Huang Jinghan, Chung Moo K, Qiu Anqi
Department of Biomedical Engineering, National University of Singapore, Singapore, Singapore.
Department of Biostatistics and Medical Informatics, The University of Wisconsin-Madison, Wisconsin, USA.
Inf Process Med Imaging. 2023 Jun;13939:278-290. doi: 10.1007/978-3-031-34048-2_22. Epub 2023 Jun 8.
This study proposes a novel heterogeneous graph convolutional neural network (HGCNN) to handle complex brain fMRI data at regional and across-region levels. We introduce a generic formulation of spectral filters on heterogeneous graphs by introducing the - Hodge-Laplacian (HL) operator. In particular, we propose Laguerre polynomial approximations of HL spectral filters and prove that their spatial localization on graphs is related to the polynomial order. Furthermore, based on the bijection property of boundary operators on simplex graphs, we introduce a generic topological graph pooling (TGPool) method that can be used at any dimensional simplices. This study designs HL-node, HL-edge, and HL-HGCNN neural networks to learn signal representation at a graph node, edge levels, and both, respectively. Our experiments employ fMRI from the Adolescent Brain Cognitive Development (ABCD; n=7693) to predict general intelligence. Our results demonstrate the advantage of the HL-edge network over the HL-node network when functional brain connectivity is considered as features. The HL-HGCNN outperforms the state-of-the-art graph neural networks (GNNs) approaches, such as GAT, BrainGNN, dGCN, BrainNetCNN, and Hypergraph NN. The functional connectivity features learned from the HL-HGCNN are meaningful in interpreting neural circuits related to general intelligence.
本研究提出了一种新型的异构图卷积神经网络（HGCNN），用于处理区域和跨区域层面复杂的脑功能磁共振成像（fMRI）数据。我们通过引入 - 霍奇 - 拉普拉斯（HL）算子，给出了异构图上谱滤波器的一般公式。特别地，我们提出了HL谱滤波器的拉盖尔多项式近似，并证明了它们在图上的空间局部化与多项式阶数有关。此外，基于单纯形图上边界算子的双射性质，我们引入了一种通用的拓扑图池化（TGPool）方法，该方法可用于任何维度的单纯形。本研究设计了HL节点、HL边和HL - HGCNN神经网络，分别在图节点、边层面以及两者上学习信号表示。我们的实验使用了青少年大脑认知发展（ABCD；n = 7693）的fMRI数据来预测一般智力。我们的结果表明，当将功能性脑连接性作为特征时，HL边网络优于HL节点网络。HL - HGCNN的性能优于诸如GAT、BrainGNN、dGCN、BrainNetCNN和超图神经网络等当前最先进的图神经网络（GNN）方法。从HL - HGCNN学习到的功能性连接特征对于解释与一般智力相关的神经回路具有重要意义。
