Mejia Amanda F, Yue Yu Ryan, Bolin David, Lindgren Finn, Lindquist Martin A
Indiana University, Bloomington, IN 47405.
Baruch College, The City University of New York, New York, NY 10010.
J Am Stat Assoc. 2020;115(530):501-520. doi: 10.1080/01621459.2019.1611582. Epub 2019 Jun 12.
Cortical surface fMRI (cs-fMRI) has recently grown in popularity versus traditional volumetric fMRI. In addition to offering better whole-brain visualization, dimension reduction, removal of extraneous tissue types, and improved alignment of cortical areas across subjects, it is also more compatible with common assumptions of Bayesian spatial models. However, as no spatial Bayesian model has been proposed for cs-fMRI data, most analyses continue to employ the classical general linear model (GLM), a "massive univariate" approach. Here, we propose a spatial Bayesian GLM for cs-fMRI, which employs a class of sophisticated spatial processes to model latent activation fields. We make several advances compared with existing spatial Bayesian models for volumetric fMRI. First, we use integrated nested Laplacian approximations (INLA), a highly accurate and efficient Bayesian computation technique, rather than variational Bayes (VB). To identify regions of activation, we utilize an excursions set method based on the joint posterior distribution of the latent fields, rather than the marginal distribution at each location. Finally, we propose the first multi-subject spatial Bayesian modeling approach, which addresses a major gap in the existing literature. The methods are very computationally advantageous and are validated through simulation studies and two task fMRI studies from the Human Connectome Project.
与传统的容积功能磁共振成像（v-fMRI）相比，皮质表面功能磁共振成像（cs-fMRI）最近越来越受欢迎。除了能提供更好的全脑可视化、降维、去除无关组织类型以及改善不同受试者皮质区域的对齐外，它还更符合贝叶斯空间模型的常见假设。然而，由于尚未针对cs-fMRI数据提出空间贝叶斯模型，大多数分析仍继续采用经典的一般线性模型（GLM），即一种“大规模单变量”方法。在此，我们提出了一种用于cs-fMRI的空间贝叶斯GLM，它采用一类复杂的空间过程来对潜在激活场进行建模。与现有的用于容积功能磁共振成像的空间贝叶斯模型相比，我们取得了多项进展。首先，我们使用积分嵌套拉普拉斯近似（INLA），这是一种高度准确且高效的贝叶斯计算技术，而不是变分贝叶斯（VB）。为了识别激活区域，我们利用基于潜在场联合后验分布的游程集方法，而不是每个位置的边际分布。最后，我们提出了第一种多受试者空间贝叶斯建模方法，填补了现有文献中的一个主要空白。这些方法在计算上非常有利，并通过模拟研究和来自人类连接体项目的两项任务功能磁共振成像研究进行了验证。
