Display options
Cite
Meister F, Passerini T, Audigier C, et al. Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks. Front Physiol. 2021;12:694869doi: 10.3389/fphys.2021.694869.
Meister, F., Passerini, T., Audigier, C., Lluch, �. �., Mihalef, V., Ashikaga, H., Maier, A., Halperin, H., & Mansi, T. (2021). Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks. Frontiers in physiology, 12694869. https://doi.org/10.3389/fphys.2021.694869
Meister, Felix, et al. "Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks." Frontiers in physiology vol. 12 (2021): 694869. doi: https://doi.org/10.3389/fphys.2021.694869
Meister F, Passerini T, Audigier C, Lluch È, Mihalef V, Ashikaga H, Maier A, Halperin H, Mansi T. Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks. Front Physiol. 2021 Oct 18;12:694869. doi: 10.3389/fphys.2021.694869. eCollection 2021. PMID: 34733172; PMCID: PMC8558498.
Copy Download .nbib Format: NLM
Share it on

Front Physiol. 2021 Oct 18;12:694869. doi: 10.3389/fphys.2021.694869. eCollection 2021.

Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks.

Frontiers in physiology

Felix Meister, Tiziano Passerini, Chloé Audigier, Èric Lluch, Viorel Mihalef, Hiroshi Ashikaga, Andreas Maier, Henry Halperin, Tommaso Mansi

Affiliations

  1. Pattern Recognition Lab, Friedrich-Alexander University, Erlangen, Germany.
  2. Digital Technology and Innovation, Siemens Healthineers, Erlangen, Germany.
  3. Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, United States.
  4. Cardiac Arrhythmia Service, Johns Hopkins University School of Medicine, Baltimore, MD, United States.

PMID: 34733172 PMCID: PMC8558498 DOI: 10.3389/fphys.2021.694869

Abstract

Electroanatomic mapping is the gold standard for the assessment of ventricular tachycardia. Acquiring high resolution electroanatomic maps is technically challenging and may require interpolation methods to obtain dense measurements. These methods, however, cannot recover activation times in the entire biventricular domain. This work investigates the use of graph convolutional neural networks to estimate biventricular activation times from sparse measurements. Our method is trained on more than 15,000 synthetic examples of realistic ventricular depolarization patterns generated by a computational electrophysiology model. Using geometries sampled from a statistical shape model of biventricular anatomy, diverse wave dynamics are induced by randomly sampling scar and border zone distributions, locations of initial activation, and tissue conduction velocities. Once trained, the method accurately reconstructs biventricular activation times in left-out synthetic simulations with a mean absolute error of 3.9 ms ± 4.2 ms at a sampling density of one measurement sample per cm

Copyright © 2021 Meister, Passerini, Audigier, Lluch, Mihalef, Ashikaga, Maier, Halperin and Mansi.

Keywords: cardiac computational modeling; deep learning; electroanatomic mapping; graph convolutional networks; sparse measurements

Conflict of interest statement

TP, CA, ÈL, VM, and TM are employees of Siemens Healthineers. FM's research is funded by Siemens Healthineers. The remaining authors declare that the research was conducted in the absence of any comme

References

  1. Eur Heart J. 2020 Dec 21;41(48):4556-4564 - PubMed
  2. IEEE Trans Biomed Eng. 2020 Jan;67(1):99-109 - PubMed
  3. J Am Coll Cardiol. 2020 Mar 3;75(8):884-897 - PubMed
  4. Europace. 2021 Apr 6;23(4):640-647 - PubMed
  5. Med Image Anal. 2021 Jul;71:102080 - PubMed
  6. Med Image Anal. 2014 Dec;18(8):1361-76 - PubMed
  7. IEEE Trans Neural Netw Learn Syst. 2021 Jan;32(1):4-24 - PubMed
  8. PLoS One. 2015 Jul 31;10(7):e0134869 - PubMed
  9. Med Image Anal. 2014 Jan;18(1):228-40 - PubMed
  10. JACC Clin Electrophysiol. 2015 Oct;1(5):341-352 - PubMed
  11. Circ Res. 2007 Oct 26;101(9):939-47 - PubMed
  12. Lancet. 2012 Oct 27;380(9852):1520-9 - PubMed
  13. Sci Rep. 2019 Nov 14;9(1):16803 - PubMed
  14. JACC Cardiovasc Imaging. 2013 Jan;6(1):42-52 - PubMed
  15. Europace. 2018 Nov 01;20(suppl_3):iii94-iii101 - PubMed
  16. IEEE J Transl Eng Health Med. 2016 Dec 16;5:1900215 - PubMed
  17. Circulation. 2018 Sep 25;138(13):e272-e391 - PubMed
  18. J Anat. 2017 May;230(5):664-678 - PubMed
  19. Heart Rhythm. 2011 Jul;8(7):1060-7 - PubMed
  20. Nat Biomed Eng. 2018 Oct;2(10):732-740 - PubMed

Publication Types