Deep Learning for Model Correction in Cardiac Electrophysiological Imaging
Langue
en
Communication dans un congrès
Ce document a été publié dans
MIDL 2022 - Medical Imaging with Deep Learning, 2022-07-06, Zurich.
Résumé en anglais
Imaging the electrical activity of the heart can be achieved with invasive catheterisation. However, the resulting data are sparse and noisy. Mathematical modelling of cardiac electrophysiology can help the analysis but ...Lire la suite >
Imaging the electrical activity of the heart can be achieved with invasive catheterisation. However, the resulting data are sparse and noisy. Mathematical modelling of cardiac electrophysiology can help the analysis but solving the associated mathematical systems can become unfeasible. It is often computationally demanding, for instance when solving for different patient conditions. We present a new framework to model the dynamics of cardiac electrophysiology at lower cost. It is based on the integration of a low-fidelity physical model and a learning component implemented here via neural networks. The latter acts as a complement to the physical part, and handles all quantities and dynamics that the simplified physical model neglects. We demonstrate that this framework allows us to reproduce the complex dynamics of the transmembrane potential and to correctly identify the relevant physical parameters, even when only partial measurements are available. This combined model-based and data-driven approach could improve cardiac electrophysiological imaging and provide predictive tools.< Réduire
Mots clés en anglais
Electrophysiology
Deep learning
Simulations
Physics-based learning
Projet Européen
Electrostructural Tomography - Towards Multiparametric Imaging of Cardiac Electrical Disorders
Project ANR
3IA Côte d'Azur - ANR-19-P3IA-0002
L'Institut de Rythmologie et modélisation Cardiaque - ANR-10-IAHU-0004
L'Institut de Rythmologie et modélisation Cardiaque - ANR-10-IAHU-0004
Origine
Importé de halUnités de recherche