Mesh neural networks for SE(3)-equivariant hemodynamics estimation on the artery wall

Julian Suk, Pim de Haan, Phillip Lippe, Christoph Brune, Jelmer M. Wolterink

Abstract: Highlights•Graph Neural Networks (GNN) can quickly & accurately estimate wall shear stress (WSS).•We facilitate large 3D surface meshes via a mesh U-net architecture.•Roto-translation (SE(3)) equivariance ensures robustness to mesh misalignment.•GNNs can adapt to different flow-rate boundary conditions and even mildly extrapolate.