WarpPINN: Cine-MR image registration with physics-informed neural networks
TL
TL;DR
WarpPINN is introduced, a physics-informed neural network to perform image registration to obtain local metrics of heart deformation and provides precise measurements of local cardiac deformations that can be used for a better diagnosis of heart failure and for general image registration tasks.
References64 items
1
Learning the solution operator of parametric partial differential equations with physics-informed DeepONets
2
Myofiber strain in healthy humans using DENSE and cDTI
3
DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics
4
On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
5