Skip to Main content Skip to Navigation
Conference papers

From Body Surface Potential to Activation Maps on the Atria: a Machine Learning Technique

Abstract : The treatment of atrial fibrillation has greatly changed in the past decade. Ablation therapy, in particular pul- monary vein ablation, has quickly evolved. However, the sites of the trigger remain very difficult to localize. In this study we propose a machine-learning method able to non-invasively estimate a single site trigger. The machine learning technique is based on a kernel ridge regression al- gorithm. In this study the method is tested on a simulated data. We use the monodomain model in order to simulate the electrical activation in the atria. The ECGs are com- puted on the body surface by solving the Laplace equation in the torso.
Document type :
Conference papers
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-00759210
Contributor : Simon Labarthe <>
Submitted on : Friday, November 30, 2012 - 11:32:18 AM
Last modification on : Thursday, March 19, 2020 - 11:24:09 AM
Long-term archiving on: : Saturday, December 17, 2016 - 6:31:39 PM

File

CinCInverseProblem.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00759210, version 1

Collections

Citation

Nejib Zemzemi, Simon Labarthe, Rémi Dubois, Yves Coudière. From Body Surface Potential to Activation Maps on the Atria: a Machine Learning Technique. CINC - Computing in Cardiology 2012, Sep 2012, Krakow, Poland. pp.125-128. ⟨hal-00759210⟩

Share

Metrics

Record views

487

Files downloads

286