Rapid prediction of cardiac activation in the left ventricle with geometric deep learning: a step towards cardiac resynchronization therapy planning

TL;DR

This paper introduces geometric deep learning models, GNN and GINO, to predict cardiac activation maps in real time, aiding personalized planning for cardiac resynchronization therapy and addressing current limitations in lead placement.

Contribution

The study develops and compares GNN and GINO models trained on synthetic and real data to predict LV activation times, advancing in-silico CRT planning tools.

Findings

GINO outperforms GNN on synthetic data (1.38% vs 2.44% error)

Both models perform comparably on real-world data (~4.7% error)

The models can identify optimal pacing sites and recover parameters from noisy inputs.

Abstract

Cardiac resynchronization therapy (CRT) is a common intervention for patients with dyssynchronous heart failure, yet approximately one-third of recipients fail to respond, partly due to suboptimal lead placement. Identifying optimal pacing sites remains challenging, largely due to patient-specific anatomical variability and limitations of current individualized planning strategies. In a step toward an in-silico approach, we develop two geometric deep learning models, based on graph neural network (GNN) and geometry-informed neural operator (GINO), to predict activation time maps on left ventricular (LV) geometries in real time. Trained on a large dataset generated from finite-element simulations spanning a wide range of synthetic LV shapes, pacing site configurations, and tissue conductivities, the GINO model outperforms the GNN on synthetic cases (1.38% vs 2.44% error), while both demonstrate comparable performance on real-world LV geometries (GINO: 4.79% vs GNN: 4.07%). Using the trained models, we develop a workflow to identify an optimal pacing site on the LV from a given activation time map and show that both models can robustly recover ground-truth subject-specific parameters from noisy inputs. In conjunction with an interactive web-based interface (https://dcsim.egr.msu.edu/), this study shows potential and motivates future extension toward a clinical decision-support tool for personalized pre-procedural CRT optimization.