EUVIMEDScopri EUVIMED
Crossref

Ensemble learning of the atrial fibre orientation with physics‐informed neural networks

Efraín Magaña iD, Simone Pezzuto iD, Francisco Sahli Costabal

The Journal of Physiology · 2026-10 · 604 (19) · 8201-8218

DOI: 10.1113/jp288001 ↗

At a glance

Journal article in The Journal of Physiology, published online on 2025-09-19. Written by Efraín Magaña and 2 co-authors. Institution: Department of Mechanical and Metallurgical Engineering, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile. Major MEDLINE topics: Neural Networks, Computer, Heart Atria. Cited 4 times so far (Crossref); 57 references. Funded by: Agencia Nacional de Investigación y Desarrollo (ANID), Centro Svizzero di Calcolo Scientifico (CSCS), PRIN-PNRR.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

The anisotropic structure of the myocardium is a key determinant of the cardiac function. To date there is no imaging modality to assess in vivo the cardiac fibre structure. We recently proposed Fibernet, a method for the automatic identification of the anisotropic conduction – and thus fibres – in the atria from local electrical recordings. Fibernet uses cardiac activation as recorded during electroanatomical mappings to infer local conduction properties using physics‐informed neural networks. In this work we extend Fibernet to cope with the uncertainty in the estimated fibre field. Specifically we use an ensemble of neural networks to produce multiple samples, all fitting the observed data, and compute posterior statistics. We also introduce a methodology to select the best fibre orientation members and define the input of the neural networks directly on the atrial surface. With these improvements we outperform the previous methodology in terms of fibre orientation error in eight different atrial anatomies. Currently our approach can estimate the fibre orientation and conduction velocities in under 7 min with quantified uncertainty, which opens the door to its application in clinical practice. We hope the proposed methodology will enable further personalisation of cardiac digital twins for precision medicine. image Key points The direction of heart muscle fibres strongly affects how electrical signals travel, but current imaging methods cannot measure these fibres inside the living atria. We improved our previous method (Fibernet) by introducing ‐Fibernet, which is more accurate and can estimate uncertainty in the results. ‐Fibernet works directly on the surface of the heart and includes a new approach to select the most reliable fibre direction. The method produces results in under 7 min and could support personalised treatment planning for heart rhythm disorders.

Subjects

MeSH terms (MEDLINE)

Neural Networks, ComputerHeart AtriaAnimalsHumansAnisotropy

Author keywords

anisotropic conduction velocitycardiac electrophysiologycardiac fibresdeep learningeikonal equationphysics‐informed neural networks

Authors and institutions

  • Department of Mechanical and Metallurgical Engineering, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile.
  • Institute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences, Pontificia Universidad Católica de Chile, Santiago, Chile.
  • Millennium Institute for Intelligent Healthcare Engineering, iHEALTH, Santiago, Chile.
  • Laboratory of Mathematics for Biology and Medicine, Department of Mathematics, University of Trento, Trento, Italy.
  • Euler Institute, Università della Svizzera italiana, Lugano, Switzerland.

ORCID profiles: Efraín Magaña, Simone Pezzuto

Funding

  • Agencia Nacional de Investigación y Desarrollo (ANID)
  • Centro Svizzero di Calcolo Scientifico (CSCS)
  • PRIN-PNRR

Cite

APA

Magaña, E., Pezzuto, S., & Sahli Costabal, F. (2026). Ensemble learning of the atrial fibre orientation with physics‐informed neural networks. The Journal of Physiology, 604(19), 8201-8218. https://doi.org/10.1113/jp288001

Vancouver

Magaña E, Pezzuto S, Sahli Costabal F. Ensemble learning of the atrial fibre orientation with physics‐informed neural networks. The Journal of Physiology. 2026;604(19):8201-8218. doi:10.1113/jp288001

BibTeX
@article{Magaa2026,
  author = {Magaña, Efraín and Pezzuto, Simone and Sahli Costabal, Francisco},
  title = {Ensemble learning of the atrial fibre orientation with physics‐informed neural networks},
  journal = {The Journal of Physiology},
  year = {2026},
  volume = {604},
  number = {19},
  pages = {8201--8218},
  doi = {10.1113/jp288001}
}
Start for free →