Learning Reduced-Order Models for Cardiovascular Simulations with Graph
Neural Networks
- URL: http://arxiv.org/abs/2303.07310v1
- Date: Mon, 13 Mar 2023 17:32:46 GMT
- Title: Learning Reduced-Order Models for Cardiovascular Simulations with Graph
Neural Networks
- Authors: Luca Pegolotti, Martin R. Pfaller, Natalia L. Rubio, Ke Ding, Rita
Brugarolas Brufau, Eric Darve, Alison L. Marsden
- Abstract summary: We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data.
Our method exhibits superior performance compared to physics-based one-dimensional models, while maintaining high efficiency at inference time.
- Score: 1.2643625859899612
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reduced-order models based on physics are a popular choice in cardiovascular
modeling due to their efficiency, but they may experience reduced accuracy when
working with anatomies that contain numerous junctions or pathological
conditions. We develop one-dimensional reduced-order models that simulate blood
flow dynamics using a graph neural network trained on three-dimensional
hemodynamic simulation data. Given the initial condition of the system, the
network iteratively predicts the pressure and flow rate at the vessel
centerline nodes. Our numerical results demonstrate the accuracy and
generalizability of our method in physiological geometries comprising a variety
of anatomies and boundary conditions. Our findings demonstrate that our
approach can achieve errors below 2% and 3% for pressure and flow rate,
respectively, provided there is adequate training data. As a result, our method
exhibits superior performance compared to physics-based one-dimensional models,
while maintaining high efficiency at inference time.
Related papers
- Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep
Learning Model [0.0]
We present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries.
Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m/s, whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.
arXiv Detail & Related papers (2023-02-13T17:56:00Z) - Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall [13.113110989699571]
We consider the estimation of vector-valued quantities on the wall of three-dimensional geometric artery models.
We employ group equivariant graph convolution in an end-to-end SE(3)-equivariant neural network that operates directly on triangular surface meshes.
We show that our method is powerful enough to accurately predict transient, vector-valued WSS over the cardiac cycle while conditioned on a range of different inflow boundary conditions.
arXiv Detail & Related papers (2022-12-09T18:16:06Z) - Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics.
Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization.
Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
arXiv Detail & Related papers (2022-10-13T10:00:30Z) - EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting.
We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
arXiv Detail & Related papers (2022-02-21T18:59:03Z) - Mixed Effects Neural ODE: A Variational Approximation for Analyzing the
Dynamics of Panel Data [50.23363975709122]
We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data.
We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem.
We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
arXiv Detail & Related papers (2022-02-18T22:41:51Z) - Machine-Learning Identification of Hemodynamics in Coronary Arteries in
the Presence of Stenosis [0.0]
An artificial neural network (ANN) model is trained using synthetic data to predict the pressure and velocity within the arterial network.
The efficiency of the model was verified using three real geometries of LAD's vessels.
arXiv Detail & Related papers (2021-11-02T23:51:06Z) - Dynamic Neural Diversification: Path to Computationally Sustainable
Neural Networks [68.8204255655161]
Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks.
We explore the diversity of the neurons within the hidden layer during the learning process.
We analyze how the diversity of the neurons affects predictions of the model.
arXiv Detail & Related papers (2021-09-20T15:12:16Z) - Sparse Flows: Pruning Continuous-depth Models [107.98191032466544]
We show that pruning improves generalization for neural ODEs in generative modeling.
We also show that pruning finds minimal and efficient neural ODE representations with up to 98% less parameters compared to the original network, without loss of accuracy.
arXiv Detail & Related papers (2021-06-24T01:40:17Z) - A Physics-Constrained Deep Learning Model for Simulating Multiphase Flow
in 3D Heterogeneous Porous Media [1.4050836886292868]
A physics-constrained deep learning model is developed for solving multiphase flow in 3D heterogeneous porous media.
The model is trained from physics-based simulation data and emulates the physics process.
The model performs prediction with a speedup of 1400 times compared to physics-based simulations.
arXiv Detail & Related papers (2021-04-30T02:15:01Z) - Deep Implicit Statistical Shape Models for 3D Medical Image Delineation [47.78425002879612]
3D delineation of anatomical structures is a cardinal goal in medical imaging analysis.
Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology.
We present deep implicit statistical shape models (DISSMs), a new approach to delineation that marries the representation power of CNNs with the robustness of SSMs.
arXiv Detail & Related papers (2021-04-07T01:15:06Z) - Physics-Informed Neural State Space Models via Learning and Evolution [1.1086440815804224]
We study methods for discovering neural state space dynamics models for system identification.
We employ an asynchronous genetic search algorithm that alternates between model selection and optimization.
arXiv Detail & Related papers (2020-11-26T23:35:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.