Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks

TL;DR

This paper introduces a physics-informed neural network approach to infer cardiac fiber orientations and conductivity tensors from electroanatomical maps, enhancing the understanding of electrical wave propagation in atrial tissue.

Contribution

It presents a novel method combining physics-informed neural networks with local basis representation to learn fiber orientations from clinical data.

Findings

Achieved RMSE of 2.2ms on synthetic data

Outperformed existing methods on patient data

Demonstrated feasibility of learning fiber orientations from electroanatomical maps

Abstract

Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. We use a local basis for the anisotropic conductivity tensor, which encodes the fiber orientation. The methodology is tested both in a synthetic example and for patient data. Our approach shows good agreement in both cases, with an RMSE of 2.2ms on the in-silico data and outperforming a state of the art method on the patient data. The results show a first step towards learning the fiber orientations from electroanatomical maps with physics-informed neural networks.