Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jara, Ramiro Valdes, Meyers, Adam
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.18615
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910001099964416
author Jara, Ramiro Valdes
Meyers, Adam
author_facet Jara, Ramiro Valdes
Meyers, Adam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18615
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometry-Free Conditional Diffusion Modeling for Solving the Inverse Electrocardiography Problem
Jara, Ramiro Valdes
Meyers, Adam
Machine Learning
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.
title Geometry-Free Conditional Diffusion Modeling for Solving the Inverse Electrocardiography Problem
topic Machine Learning
url https://arxiv.org/abs/2601.18615