A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in resting-state functional MRI Data
A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in resting-state functional MRI Data
复制标题
DOI：
10.1101/2020.11.08.370288
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Tiago Azevedo;Alexander Campbell;R. Romero-García;L. Passamonti;R. Bethlehem;P. Lio’;N. Toschi
中科院分区：
文献类型：
--
作者：
Tiago Azevedo;Alexander Campbell;R. Romero-García;L. Passamonti;R. Bethlehem;P. Lio’;N. Toschi
静息状态功能磁共振成像（rs-fMRI）已经成功地用于了解人类大脑的组织。对于rs-fMRI分析，大脑通常被分割成感兴趣区域（ROI），并建模为一个图，其中每个ROI是一个节点，ROI血氧水平依赖（BOLD）时间序列之间的成对相关性是边缘。最近，图神经网络（gnn）因其在非结构化关系数据建模方面的成功而受到广泛欢迎。然而，gnn的最新发展尚未被充分利用于rs-fMRI数据的分析，特别是关于其时空动态。在这里，我们提出了一种新的深度神经网络架构，结合了gnn和时间卷积网络（tcn），它能够以端到端的方式从rs-fMRI数据的空间和时间成分中学习。特别是，这对应于特征内学习（即使用tcn学习时间动态）以及特征间学习（即利用roi与gnn之间的空间交互）。我们使用来自英国生物银行rs-fMRI数据库的35,159个样本进行消融研究来评估我们的模型。我们还展示了我们的架构的可解释性特征，这些特征映射到现实的神经生物学见解。我们希望我们的模型可以为未来的深度学习架构奠定基础，这些架构专注于利用rs-fMRI数据固有的和不可分割的时空性质。
Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. For rs-fMRI analysis, the brain is typically parcellated into regions of interest (ROIs) and modelled as a graph where each ROI is a node and pairwise correlation between ROI blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their successes in modelling unstructured relational data. The latest developments with GNNs, however, have not yet been fully exploited for the analysis of rs-fMRI data, particularly with regards to its spatio-temporal dynamics. Herein we present a novel deep neural network architecture, combining both GNNs and temporal convolutional networks (TCNs), which is able to learn from the spatial and temporal components of rs-fMRI data in an end-to-end fashion. In particular, this corresponds to intra-feature learning (i.e., learning temporal dynamics with TCNs) as well as inter-feature learning (i.e., leveraging spatial interactions between ROIs with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database. We also demonstrate explainability features of our architecture which map to realistic neurobiological insights. We hope our model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.