AUTHOR=Zhong Gaoyan , Feng Xujian , Yuan Han , Yang Cuiwei 

TITLE=A 3D-CNN with temporal-attention block to predict the recurrence of atrial fibrillation based on body-surface potential mapping signals

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.1030307

DOI=10.3389/fphys.2022.1030307

ISSN=1664-042X

ABSTRACT=Catheter ablation has become an important treatment for atrial fibrillation (AF), but its recurrence rate is still high. The aim of this study was to predict AF recurrence using a three-dimensional (3D) network model based on body surface potential mapping (BSPM) signals. BSPM signals were recorded with a 128-lead vest in 14 persistent AF patients before undergoing catheter ablation (Maze-IV). The torso geometry was acquired and meshed by point cloud technology, and the BSPM signal is interpolated to the torso geometry by inverse distance weighted (IDW) interpolation method to generate the isopotential map. Experiments show that the isopotential map of BSPM signals can reflect the electrical wavefronts propagating. The 3D isopotential sequence map was established by combining the spatial-temporal information of the isopotential map, and a 3D convolutional neural network (3D-CNN) model with temporal-attention was established to predict AF recurrence. In this paper, we propose a novel attention-block focused the characteristics of atrial activations to improve sampling accuracy. In our experiment, the accuracy (ACC) in the intra-patient evaluation for predicting the recurrence of AF was 99.38%. In the inter-patient evaluation, the ACC of 3D-CNN was 81.48%, and the area under the curve (AUC) was 0.88. It can be concluded that the dynamic rendering of multiple isopotential maps can not only comprehensively display the conduction of cardiac electrical activity on body surface, but also successfully predict the recurrence of AF after CA by using the 3D isopotential sequence maps.