# Neural network reconstruction of the left atrium using sparse catheter paths

## TL;DR

This paper introduces a neural network that reconstructs the left atrium from sparse catheter data, reducing mapping time during heart procedures.

## Contribution

A novel encoder-decoder network with regularization for fast and accurate 3D atrium reconstruction from sparse catheter paths.

## Key findings

- The proposed network reconstructs realistic left atrium shapes from sparse catheter data in under 3 minutes.
- The method outperforms other network solutions in 3D atrium reconstruction accuracy and speed.
- The approach uses a large dataset of 3D atria and simulated catheter trajectories for training.

## Abstract

Catheter-based radiofrequency ablation for pulmonary vein isolation has become the first line of treatment for atrial fibrillation in recent years. This requires a rather accurate map of the left atrial sub-endocardial surface including the ostia of the pulmonary veins, which requires dense sampling of the surface and currently takes more than 10 min. The focus of this work is to provide left atrial visualization early in the procedure to ease procedure complexity and enable further workflows, such as using catheters that have difficulty sampling the surface.

We propose a dense encoder–decoder network with a novel regularization term to reconstruct the shape of the left atrium from partial data which is derived from simple catheter maneuvers. To train the network, we acquire a large dataset of 3D atria shapes and generate corresponding catheter trajectories, from which traversed point clouds are obtained. Once trained, we show that the suggested network can sufficiently approximate the atrium shape based on a given trajectory.

We compare several network solutions for the 3D atrium reconstruction. We demonstrate that the solution proposed produces realistic visualization using partial acquisition within a 3-min time interval using human clinical cases.

The online version contains supplementary material available at 10.1007/s11548-024-03268-y.