Mesh-Informed Reduced Order Models for Aneurysm Rupture Risk Prediction

TL;DR

This paper presents a novel approach combining full and reduced order models with graph neural networks to efficiently predict aneurysm growth and rupture risk, potentially enabling real-time clinical decision support.

Contribution

The study introduces a graph neural network-based framework that integrates CFD FOMs and ROMs for aneurysm risk prediction, addressing computational challenges in personalized medicine.

Findings

GNNs accurately predict Wall Shear Stress and OSI at different aneurysm stages.

The method overcomes the curse of dimensionality in CFD data analysis.

Experimental results validate the approach as a promising clinical tool.

Abstract

The complexity of the cardiovascular system needs to be accurately reproduced in order to promptly acknowledge health conditions; to this aim, advanced multifidelity and multiphysics numerical models are crucial. On one side, Full Order Models (FOMs) deliver accurate hemodynamic assessments, but their high computational demands hinder their real-time clinical application. In contrast, Reduced Order Models (ROMs) provide more efficient yet accurate solutions, essential for personalized healthcare and timely clinical decision-making. In this work, we explore the application of computational fluid dynamics (CFD) in cardiovascular medicine by integrating FOMs with ROMs for predicting the risk of aortic aneurysm growth and rupture. Wall Shear Stress (WSS) and the Oscillatory Shear Index (OSI), sampled at different growth stages of the thoracic aortic aneurysm, are predicted by means of Graph Neural Networks (GNNs). GNNs exploit the natural graph structure of the mesh obtained by the Finite Volume (FV) discretization, taking into account the spatial local information, regardless of the dimension of the input graph. Our experimental validation framework yields promising results, confirming our method as a valid alternative that overcomes the curse of dimensionality.