Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning.
Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning.
复制标题
DOI：
10.3389/fphys.2021.740306
复制
发表时间：
2021
影响因子：
4
通讯作者：
Wang L
中科院分区：
文献类型：
--
作者：
Zaman MS;Dhamala J;Bajracharya P;Sapp JL;Horácek BM;Wu KC;Trayanova NA;Wang L
心脏电生理模型参数的概率估计是实现模型个性化和不确定量化的重要步骤。然而，与这些模型模拟相关的昂贵计算使得模型参数的后验概率密度函数（pdf）的直接马尔可夫链蒙特卡罗（MCMC）采样计算量很大。另一方面，用计算效率高的代理替代模拟模型所产生的近似后验pdf的精度有限。在本研究中，我们提出了一种直接近似心脏模型参数后验pdf函数的贝叶斯主动学习方法，该方法通过使用少量样本，智能选择训练点查询仿真模型，从而学习后验pdf。我们将生成模型集成到贝叶斯主动学习中，以便在心脏网格的分辨率下近似高维模型参数的后验pdf。我们进一步引入了新的获取函数，将训练点的选择集中在更好地接近形状上，而不是关注后验pdf的模式。我们在一系列合成和实际数据实验中评估了在三维心脏电生理模型中估计组织兴奋性的方法。我们证明了与使用常规获取函数的贝叶斯主动学习相比，它在近似后验pdf方面的准确性有所提高，并且与现有的标准或加速MCMC采样相比，它大大降低了计算成本。
Probabilistic estimation of cardiac electrophysiological model parameters serves an important step toward model personalization and uncertain quantification. The expensive computation associated with these model simulations, however, makes direct Markov Chain Monte Carlo (MCMC) sampling of the posterior probability density function (pdf) of model parameters computationally intensive. Approximated posterior pdfs resulting from replacing the simulation model with a computationally efficient surrogate, on the other hand, have seen limited accuracy. In this study, we present a Bayesian active learning method to directly approximate the posterior pdf function of cardiac model parameters, in which we intelligently select training points to query the simulation model in order to learn the posterior pdf using a small number of samples. We integrate a generative model into Bayesian active learning to allow approximating posterior pdf of high-dimensional model parameters at the resolution of the cardiac mesh. We further introduce new acquisition functions to focus the selection of training points on better approximating the shape rather than the modes of the posterior pdf of interest. We evaluated the presented method in estimating tissue excitability in a 3D cardiac electrophysiological model in a range of synthetic and real-data experiments. We demonstrated its improved accuracy in approximating the posterior pdf compared to Bayesian active learning using regular acquisition functions, and substantially reduced computational cost in comparison to existing standard or accelerated MCMC sampling.
登录
查看更多内容
影响因子：
10.9
作者：
Dhamala J;Arevalo HJ;Sapp J;Horácek BM;Wu KC;Trayanova NA;Wang L
通讯作者：
Wang L
影响因子：
10.6
作者：
Chinchapatnam, Phani;Rhode, Kawal S.;Sermesant, Maxime
通讯作者：
Sermesant, Maxime
DOI：
10.1198/106186006x100579
发表时间：
2006-03-01
影响因子：
2.4
作者：
Brockwell, AE
通讯作者：
Brockwell, AE
影响因子：
7.8
作者：
Aliev, RR;Panfilov, AV
通讯作者：
Panfilov, AV
影响因子：
16.6
作者：
Arevalo HJ;Vadakkumpadan F;Guallar E;Jebb A;Malamas P;Wu KC;Trayanova NA
通讯作者：
Trayanova NA