Affordable Access

deepdyve-link
Publisher Website

Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy.

Authors
  • Giffard-Roisin, Sophie
  • Delingette, Herve
  • Jackson, Thomas
  • Webb, Jessica
  • Fovargue, Lauren
  • Lee, Jack
  • Rinaldi, Christopher A
  • Razavi, Reza
  • Ayache, Nicholas
  • Sermesant, Maxime
Type
Published Article
Journal
IEEE Transactions on Biomedical Engineering
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Feb 01, 2019
Volume
66
Issue
2
Pages
343–353
Identifiers
DOI: 10.1109/TBME.2018.2839713
PMID: 29993409
Source
Medline
Language
English
License
Unknown

Abstract

Noninvasive cardiac electrophysiology (EP) model personalisation has raised interest for instance in the scope of predicting EP cardiac resynchronization therapy (CRT) response. However, the restricted clinical applicability of current methods is due in particular to the limitation to simple situations and the important computational cost. We propose in this manuscript an approach to tackle these two issues. First, we analyze more complex propagation patterns (multiple onsets and scar tissue) using relevance vector regression and shape dimensionality reduction on a large simulated database. Second, this learning is performed offline on a reference anatomy and transferred onto patient-specific anatomies in order to achieve fast personalized predictions online. We evaluated our method on a dataset composed of 20 dyssynchrony patients with a total of 120 different cardiac cycles. The comparison with a commercially available electrocardiographic imaging (ECGI) method shows a good identification of the cardiac activation pattern. From the cardiac parameters estimated in sinus rhythm, we predicted five different paced patterns for each patient. The comparison with the body surface potential mappings (BSPM) measured during pacing and the ECGI method indicates a good predictive power. We showed that learning offline from a large simulated database on a reference anatomy was able to capture the main cardiac EP characteristics from noninvasive measurements for fast patient-specific predictions. The fast CRT pacing predictions are a step forward to a noninvasive CRT patient selection and therapy optimisation, to help clinicians in these difficult tasks.

Report this publication

Statistics

Seen <100 times