Spatio-temporal Dynamics of Intrinsic Networks in Functional Magnetic Imaging Data Using Recurrent Neural Networks

TL;DR

This paper presents RNN-ICA, a novel recurrent neural network method that models and visualizes the dynamic temporal and directed connectivity patterns in brain networks from fMRI data, capturing both activity and connectivity changes.

Contribution

The paper introduces RNN-ICA, a new approach that directly models temporal dynamics and directed connectivity in brain networks using recurrent neural networks, enabling dynamic visualization.

Findings

RNN-ICA predicts task-related brain dynamics.

It reveals group differences in directed connectivity.

The method captures both activity and connectivity changes over time.

Abstract

We introduce a novel recurrent neural network (RNN) approach to account for temporal dynamics and dependencies in brain networks observed via functional magnetic resonance imaging (fMRI). Our approach directly parameterizes temporal dynamics through recurrent connections, which can be used to formulate blind source separation with a conditional (rather than marginal) independence assumption, which we call RNN-ICA. This formulation enables us to visualize the temporal dynamics of both first order (activity) and second order (directed connectivity) information in brain networks that are widely studied in a static sense, but not well-characterized dynamically. RNN-ICA predicts dynamics directly from the recurrent states of the RNN in both task and resting state fMRI. Our results show both task-related and group-differentiating directed connectivity.