graph-classification-g2i

A Novel Functional Brain Connectivity Network Classification Method

Story:

Connections in the human brain can be examined efficiently using brain imaging techniques such as Diffusion Tensor Imaging (DTI), Resting-State fMRI. Brain connectivity networks are constructed by using image processing and statistical methods, these networks explain how brain regions interact with each other. Brain networks can be used to train machine learning models that can help the diagnosis of neurological disorders.

In functional brain graphs, the nodes describe the regions and the edge weights correspond to the values of correlation coefficients of the time-series of the two nodes associated with the edges.

Task:

Functional Brain Connectivity Network Classification for ASD Screening

Method:

Convert graph classification to image classification based on this paper.you can see some images obtained from the brain functional network:

Dataset:

UCLA Dataset

Requirments:

• python3
• sklearn
• networkx 2.1
• numpy

Run:

Download ASD and TD FMRI connectivity networks from UCLA Dataset and set paths to those folders in conf.ini file.

command:
python demo.py -c [path to conf.ini]