Multi-View Brain HyperConnectome

Graph embedding is a powerful method to represent graph neurological data (e.g., brain connectomes) in a low dimensional space for brain connectivity mapping, prediction and classification. However, existing embedding algorithms have two major limitations. First, they primarily focus on preserving one-to-one topological relationships between nodes (i.e., regions of interest (ROIs) in a connectome), but they have mostly ignored many-to-many relationships (i.e., set to set), which can be captured using a hyperconnectome structure. Second, existing graph embedding techniques cannot be easily adapted to multi-view graph data with heterogeneous distributions. In this paper, while cross-pollinating adversarial deep learning with hypergraph theory, we aim to jointly learn deep latent embeddings of subject-specific multi-view brain graphs to eventually disentangle different brain states such as Alzheimer’s disease (AD) versus mild cognitive impairment (MCI). First, we propose a new simple strategy to build a hyperconnectome for each brain view based on nearest neighbour algorithm to preserve the con-nectivities across pairs of ROIs. Second, we design a hyperconnectome autoencoder (HCAE) framework which operates directly on the multi-view hyperconnectomes based on hypergraph convolutional layers to better capture the many-to-many relationships between brain regions (i.e., graph nodes). For each subject, we further regularize the hyper-graph autoencoding by adversarial regularization to align the distribution of the learned hyperconnectome embeddings with the original hyperconnectome distribution. We formalize our hyperconnectome embedding within a geometric deep learning framework to optimize for a given subject, thereby designing an individual-based learning framework.

图嵌入（Graph Embedding）是一类将神经图数据（如脑连接组（brain connectomes））映射至低维空间的有效方法，可用于脑连接映射、预测与分类任务。然而现有嵌入算法存在两大核心局限：其一，多数算法仅致力于保留节点（即脑连接组中的感兴趣脑区（regions of interest, ROIs））间的一对一拓扑关系，却大多忽略了多对多关系（即集合间关系），而这类关系可通过超连接组（hyperconnectome）结构进行捕捉；其二，现有图嵌入技术难以适配具有异质分布的多视图图数据。本文将对抗式深度学习与超图理论交叉融合，旨在联合学习个体特异性多视图脑图的深层潜在嵌入，最终实现不同脑状态的解耦区分，例如阿尔茨海默病（Alzheimer’s disease, AD）与轻度认知障碍（mild cognitive impairment, MCI）。首先，我们提出一种简洁的新策略：基于最近邻算法为每个脑视图构建超连接组，以保留成对感兴趣脑区之间的连接特性。其次，我们设计了超连接组自编码器（hyperconnectome autoencoder, HCAE）框架，该框架可直接基于超图卷积层处理多视图超连接组，从而更好地捕捉脑区（即图节点）间的多对多关系。针对每个受试者，我们进一步通过对抗正则化对超图自编码过程施加约束，使学习得到的超连接组嵌入分布与原始超连接组分布保持一致。我们将超连接组嵌入形式化为几何深度学习框架下的优化问题，以针对单个受试者进行优化，由此构建了基于个体的学习框架。