A preliminary implementation of BrainGNN. The example presented here is on the public resting-state fMRI ABIDE for the convenience of development. This dataset was different from the ones used in our publication, which are cleaner task-fMRI. Still seeking solutions improve representation learning on the noisy data.

pip

See the requirements.txt for environment configuration.

pip install -r requirements.txt

PYG

To install pyg library, please refer to the document

ABIDE

We treat each fMRI as a brain graph. How to download and construct the graphs?

python 01-fetch_data.py
python 02-process_data.py

Training and testing are integrated in file main.py. To run

python 03-main.py 

If you find the code and dataset useful, please cite our paper.

@article{li2020braingnn,
  title={Braingnn: Interpretable brain graph neural network for fmri analysis},
  author={Li, Xiaoxiao and Zhou,Yuan and Dvornek, Nicha and Zhang, Muhan and Gao, Siyuan and Zhuang, Juntang and Scheinost, Dustin and Staib, Lawrence and Ventola, Pamela and Duncan, James},
  journal={bioRxiv},
  year={2020},
  publisher={Cold Spring Harbor Laboratory}
}