BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks

Abstract

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data. Despite their established performance in other fields, there has not yet been a systematic study of how to design effective GNNs for brain network analysis. To bridge this gap, we present BrainGB, a benchmark for brain network analysis with GNNs. BrainGB standardizes the process by 1) summarizing brain network construction pipelines for both functional and structural neuroimaging modalities and 2) modularizing the implementation of GNN designs. We conduct extensive experiments on datasets across cohorts and modalities and recommend a set of general recipes for effective GNN designs on brain networks. To support open and reproducible research on GNN-based brain network analysis, we also host the BrainGB website at https:// brainnet.us/ with models, tutorials, examples, as well as an out-of-box Python package. We hope that this work will provide useful empirical evidence and offer insights for future research in this novel and promising direction.

Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis

“…Recently, Graph Neural Networks (GNNs) attract broad interest due to their established power for analyzing graph-structured data [19,34]. Compared with shallow models, GNNs are suitable for brain network analysis with universal expressiveness to capture the sophisticated connectome structures [4,26,38,43]. However, GNNs as a family of deep models are prone to overfitting and lack transparency in predictions, preventing their usage in decision-critical areas like disorder analysis.…”