Graph Neural Network Emulation of Cardiac Mechanics

Abstract

This paper compares the performance of two graph neural network architectures on the emulation of a cardiac mechanic model of the left ventricle of the heart. These models can be applied directly on the same computational mesh of the left ventricle geometry that is used by the expensive numerical forward solver, precluding the need for a low-order approximation of the true geometry. Our results show that these emulation approaches incur negligible loss in accuracy compared in the forward simulator, while making predictions multiple orders of magnitude more quickly, raising the prospect for their use in both forward and inverse problems in cardiac modelling.