A deep learning model for data-driven discovery of functional connectivity

TL;DR

This paper introduces BrainGNN, a deep learning model that learns brain connectivity directly from fMRI data for improved classification of disorders like schizophrenia, providing interpretable insights aligned with existing neuroscience findings.

Contribution

The paper presents a novel deep learning architecture that jointly learns functional connectivity and performs classification, reducing reliance on manual FC computation and post-hoc analysis.

Findings

State-of-the-art schizophrenia classification accuracy

Learned connectivity graphs show strong class discrimination

Identified brain regions consistent with schizophrenia literature

Abstract

Functional connectivity (FC) studies have demonstrated the overarching value of studying the brain and its disorders through the undirected weighted graph of fMRI correlation matrix. Most of the work with the FC, however, depends on the way the connectivity is computed, and further depends on the manual post-hoc analysis of the FC matrices. In this work we propose a deep learning architecture BrainGNN that learns the connectivity structure as part of learning to classify subjects. It simultaneously applies a graphical neural network to this learned graph and learns to select a sparse subset of brain regions important to the prediction task. We demonstrate the model's state-of-the-art classification performance on a schizophrenia fMRI dataset and demonstrate how introspection leads to disorder relevant findings. The graphs learned by the model exhibit strong class discrimination and the sparse subset of relevant regions are consistent with the schizophrenia literature.