Accelerated Patient-Specific Hemodynamic Simulations with Hybrid Physics-Based Neural Surrogates

TL;DR

This paper introduces a hybrid physics-based neural surrogate model that enhances 0D cardiovascular flow predictions by learning parameters from high-fidelity 3D data, achieving real-time, accurate, and interpretable simulations.

Contribution

It develops a neural network approach to predict 0D model parameters from geometry, significantly improving accuracy without losing computational efficiency.

Findings

Reduced error by at least 50% across all anatomical cohorts.

Error decreased from 30% to 7% in pulmonary anatomies with learned parameters.

Real-time simulations (<2 seconds) enable clinical and research applications.

Abstract

Physics-based 0D reduced-order models provide computationally lightweight predictions of cardiovascular flows, resolving bulk hemodynamics in fractions of a second that would take days to solve using traditional 3D finite-element techniques. However, the accuracy of 0D models is limited as a result of the dramatic simplifications made in their derivations. In this work, we use 0D parameters learned from high-fidelity 3D data to improve 0D model accuracy without sacrificing its low computational cost or interpretability. We use the resistor-quadratic resistor-inductor (RRI) model to predict pressure drops over 0D vessels and bifurcations, where the resistances and inductance (0D parameters) are predicted from the bifurcation or vessel geometry using neural networks trained on high-fidelity 3D simulations. We validate the hybrid physics-based data-driven framework in three types of patient-specific vasculature - aortic, aortofemoral, and pulmonary anatomies. Use of learned 0D parameters reduces error by at least 50% compared to baseline 0D parameters across all anatomical cohorts. The improvements are especially marked for the more complex pulmonary anatomies, where 0D models with learned parameters reduced error from 30% to 7%. Exclusion of the quadratic resistor in the RRI model improved convergence compared to using the full RRI model. The resulting hybrid model presents a means of real-time (personal laptop runtime of <2 seconds for the most complex pulmonary anatomies), interpretable, and accurate cardiovascular flow modeling, enabling digital twins that support clinical decision-making as well as cardiovascular science and engineering research.