Unifying blind separation and clustering for resting-state EEG/MEG functional connectivity analysis

View Researcher II's Other Codes

Disclaimer: “The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).”

Please contact us in case of a broken link from here

Authors J. Hirayama, T. Ogawa and A. Hyvärinen
Journal/Conference Name Neural Computation
Paper Category
Paper Abstract Unsupervised analysis of the dynamics (non-stationarity) of functional brain connectivity during rest has recently received a lot of attention in both the neuroimaging and neuroengineering communities. Most studies have used functional magnetic resonance imaging (fMRI), but electroencephalography (EEG) and magnetoencephalography (MEG) also hold great promise for analyzing non-stationary functional connectivity with high temporal resolution. However, previous EEG/MEG analyses divided the problem into two consecutive stages: first, the separation of neural sources, and second, the connectivity analysis of the separated sources. Such non-optimal division into two stages may bias the result because of the different prior assumptions made about the data in the two stages. Here, we propose a unified method for separating EEG/MEG sources and learning their functional connectivity (coactivation) patterns. We combine blind source separation (BSS) with unsupervised clustering of the activity levels of the sources in a single probabilistic model. A BSS is performed on the Hilbert transforms of band-limited EEG/MEG signals, and coactivation patterns are learned by a mixture model of source envelopes. Simulation studies show that the unified approach often outperforms conventional two-stage methods, further indicating the benefit of using Hilbert transforms to deal with oscillatory sources. Experiments on resting-state EEG data, acquired in conjunction with a cued motor imagery/non-imagery task, also show that the states (clusters) obtained by the proposed method often correlate better with physiologically meaningful quantities than those obtained by a two-stage method.
Date of publication 2015
Code Programming Language MATLAB

Copyright Researcher II 2022