BrainGB
收藏资源简介:
BrainGB是一个专为大脑网络分析设计的基准数据集,由埃默里大学计算机科学系的研究团队开发。该数据集标准化了功能和结构神经影像模态的大脑网络构建流程,并模块化了图神经网络(GNN)设计的实现。BrainGB通过广泛的实验,推荐了一套通用的大脑网络GNN设计方案。数据集支持开放和可重复的研究,提供模型、教程、示例以及一个即用的Python包,旨在为这一新兴且有前景的研究方向提供有用的实证证据和见解。
BrainGB is a benchmark dataset dedicated to brain network analysis, developed by the research team from the Department of Computer Science at Emory University. This dataset standardizes the workflow for constructing brain networks across functional and structural neuroimaging modalities, and modularizes the implementation of graph neural network (GNN) designs. Through extensive experiments, BrainGB has recommended a universal GNN design framework for brain network research. The dataset supports open and reproducible research, and provides models, tutorials, examples, and a ready-to-use Python package, aiming to provide valuable empirical evidence and insights for this emerging and promising research direction.




