Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. We use a local basis for the anisotropic conductivity tensor, which encodes the fiber orientation. The methodology is tested both in a synthetic example and for patient data. Our approach shows good agreement in both cases, with an RMSE of 2.2 ms on the in-silico data and outperforming a state of the art method on the patient data. The results show a first step towards learning the fiber orientations from electroanatomical maps with physics-informed neural networks.

Learning Atrial Fiber Orientations and Conductivity Tensors from Intracardiac Maps Using Physics-Informed Neural Networks / Grandits, T.; Pezzuto, S.; Costabal, F. S.; Perdikaris, P.; Pock, T.; Plank, G.; Krause, R.. - STAMPA. - 12738:(2021), pp. 650-658. (Intervento presentato al convegno FIMH2021 tenutosi a Stanford nel June 21-25, 2021) [10.1007/978-3-030-78710-3_62].

Learning Atrial Fiber Orientations and Conductivity Tensors from Intracardiac Maps Using Physics-Informed Neural Networks

Pezzuto S.;
2021-01-01

Abstract

Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. We use a local basis for the anisotropic conductivity tensor, which encodes the fiber orientation. The methodology is tested both in a synthetic example and for patient data. Our approach shows good agreement in both cases, with an RMSE of 2.2 ms on the in-silico data and outperforming a state of the art method on the patient data. The results show a first step towards learning the fiber orientations from electroanatomical maps with physics-informed neural networks.
2021
Functional Imaging and Modeling of the Heart 11th International Conference, FIMH 2021
Stanford
Springer Cham
Grandits, T.; Pezzuto, S.; Costabal, F. S.; Perdikaris, P.; Pock, T.; Plank, G.; Krause, R.
Learning Atrial Fiber Orientations and Conductivity Tensors from Intracardiac Maps Using Physics-Informed Neural Networks / Grandits, T.; Pezzuto, S.; Costabal, F. S.; Perdikaris, P.; Pock, T.; Plank, G.; Krause, R.. - STAMPA. - 12738:(2021), pp. 650-658. (Intervento presentato al convegno FIMH2021 tenutosi a Stanford nel June 21-25, 2021) [10.1007/978-3-030-78710-3_62].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/360483
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? 4
  • Scopus 8
  • ???jsp.display-item.citation.isi??? ND
social impact