SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets
This addresses the need for efficient hemodynamic velocity estimation in cardiovascular disease diagnosis, offering a faster alternative to CFD for clinical practice, though it is incremental as it builds on existing GNN methods.
The paper tackled the problem of estimating 3D velocity fields in coronary arteries, which is time-intensive with traditional CFD methods, by proposing an SE(3)-equivariant graph neural network that achieves a 36-fold speed-up compared to CFD.
Hemodynamic velocity fields in coronary arteries could be the basis of valuable biomarkers for diagnosis, prognosis and treatment planning in cardiovascular disease. Velocity fields are typically obtained from patient-specific 3D artery models via computational fluid dynamics (CFD). However, CFD simulation requires meticulous setup by experts and is time-intensive, which hinders large-scale acceptance in clinical practice. To address this, we propose graph neural networks (GNN) as an efficient black-box surrogate method to estimate 3D velocity fields mapped to the vertices of tetrahedral meshes of the artery lumen. We train these GNNs on synthetic artery models and CFD-based ground truth velocity fields. Once the GNN is trained, velocity estimates in a new and unseen artery can be obtained with 36-fold speed-up compared to CFD. We demonstrate how to construct an SE(3)-equivariant GNN that is independent of the spatial orientation of the input mesh and show how this reduces the necessary amount of training data compared to a baseline neural network.