Motion (physics)

Statistics

Machine learning

Physics

Internal medicine

Geodesy

Interpolation (computer graphics)

Artificial intelligence

Gaussian

Set (abstract data type)

Electrophysiology

Benchmark (surveying)

Predictability

Programming language

Geography

Code (set theory)

Mathematics

Computer science

Artificial neural network

Gaussian process

Cardiac electrophysiology

Quantum mechanics

Medicine

Kriging

Frontiers in Physics

A critical procedure in diagnosing atrial fibrillation is the creation of electro-anatomic activation maps. Current methods generate these mappings from interpolation using a few sparse data points recorded inside the atria; they neither include prior knowledge of the underlying physics nor uncertainty of these recordings. Here we propose a physics-informed neural network for cardiac activation mapping that accounts for the underlying wave propagation dynamics and we quantify the epistemic uncertainty associated with these predictions. These uncertainty estimates not only allow us to quantify the predictive error of the neural network, but also help to reduce it by judiciously selecting new informative measurement locations via active learning. We illustrate the potential of our approach using a synthetic benchmark problem and a personalized electrophysiology model of the left atrium. We show that our new method outperforms linear interpolation and Gaussian process regression for the benchmark problem and linear interpolation at clinical densities for the left atrium. In both cases, the active learning algorithm achieves lower error levels than random allocation. Our findings open the door towards physics-based electro-anatomic mapping with the ultimate goals to reduce procedural time and improve diagnostic predictability for patients affected by atrial fibrillation. Open source code is available at https://github.com/fsahli/EikonalNet.

Physics-Informed Neural Networks for Cardiac Activation Mapping