Stefano Buoso1, Thomas Joyce1, and Sebastian Kozerke1
1ETH Zurich, Zurich, Switzerland
1ETH Zurich, Zurich, Switzerland
Physics informed neural networks can be personalized to cardiac
MRI data and trained with unsupervised approaches. They can be quickly trained
and used to simulate cardiac cycles for various physiological conditions.
Figure 1.
Schematic representation of the PINN. From
the MR data, anatomy, microstructure, tissue and circulation properties are defined. A dense neural network is generated with a preselected number of FM bases as the last layer. The bases are set as fixed network weights which are not updated during
training. The PINN is trained to provide the deformation consistent with
cardiac mechanics and it is then coupled to a lumped-parameter model of the
systemic circulation to predict cardiac deformation and the corresponding functional metrics
Figure 5.
Comparison of pressure-volume loops for 4 of the
60 new different anatomies different cases from the PINN (5 hidden layers, 5
neurons per layers, 10 FM basis) FE model
