Physics-informed neural network estimation of active material properties in time-dependent cardiac biomechanical models

TL;DR

This study demonstrates the use of physics-informed neural networks to accurately infer active stress parameters in cardiac tissue models from imaging data, even with noise, aiding clinical diagnosis and treatment of heart conditions.

Contribution

The paper introduces an advanced PINN framework with adaptive weighting, regularisation, and Fourier features for high-resolution active stress estimation in cardiac models from limited imaging data.

Findings

Successfully reconstructs active stress fields with high spatial resolution.

Robustly infers tissue inhomogeneities and fibrotic scars.

Enhances PINN algorithms for biomedical applications.

Abstract

Active stress models in cardiac biomechanics account for the mechanical deformation caused by muscle activity, thus providing a link between the electrophysiological and mechanical properties of the tissue. The accurate assessment of active stress parameters is fundamental for a precise understanding of myocardial function but remains difficult to achieve in a clinical setting, especially when only displacement and strain data from medical imaging modalities are available. This work investigates, through an in-silico study, the application of physics-informed neural networks (PINNs) for inferring active contractility parameters in time-dependent cardiac biomechanical models from these types of imaging data. In particular, by parametrising the sought state and parameter field with two neural networks, respectively, and formulating an energy minimisation problem to search for the optimal network parameters, we are able to reconstruct in various settings active stress fields in the presence of noise and with a high spatial resolution. To this end, we also advance the vanilla PINN learning algorithm with the use of adaptive weighting schemes, ad-hoc regularisation strategies, Fourier features, and suitable network architectures. In addition, we thoroughly analyse the influence of the loss weights in the reconstruction of active stress parameters. Finally, we apply the method to the characterisation of tissue inhomogeneities and detection of fibrotic scars in myocardial tissue. This approach opens a new pathway to significantly improve the diagnosis, treatment planning, and management of heart conditions associated with cardiac fibrosis.