Physics-Informed Neural Networks for Cardiac Activation Mapping
Physics-Informed Neural Networks for Cardiac Activation Mapping
复制标题
DOI：
10.3389/fphy.2020.00042
复制
发表时间：
2020-02-28
影响因子：
3.1
通讯作者：
Kuhl, Ellen
中科院分区：
文献类型：
--
作者：
Costabal, Francisco Sahli;Yang, Yibo;Kuhl, Ellen
诊断心房颤动的一个关键步骤是创建电解剖激活图。目前的方法是使用记录在心房内部的一些稀疏数据点从插值中生成这些映射；它们既不包括对潜在物理的先验知识，也不包括这些录音的不确定性。在这里，我们提出了一个物理信息的神经网络，用于心脏激活映射，该网络解释了潜在的波传播动力学，我们量化了与这些预测相关的认知不确定性。这些不确定性估计不仅使我们能够量化神经网络的预测误差，而且还有助于通过主动学习明智地选择新的信息测量位置来减少它。我们使用一个合成基准问题和一个个性化的左心房电生理模型来说明我们的方法的潜力。我们表明，我们的新方法优于基准问题的线性插值和高斯过程回归，以及左心房临床密度的线性插值。在这两种情况下，主动学习算法的误差水平都比随机分配低。我们的发现为基于物理的电解剖定位打开了大门，最终目标是减少手术时间，提高心房颤动患者的诊断可预测性。开源代码可从https://github.com/fsahli/EikonalNet获得。
A critical procedure in diagnosing atrial fibrillation is the creation of electro-anatomic activation maps. Current methods generate these mappings from interpolation using a few sparse data points recorded inside the atria; they neither include prior knowledge of the underlying physics nor uncertainty of these recordings. Here we propose a physics-informed neural network for cardiac activation mapping that accounts for the underlying wave propagation dynamics and we quantify the epistemic uncertainty associated with these predictions. These uncertainty estimates not only allow us to quantify the predictive error of the neural network, but also help to reduce it by judiciously selecting new informative measurement locations via active learning. We illustrate the potential of our approach using a synthetic benchmark problem and a personalized electrophysiology model of the left atrium. We show that our new method outperforms linear interpolation and Gaussian process regression for the benchmark problem and linear interpolation at clinical densities for the left atrium. In both cases, the active learning algorithm achieves lower error levels than random allocation. Our findings open the door toward physics-based electro-anatomic mapping with the ultimate goals to reduce procedural time and improve diagnostic predictability for patients affected by atrial fibrillation. Open source code is available at https://github.com/fsahli/EikonalNet.