Graph-In-Graph Convolutional Networks For Brain Disease Diagnosis

Abstract

So far, in the study of neurological brain disorder diagnosis, there are mainly two kinds of work that exploits graph via Graph Convolutional Networks (GCN). Though they have achieved remarkable success, neither of them is able to simultaneously account for the brain region level correlation and subject level correlation. To tackle this issue, we design a Graph-In-Graph Convolutional Networks(GIGCN) framework, which turns out to inherit the merits of the two kinds of existing work. Specifically, we propose a graph-in-graph data structure that consists of two types of graph, namely internal brain connective graph and external population graph. In this data structure, an internal graph is assigned to each subject whose nodes represent brain regions and edges incorporate associations between brain regions, while the external graph is a population graph generated from the demographic of all subjects where edges describe the similarity between subjects. After that, our proposed framework employs GCN to explore some deeper relationships for better disease prediction. Results on the ABIDE dataset validate the effectiveness of our proposed method.

TSP-GNN: a novel neuropsychiatric disorder classification framework based on task-specific prior knowledge and graph neural network

“…In the classification experiments of ADHD and ABIDE datasets, TSP-GNN has obtained the optimal results (Figure 6), and the detailed numerical values of the classification results can be found in Supplementary Tables S2, S3. In comparison to classic machine learning approaches such as SVM (Abraham et al, 2017) and ensemble learning (Liu et al, 2020), GNN models the individual-based topologies structure (Zhou and Zhang, 2021) between subjects utilizing participant similarity, which is advantageous for enhancing classification performance. After numerous layers of graph convolution computation, highly relevant characteristics are continually aggregated .…”

VGA‐Net: Vessel graph based attentional U‐Net for retinal vessel segmentation

“…Existing CNN-based methods focus more on pixel-by-pixel performance and reduce the focus on assessing the graphical similarity of vessels. Learning the graphical structures of vessels not only enhances segmentation accuracy but also yields advantages in subsequent analysis steps [16].…”

“…FIGURE16 Segmentation performance comparison with our approach versus state-of-the-art methods on the STARE First row is about pixel-level approaches (b-d), and second row is about graph-level approaches (e-g).…”

A Deep Probabilistic Spatiotemporal Framework for Dynamic Graph Representation Learning with Application to Brain Disorder Identification

“…Geometric Deep Learning (GDL) (Cao et al, 2020;Bronstein et al, 2017), a sub-branch of deep learning, has become popular in recent years to deal with more complex non-Euclidean data such as brain networks. The graph approach to GDL allows for great flexibility in modelling pairwise communications between brain regions at the subject level (Yan et al, 2019a), group-level relationships based on a population graph (Jiang et al, 2020a), or an ensemble of both (Li et al, 2022;Zhou & Zhang, 2021). However, these studies that use graph neural networks (GNNs) generally consider group-level network topology using phenotypic-based information, or use supervised subject-level embedding learning with pre-calculated population graphs for static brain network classification.…”