Fast personalized electrophysiological models from computed tomography images for ventricular tachycardia ablation planning

Lecture Notes in Computer Science

Sermesant

2020

Self Cite

In this manuscript, we personalise an Eikonal model of cardiac wave front propagation using data acquired during an invasive electrophysiological study. To this end, we use a genetic algorithm to determine the parameters that provide the best fit between simulated and recorded activation maps during sinus rhythm. We propose a way to parameterise the Eikonal simulations that take into account the Purkinje network and the septomarginal trabecula influences while keeping the computational cost low. We then re-use these parameters to predict the cardiac resynchronisation therapy electrophysiological response by adapting the simulation initialisation to the pacing locations. We experiment different divisions of the myocardium on which the propagation velocities have to be optimised. We conclude that separating both ventricles and both endocardia seems to provide a reasonable personalisation framework in terms of accuracy and predictive power.

Section: Introductionmentioning

confidence: 99%

Eikonal Model Personalisation Using Invasive Data to Predict Cardiac Resynchronisation Therapy Electrophysiological Response

Lecture Notes in Computer Science

Sermesant

2020

Self Cite

“…We simulated cardiac activation maps and BSP data using the Eikonal Model directly on a Cartesian grid from image segmentation [1]. The Eikonal model is a fast generic model of wave front propagation.…”

Section: Ecgi Forward Problem: Data Simulationmentioning

confidence: 99%

Deep Learning Formulation of ECGI for Data-Driven Integration of Spatiotemporal Correlations and Imaging Information

Bacoyannis

Krebs

Lecture Notes in Computer Science

et al. 2019

Self Cite

The challenge of non-invasive Electrocardiographic Imaging (ECGI) is to recreate the electrical activity of the heart using body surface potentials. Specifically, there are numerical difficulties due to the ill-posed nature of the problem. We propose a novel method based on Conditional Variational Autoencoders using Deep generative Neural Networks to overcome this challenge. By conditioning the electrical activity on heart shape and electrical potentials, our model is able to generate activation maps with good accuracy on simulated data (mean square error, MSE = 0.095). This method differs from other formulations because it naturally takes into account spatio-temporal correlations as well as the imaging substrate through convolutions and conditioning. We believe these features can help improving ECGI results.

“…It indeed requires to solve a partial differential equation using the endocardium and epicardum masks [12]. Such approach, which assign a thickness value to each voxel of the LV wall mask, is particularly adapted for simulations on regular grids; it has been previously used to such ends [1].…”

Section: Thickness Computationmentioning

confidence: 99%

“…We used the thickness information to parameterise an Eikonal model previously described in [1]. Briefly, wall thinning is related to a macroscopic slowing of the activation front, due to a microscopic zig-zag course of activation in the infarcted tissue.…”

Section: Electrophysiological Modelmentioning

confidence: 99%

“…Given these scar characteristics on CT images, it is no surprise that CT has been successfully used as a way to personalise EP models [1]. However, up until now, this personalisation relies on manual or semi-automated segmentation of the left ventricular (LV) wall, despite the availability of efficient three-dimensional medical image automated segmentation methods [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automated Electrophysiological Model Personalisation Framework from CT Imaging

Functional Imaging and Modeling of the Heart

Duchâteau

Sacher

et al. 2019

Self Cite

There has been a recent growing interest for cardiac computed tomography (CT) imaging in the electrophysiological community. This imaging modality indeed allows to locate and assess post-infarct scar heterogeneity, allowing to predict zones of abnormal electrical activity and even personalise EP models. To this end, most of the literature uses manually segmented CT images where one fundamental information is extracted, the myocardial wall thickness. In this paper, we evaluate the impact of using an automated deep learning (DL) methodology to segment the left ventricular wall and extract relevant scar information on the resulting personalised models. Using CT images from 8 patients that were not used during the DL training, we show that the automated segmentation is very similar to the manual one (median Dice score: 0.9). Thickness information obtained this way is also very close to the manual one (median difference: 0.7 mm). A wavefront propagation model personalisation framework based on this thickness information does not show relevant differences in its output (median difference in local activation time: 2 ms), proving its robustness. Bipolar electrograms, simulated through a novel approach, do not differ significantly between manual and automated segmentations (Pearson's r: 0.99).