EP-Net 2.0: Out-of-Domain Generalisation for Deep Learning Models of Cardiac Electrophysiology - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

EP-Net 2.0: Out-of-Domain Generalisation for Deep Learning Models of Cardiac Electrophysiology

Abstract

Cardiac electrophysiology models achieved good progress in simulating cardiac electrical activity. However, it is still challenging to leverage clinical measurements due to the discrepancy between idealised models and patient-specific conditions. In the last few years, data-driven machine learning methods have been actively used to learn dynamics and physical model parameters from data. In this paper, we propose a principled deep learning approach to learn the cardiac electrophysiology dynamics from data in the presence of scars in the cardiac tissue slab. We demonstrate that this technique is indeed able to reproduce the transmembrane potential dynamics in situations close to the training context. We then focus on evaluating the ability of the trained networks to generalize outside their training domain. We show experimentally that our model is able to generalize to new conditions including more complex scar geometries, multiple signal onsets and various conduction velocities.
Fichier principal
Vignette du fichier
FIMH_2021_final.pdf (1.14 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03369201 , version 1 (07-10-2021)

Identifiers

Cite

Victoriya Kashtanova, Ibrahim Ayed, Nicolas Cedilnik, Patrick Gallinari, Maxime Sermesant. EP-Net 2.0: Out-of-Domain Generalisation for Deep Learning Models of Cardiac Electrophysiology. FIMH 2021 - 11th International Conference on Functional Imaging and Modeling of the Heart, Jun 2021, Stanford, CA (virtual), United States. pp.482-492, ⟨10.1007/978-3-030-78710-3_46⟩. ⟨hal-03369201⟩
99 View
207 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More