Spatio-temporal Dynamics of Intrinsic Networks in Functional Magnetic Imaging Data Using Recurrent Neural Networks
This work addresses the challenge of dynamically analyzing brain networks in fMRI for neuroscience and medical research, representing an incremental advancement by applying a novel method to a known bottleneck in static network analysis.
The authors tackled the problem of characterizing temporal dynamics in brain networks from fMRI data by introducing RNN-ICA, a recurrent neural network approach that models temporal dependencies for blind source separation, enabling visualization of activity and directed connectivity dynamics; results demonstrated task-related and group-differentiating directed connectivity.
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.