Learning cardiac activation and repolarization times with operator learning

2025-05-13

AI Summary

In cardiac electrophysiology simulation, conventional PDE-based models (e.g., the Monodomain model) incur prohibitive computational cost, hindering clinical real-time deployment and interpretability. To address this, we propose a data-driven operator learning framework that—novelty—integrates Fourier Neural Operators (FNO) with Kernel Operator Learning (KOL) to directly learn the nonlinear mapping from stimulation current to activation time (AT) and repolarization time (RT) distributions. Crucially, this bypasses the need for explicit PDE formulations for RT—a long-standing challenge—and transcends single-domain physics-based solvers via end-to-end biphase prediction. Evaluated on synthetic 2D/3D domains and realistic left-ventricular geometries, our method achieves millisecond-scale inference, exhibits strong robustness and low hyperparameter sensitivity, and accelerates computation over the Monodomain model by over two orders of magnitude—significantly enhancing feasibility for real-time clinical simulation.

Technology Category

• Machine Learning: Kernel Methods
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Learning & Optimization for CV

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Solving partial or ordinary differential equation models in cardiac electrophysiology is a computationally demanding task, particularly when high-resolution meshes are required to capture the complex dynamics of the heart. Moreover, in clinical applications, it is essential to employ computational tools that provide only relevant information, ensuring clarity and ease of interpretation. In this work, we exploit two recently proposed operator learning approaches, namely Fourier Neural Operators (FNO) and Kernel Operator Learning (KOL), to learn the operator mapping the applied stimulus in the physical domain into the activation and repolarization time distributions. These data-driven methods are evaluated on synthetic 2D and 3D domains, as well as on a physiologically realistic left ventricle geometry. Notably, while the learned map between the applied current and activation time has its modelling counterpart in the Eikonal model, no equivalent partial differential equation (PDE) model is known for the map between the applied current and repolarization time. Our results demonstrate that both FNO and KOL approaches are robust to hyperparameter choices and computationally efficient compared to traditional PDE-based Monodomain models. These findings highlight the potential use of these surrogate operators to accelerate cardiac simulations and facilitate their clinical integration.

Problem

• Learning cardiac activation and repolarization times efficiently
• Mapping stimulus to activation/repolarization without known PDE models
• Evaluating operator learning for clinical cardiac simulations

Innovation

• Uses Fourier Neural Operators for cardiac mapping
• Applies Kernel Operator Learning to repolarization
• Compares efficiency with traditional PDE models