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

Abstract

Event Abstract Back to Event Unifying blind separation and clustering for resting-state EEG/MEG functional connectivity analysis Jun-ichiro Hirayama1*, Takeshi Ogawa2 and Aapo Hyvärinen3 1 ATR, Neural Information Analysis Laboratories, Japan 2 ATR, Cognitive Mechanisms Laboratories, Japan 3 University of Helsinki, Department of Computer Science and HIIT, Finland Unsupervised analysis of non-stationary functional brain connectivity during rest has recently received a lot of attention in the field of functional brain imaging. Most studies have used functional magnetic resonance imaging, but electroencephalography (EEG) and magnetoencephalography (MEG) also hold great promise for analyzing nonstationary functional connectivity with high temporal resolution. However, conventional two-stage analyses of resting-state EEG/MEG may be nonoptimal as they divide the problem into two stages making different prior assumptions about the data, i.e., separation of neural sources and subsequent connectivity analysis of the separated sources. Here, we propose a first unifying approach to separating EEG/MEG sources and learning their functional connectivity (coactivation) patterns simultaneously. Specifically, we combine blind source separation (BSS) with unsupervised clustering of the activity levels of the sources in a single probabilistic model. The 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, indicating further the benefit of using Hilbert transform to deal with oscillatory sources. Experiments on resting-state EEG data, acquired in conjunction with a cued motor imagery or nonimagery task, also show that the states (clusters) obtained by the proposed method are often more interpretable than those obtained by a two-stage method. Acknowledgements This work was supported by a contract with the Ministry of Internal Affairs and Communications “Novel and Innovative R&D Making Use of Brain Structures” and by JSPS KAKENHI Grant Number 25730155. J.H. was partially supported by Strategic International Research Cooperative Program, Japan Science and Technology Agency (JST). A.H. was supported by the Academy of Finland, Centre-of-Excellence in Inverse Problems Research and Centre-of-Excellence Algorithmic Data Analysis. References J. Hirayama, T. Ogawa and A. Hyvarinen. Unifying blind separation and clustering for resting-state EEG/MEG functional connectivity analysis. Neural Computation, 27(7), 1373-1404, 2015. Keywords: unsupervised learning, functional connectivity, resting state, Electroencephalography (EEG), Magnetoencephalography (MEG) Conference: German-Japanese Adaptive BCI Workshop, Kyoto, Japan, 28 Oct - 29 Oct, 2015. Presentation Type: Oral presentation (Invited speakers) Topic: Adaptive BCI Citation: Hirayama J, Ogawa T and Hyvärinen A (2015). Unifying blind separation and clustering for resting-state EEG/MEG functional connectivity analysis. Front. Comput. Neurosci. Conference Abstract: German-Japanese Adaptive BCI Workshop. doi: 10.3389/conf.fncom.2015.56.00010 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 15 Oct 2015; Published Online: 04 Nov 2015. * Correspondence: Dr. Jun-ichiro Hirayama, ATR, Neural Information Analysis Laboratories, Seika-cho, Soraku-gun, Kyoto, 6190288, Japan, hirayama@atr.jp Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Jun-ichiro Hirayama Takeshi Ogawa Aapo Hyvärinen Google Jun-ichiro Hirayama Takeshi Ogawa Aapo Hyvärinen Google Scholar Jun-ichiro Hirayama Takeshi Ogawa Aapo Hyvärinen PubMed Jun-ichiro Hirayama Takeshi Ogawa Aapo Hyvärinen Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.