Learning reduced-order models for cardiovascular simulations with graph neural networks

L Pegolotti, MR Pfaller, NL Rubio, K Ding… - Computers in Biology …, 2024 - Elsevier
Reduced-order models based on physics are a popular choice in cardiovascular modeling
due to their efficiency, but they may experience loss in accuracy when working with …

The role of artificial intelligence in coronary CT angiography

RLM van Herten, I Lagogiannis, T Leiner… - Netherlands Heart …, 2024 - Springer
Coronary CT angiography (CCTA) offers an efficient and reliable tool for the non-invasive
assessment of suspected coronary artery disease through the analysis of coronary artery …

LaB-GATr: geometric algebra transformers for large biomedical surface and volume meshes

J Suk, B Imre, JM Wolterink - … on Medical Image Computing and Computer …, 2024 - Springer
Many anatomical structures can be described by surface or volume meshes. Machine
learning is a promising tool to extract information from these 3D models. However, high …

Domain independent post-processing with graph U-nets: applications to electrical impedance tomographic imaging⋆

W Herzberg, A Hauptmann… - Physiological …, 2023 - iopscience.iop.org
Objective. To extend the highly successful U-Net Convolutional Neural Network architecture,
which is limited to rectangular pixel/voxel domains, to a graph-based equivalent that works …

Physics-informed graph neural networks for flow field estimation in carotid arteries

J Suk, D Alblas, BA Hutten, A Wiegman… - arXiv preprint arXiv …, 2024 - arxiv.org
Hemodynamic quantities are valuable biomedical risk factors for cardiovascular pathology
such as atherosclerosis. Non-invasive, in-vivo measurement of these quantities can only be …

Deep vectorised operators for pulsatile hemodynamics estimation in coronary arteries from a steady-state prior

J Suk, G Nannini, P Rygiel, C Brune, G Pontone… - arXiv preprint arXiv …, 2024 - arxiv.org
Cardiovascular hemodynamic fields provide valuable medical decision markers for coronary
artery disease. Computational fluid dynamics (CFD) is the gold standard for accurate, non …

Mesh-Informed Reduced Order Models for Aneurysm Rupture Risk Prediction

GA D'Inverno, S Moradizadeh… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

Geometric algebra transformers for large 3d meshes via cross-attention

J Suk, P De Haan, B Imre… - ICML 2024 Workshop on …, 2024 - openreview.net
Surface and volume meshes of 3D anatomical structures are widely used in biomedical
engineering and medicine. The advent of machine learning enabled viable applications …

Deep graph convolutional neural network for one-dimensional hepatic vascular haemodynamic prediction

W Zhang, S Shi, Q Qi - bioRxiv, 2024 - biorxiv.org
Hepatic vascular hemodynamics is an important reference indicator in the diagnosis and
treatment of hepatic diseases. However, Method based on Computational Fluid Dynamics …

A Novel LSTM and Graph Neural Networks Approach for Cardiovascular Simulations

A Iacovelli, L Pegolotti, M Salvador… - … on Biomedical and …, 2023 - openreview.net
We propose a novel method that integrates Long Short-Term Memory (LSTM) networks with
Graph Neural Networks (GNNs) to build reduced-order models of cardiovascular …