Geometry-Free Conditional Diffusion Modeling for Solving the Inverse Electrocardiography Problem

TL;DR

This paper introduces a geometry-free, data-driven conditional diffusion model for the inverse electrocardiography problem, enabling probabilistic and accurate reconstruction of heart surface potentials from body surface signals.

Contribution

It presents a novel diffusion-based framework that is geometry-free and outperforms traditional deterministic models in ECGI reconstruction accuracy.

Findings

Improved reconstruction accuracy over baseline models

Probabilistic sampling captures multiple plausible solutions

Eliminates need for patient-specific mesh construction

Abstract

This paper proposes a data-driven model for solving the inverse problem of electrocardiography, the mathematical problem that forms the basis of electrocardiographic imaging (ECGI). We present a conditional diffusion framework that learns a probabilistic mapping from noisy body surface signals to heart surface electric potentials. The proposed approach leverages the generative nature of diffusion models to capture the non-unique and underdetermined nature of the ECGI inverse problem, enabling probabilistic sampling of multiple reconstructions rather than a single deterministic estimate. Unlike traditional methods, the proposed framework is geometry-free and purely data-driven, alleviating the need for patient-specific mesh construction. We evaluate the method on a real ECGI dataset and compare it against strong deterministic baselines, including a convolutional neural network, long short-term memory network, and transformer-based model. The results demonstrate that the proposed diffusion approach achieves improved reconstruction accuracy, highlighting the potential of diffusion models as a robust tool for noninvasive cardiac electrophysiology imaging.