Aims: Electrocardiographic imaging (ECGI) is a promising tool to map the electrical activity of the heart non-invasively using body surface potentials (BSP). However, it is still challenging due to the mathematically ill-posed nature of the inverse problem to solve. Novel approaches leveraging progress in artificial intelligence could alleviate these difficulties. Methods and results: We propose a deep learning (DL) formulation of ECGI in order to learn the statistical relation between BSP and cardiac activation. The presented method is based on Conditional Variational AutoEncoders using deep generative neural networks. To quantify the accuracy of this method, we simulated activation maps and BSP data on six cardiac anatomies. We evaluated our model by training it on five different cardiac anatomies (5000 activation maps) and by testing it on a new patient anatomy over 200 activation maps. Due to the probabilistic property of our method, we predicted 10 distinct activation maps for each BSP data. The proposed method is able to generate volumetric activation maps with a good accuracy on the simulated data: the mean absolute error is 9.40 ms with 2.16 ms standard deviation on this testing set. Conclusion: The proposed formulation of ECGI enables to naturally include imaging information in the estimation of cardiac electrical activity from BSP. It naturally takes into account all the spatio-temporal correlations present in the data. We believe these features can help improve ECGI results.

Electrophysiological mapping of ventricular tachycardia (VT) is tedious and poorly reproducible. Substrate analysis on imaging cannot explicitly display VT circuits. This study sought to introduce a computed tomography-based model personalization approach, allowing for the simulation of postinfarction VT in a clinically compatible time frame. In 10 patients (age 65 ± 11 years, 9 male) referred for post-VT ablation, computed tomography-derived wall thickness maps were registered to 25 electroanatomical maps (sinus rhythm, paced, and VT). The relationship between wall thickness and electrophysiological characteristics (activation-recovery interval) was analyzed. Wall thickness was then employed to parameterize a fast and tractable organ-scale wave propagation model. Pacing protocols were simulated from multiple sites to test VT induction in silico. In silico VTs were compared to VT circuits mapped clinically. Clinically, 6 different VTs could be induced with detailed maps in 9 patients. The proposed model allowed for fast simulation (median: 6 min/pacing site). Simulations of steady pacing (600 milliseconds) from 100 different sites/patient never triggered any arrhythmia. Applying S1-S2 or S1-S2-S3 induction schemes allowed for the induction of in silico VTs in the 9 of 10 patients who were clinically inducible. The patient who was not inducible clinically was also noninducible in silico. A total of 42 different VTs were simulated (4.2 ± 2 per patient). Six in silico VTs matched a VT circuit mapped clinically. The proposed framework allows for personalized simulations in a matter of hours. In 6 of 9 patients, simulations show re-entrant patterns matching intracardiac recordings.

Computational models of cardiac electrophysiology are promising tools for reducing the rates of non-response patients suitable for cardiac resynchronization therapy (CRT) by optimizing electrode placement. The majority of computational models in the literature are mesh-based, primarily using the finite element method (FEM). The generation of patient-specific cardiac meshes has traditionally been a tedious task requiring manual intervention and hindering the modeling of a large number of cases. Meshless models can be a valid alternative due to their mesh quality independence. The organization of challenges such as the CRT-EPiggy19, providing unique experimental data as open access, enables benchmarking analysis of different cardiac computational modeling solutions with quantitative metrics. We present a benchmark analysis of a meshless-based method with finite-element methods for the prediction of cardiac electrical patterns in CRT, based on a subset of the CRT-EPiggy19 dataset. A data assimilation strategy was designed to personalize the most relevant parameters of the electrophysiological simulations and identify the optimal CRT lead configuration. The simulation results obtained with the meshless model were equivalent to FEM, with the most relevant aspect for accurate CRT predictions being the parameter personalization strategy (e.g., regional conduction velocity distribution, including the Purkinje system and CRT lead distribution).