期刊
FRONTIERS IN PHYSIOLOGY
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fphys.2021.686136
关键词
data-driven approaches; physics-based approaches; ECGI inverse problem; cardiac activation mapping; neural networks; deep learning
类别
资金
- French National Research Agency [ANR-10-IAHU04-LIRYC, ANR-11-EQPX-0030]
By comparing data-driven and traditional methods for cardiac arrhythmia diagnosis, the study found that the data-driven approach outperforms the classic technique and demonstrates greater robustness against noise.
One of the essential diagnostic tools of cardiac arrhythmia is activation mapping. Noninvasive current mapping procedures include electrocardiographic imaging. It allows reconstructing heart surface potentials from measured body surface potentials. Then, activation maps are generated using the heart surface potentials. Recently, a study suggests to deploy artificial neural networks to estimate activation maps directly from body surface potential measurements. Here we carry out a comparative study between the data-driven approach DirectMap and noninvasive classic technique based on reconstructed heart surface potentials using both Finite element method combined with L1-norm regularization (FEM-L1) and the spatial adaptation of Time-delay neural networks (SATDNN-AT). In this work, we assess the performance of the three approaches using a synthetic single paced-rhythm dataset generated on the atria surface. The results show that data-driven approach DirectMap quantitatively outperforms the two other methods. In fact, we observe an absolute activation time error and a correlation coefficient, respectively, equal to 7.20 ms, 93.2% using DirectMap, 14.60 ms, 76.2% using FEM-L1 and 13.58 ms, 79.6% using SATDNN-AT. In addition, results show that data-driven approaches (DirectMap and SATDNN-AT) are strongly robust against additive gaussian noise compared to FEM-L1.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据