Brain network constraints and recurrent neural networks reproduce unique trajectories and state transitions seen over the span of minutes in resting-state fMRI
Brain network constraints and recurrent neural networks reproduce unique trajectories and state transitions seen over the span of minutes in resting-state fMRI
复制标题
DOI：
10.1162/netn_a_00129
复制
发表时间：
2020-01-01
影响因子：
4.7
通讯作者：
Keilholz, Shella
中科院分区：
文献类型：
--
作者：
Kashyap, Amrit;Keilholz, Shella
在静息态功能磁共振成像 (rs-fMRI) 中看到的大规模自发全脑活动模式部分被认为是由通过结构网络相互作用的神经群体引起的 (Honey, Kotter, Breakspear, & Sporns, 2007)。模拟这种网络活动的生成模型称为脑网络模型 (BNM)，能够重现经验 rs-fMRI 活动的全局平均属性，例如功能连接 (FC)，但在重现全脑数据中在几分钟内观察到的独特轨迹和状态转换方面表现不佳（Cabral、Kringelbach 和 Deco，2017 年；Kashyap 和 Keilholz，2019 年）。该手稿表明，通过使用循环神经网络，它可以以一种新颖的方式将 BNM 拟合到 rs-fMRI 数据，并预测 rs-fMRI 数据后续测量之间的大量方差。模拟数据还包含在 rs-fMRI 中观察到的独特重复轨迹，称为准周期模式 (QPP)，跨越 20 秒，以及使用加窗 FC 矩阵的 k 均值分析观察到的复杂状态转换（Allen 等人，2012 年；Majeed 等人，2011 年）。我们的方法能够通过生成后续时间点的训练来估计 rs-fMRI 动力学的流形，并且它可以比传统的生成方法更好地模拟复杂的静息态轨迹。作者摘要脑网络模型已成为一种有前途的理论框架，用于模拟代表全脑活动的信号，例如静息态功能磁共振成像。然而，很难将模拟获得的复杂大脑活动与经验数据进行比较。先前的研究使用简单的指标来表征区域之间的协调，例如功能连接性。在这份手稿中，我们通过利用现代机器学习技术来扩展这项工作，使大脑网络模型适合观察到的数据，并针对模型和观察到的信号之间的不匹配进行训练。我们的结果表明，我们对这些新指标的系统训练可以推广到一个能够在几分钟内重现 rs-fMRI 中看到的轨迹和复杂状态转换的系统。我们的结果将有助于约束和开发更真实的全脑活动模拟。
Large-scale patterns of spontaneous whole-brain activity seen in resting-state functional magnetic resonance imaging (rs-fMRI) are in part believed to arise from neural populations interacting through the structural network (Honey, Kotter, Breakspear, & Sporns, 2007). Generative models that simulate this network activity, called brain network models (BNM), are able to reproduce global averaged properties of empirical rs-fMRI activity such as functional connectivity (FC) but perform poorly in reproducing unique trajectories and state transitions that are observed over the span of minutes in whole-brain data (Cabral, Kringelbach, & Deco, 2017; Kashyap & Keilholz, 2019). The manuscript demonstrates that by using recurrent neural networks, it can fit the BNM in a novel way to the rs-fMRI data and predict large amounts of variance between subsequent measures of rs-fMRI data. Simulated data also contain unique repeating trajectories observed in rs-fMRI, called quasiperiodic patterns (QPP), that span 20 s and complex state transitions observed using k-means analysis on windowed FC matrices (Allen et al., 2012; Majeed et al., 2011). Our approach is able to estimate the manifold of rs-fMRI dynamics by training on generating subsequent time points, and it can simulate complex resting-state trajectories better than the traditional generative approaches. Author SummaryBrain network models have become a promising theoretical framework for simulating signals that are representative of whole-brain activity such as resting-state fMRI. However, it has been difficult to compare the complex brain activity obtained from simulations with empirical data. Previous studies have used simple metrics to characterize coordination between regions such as functional connectivity. In this manuscript, we extend this work by utilizing modern machine learning techniques to fit the brain network models to observed data and train on the mismatch between the model and observed signal. Our results show that our system training on these new metrics generalizes to a system that is able to reproduce trajectories and complex state transitions seen in rs-fMRI over the span of minutes. Our results will be useful in constraining and developing more realistic simulations of whole-brain activity.