Mesh convolutional neural networks for wall shear stress estimation in 3D artery models

@article{Suk2021MeshCN,
  title={Mesh convolutional neural networks for wall shear stress estimation in 3D artery models},
  author={Julian Suk and Pim de Haan and Phillip Lippe and Christoph Brune and Jelmer M. Wolterink},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.04797}
}
Computational fluid dynamics (CFD) is a valuable tool for personalised, non-invasive evaluation of hemodynamics in arteries, but its complexity and time-consuming nature prohibit large-scale use in practice. Recently, the use of deep learning for rapid estimation of CFD parameters like wall shear stress (WSS) on surface meshes has been investigated. However, existing approaches typically depend on a handcrafted re-parametrisation of the surface mesh to match convolutional neural network… 

References

SHOWING 1-10 OF 19 REFERENCES
FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
TLDR
This work proposes a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity, and obtains excellent experimental results that significantly improve over previous state-of-the-art shape correspondence results.
Inductive Representation Learning on Large Graphs
TLDR
GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
Deep Learning Framework for Real-Time Estimation of in-silico Thrombotic Risk Indices in the Left Atrial Appendage
TLDR
A deep learning framework capable of predicting the endothelial cell activation potential (ECAP), an in-silico index linked to the risk of thrombosis, typically derived from CFD simulations, solely from the patient-specific LAA morphology is developed.
Learning Mesh-Based Simulation with Graph Networks
TLDR
MeshGraphNets is introduced, a framework for learning mesh-based simulations using graph neural networks that can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation, and can accurately predict the dynamics of a wide range of physical systems.
Graph convolutional regression of cardiac depolarization from sparse endocardial maps
TLDR
A novel deep learning method based on graph convolutional neural networks to estimate the depolarization time in the myocardium, given sparse catheter data on the left ventricular endocardium; the results show that the proposed method, trained on synthetically generated data, may generalize to real data.
Deep Learning for Time Averaged Wall Shear Stress Prediction in Left Main Coronary Bifurcations
TLDR
A deep learning approach to estimating the well established hemodynamic risk indicator time average wall shear stress (TAWSS) based on the vessel geometry is proposed, which bypasses costly computational simulations and allows large scale population studies as required for meaningful CVD risk prediction.
Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
TLDR
Gauge Equivariant Mesh CNNs are proposed which generalize GCNs to apply anisotropic gauge equivariant kernels and introduce a geometric message passing scheme defined by parallel transporting features over mesh edges.
A feasibility study of deep learning for predicting hemodynamics of human thoracic aorta.
Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey
TLDR
A survey of the literature on ML-based analysis of coronary artery disease in cardiac CT methods for detection and characterization of atherosclerotic plaque as well as anatomically and functionally significant coronary artery stenosis is presented.
...
...