Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes
Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Lingge Li;Dustin S. Pluta;B. Shahbaba;N. Fortin;H. Ombao;P. Baldi
中科院分区：
文献类型：
--
作者：
Lingge Li;Dustin S. Pluta;B. Shahbaba;N. Fortin;H. Ombao;P. Baldi
动态功能连通性是通过神经信号的时变协方差来衡量的，被认为在认知的许多方面起着重要作用。虽然已经提出了许多方法，但由于神经成像数据的高维性和噪声，可靠地建立大脑连接的存在和特征是具有挑战性的。我们提出了一个潜在因素高斯过程模型，该模型通过学习连接动态的简约表示来解决这些挑战。所提出的模型自然地允许连接动态的推理和可视化。为了说明该模型的科学实用性，应用于在复杂的非空间记忆任务中记录的大鼠局部场电位活动数据集，提供了刺激分化的证据。
Dynamic functional connectivity, as measured by the time-varying covariance of neurological signals, is believed to play an important role in many aspects of cognition. While many methods have been proposed, reliably establishing the presence and characteristics of brain connectivity is challenging due to the high dimensionality and noisiness of neuroimaging data. We present a latent factor Gaussian process model which addresses these challenges by learning a parsimonious representation of connectivity dynamics. The proposed model naturally allows for inference and visualization of connectivity dynamics. As an illustration of the scientific utility of the model, application to a data set of rat local field potential activity recorded during a complex non-spatial memory task provides evidence of stimuli differentiation.