation and exploiting the automatic differentiation capabilities inherent to neural networks. The proposed methodology demonstrates that PINNs can serve as an efficient and accurate alternative for modelling complex vascular flow phenomena, offering significant advantages in scalability and computational cost reduction while maintaining physical consistency.
ER -