RESUMEN
Electroanatomic mapping is the gold standard for the assessment of ventricular tachycardia. Acquiring high resolution electroanatomic maps is technically challenging and may require interpolation methods to obtain dense measurements. These methods, however, cannot recover activation times in the entire biventricular domain. This work investigates the use of graph convolutional neural networks to estimate biventricular activation times from sparse measurements. Our method is trained on more than 15,000 synthetic examples of realistic ventricular depolarization patterns generated by a computational electrophysiology model. Using geometries sampled from a statistical shape model of biventricular anatomy, diverse wave dynamics are induced by randomly sampling scar and border zone distributions, locations of initial activation, and tissue conduction velocities. Once trained, the method accurately reconstructs biventricular activation times in left-out synthetic simulations with a mean absolute error of 3.9 ms ± 4.2 ms at a sampling density of one measurement sample per cm2. The total activation time is matched with a mean error of 1.4 ms ± 1.4 ms. A significant decrease in errors is observed in all heart zones with an increased number of samples. Without re-training, the network is further evaluated on two datasets: (1) an in-house dataset comprising four ischemic porcine hearts with dense endocardial activation maps; (2) the CRT-EPIGGY19 challenge data comprising endo- and epicardial measurements of 5 infarcted and 6 non-infarcted swines. In both setups the neural network recovers biventricular activation times with a mean absolute error of less than 10 ms even when providing only a subset of endocardial measurements as input. Furthermore, we present a simple approach to suggest new measurement locations in real-time based on the estimated uncertainty of the graph network predictions. The model-guided selection of measurement locations allows to reduce by 40% the number of measurements required in a random sampling strategy, while achieving the same prediction error. In all the tested scenarios, the proposed approach estimates biventricular activation times with comparable or better performance than a personalized computational model and significant runtime advantages.
RESUMEN
Cardiac modeling has recently emerged as a promising tool to study pathophysiology mechanisms and to predict treatment outcomes for personalized clinical decision support. Nevertheless, achieving convergence under large deformation and defining a robust meshing for realistic heart geometries remain challenging, especially when maintaining the computational cost reasonable. Smoothed particle hydrodynamics (SPH) appears to be a promising alternative to the finite element method (FEM) since it removes the burden of mesh generation. A point cloud is used where each point (particle) contains all the physical properties that are updated throughout the simulation. SPH was evaluated for solid mechanics applications in the last decade but its capacity to address the challenge of simulating the mechanics of the heart has never been evaluated. In this paper, a total Lagrangian formulation of a corrected SPH was used to solve three solid mechanics problems designed to test important features that a cardiac mechanics solver should have. SPH results, in terms of ventricle displacements and strains, were compared to results obtained with 11 different FEM-based solvers, by using synthetic cardiac data from a benchmark study. In particular, passive dilation and active contraction were simulated in an ellipsoidal left ventricle with the exponential anisotropic constitutive law of Guccione following the direction of fibers. The proposed meshless method is able to reproduce the results of three benchmark problems for cardiac mechanics. Hyperelastic material with fiber orientation and high Poisson ratio allows wall thickening/thinning when large deformation is present.
