Low-dimensional representation of intermittent geophysical turbulence with high-order statistics-informed neural networks (H-SiNN)

R Foldes, E Camporeale, R Marino - Physics of Fluids, 2024 - pubs.aip.org
We present a novel machine learning approach to reduce the dimensionality of state
variables in stratified turbulent flows governed by the Navier–Stokes equations in the …

Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field …

T Yao, E Pajaziti, M Quail, S Schievano… - PLOS Computational …, 2024 - journals.plos.org
Computational fluid dynamics (CFD) can be used for non-invasive evaluation of
hemodynamics. However, its routine use is limited by labor-intensive manual segmentation …

Reconstruction of blood flow velocity with deep learning information fusion from spectral ct projections and vessel geometry

S Huang, M Sigovan, B Sixou - Computer Methods in …, 2024 - Taylor & Francis
In this work, we investigate a new deep learning reconstruction method of blood flow velocity
within deformed vessels from contrast enhanced X-ray projections and vessel geometry. The …

Image2Flow: A hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D …

T Yao, E Pajaziti, M Quail, S Schievano… - arXiv preprint arXiv …, 2024 - arxiv.org
Computational fluid dynamics (CFD) can be used for evaluation of hemodynamics.
However, its routine use is limited by labor-intensive manual segmentation, CFD mesh …

A new open‐source solver for early detection of atherosclerosis based on hemodynamics and LDL transport simulation

J Molina, DR Obaid, AS Ademiloye - Engineering Reports, 2024 - Wiley Online Library
This article presents a new open‐source solver within the OpenFOAM framework, to provide
a cost‐free alternative to commercial software for simulating blood flows and the transport of …