دورية أكاديمية
Investigating the temporal dynamics of electroencephalogram (EEG) microstates using recurrent neural networks.
| العنوان: | Investigating the temporal dynamics of electroencephalogram (EEG) microstates using recurrent neural networks. |
|---|---|
| المؤلفون: | Sikka A; Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Rupnagar, Punjab, India., Jamalabadi H; Department of Psychiatry and Psychotherapy, Division for Translational Psychiatry, University of Tübingen, Tübingen, Germany., Krylova M; Department of Psychiatry and Psychotherapy, Division for Translational Psychiatry, University of Tübingen, Tübingen, Germany., Alizadeh S; Department of Psychiatry and Psychotherapy, Division for Translational Psychiatry, University of Tübingen, Tübingen, Germany., van der Meer JN; QIMR Berghofer Medical Research Institute, Brisbane, Australia., Danyeli L; Clinical Affective Neuroimaging Laboratory, Magdeburg, Germany.; Leibniz Institute for Neurobiology, Magdeburg, Germany., Deliano M; Leibniz Institute for Neurobiology, Magdeburg, Germany., Vicheva P; Clinical Affective Neuroimaging Laboratory, Magdeburg, Germany.; Department of Psychiatry, Otto von Guericke University of Magdeburg, Magdeburg, Germany., Hahn T; Institute of Translational Psychiatry, University of Muenster, Muenster, Germany., Koenig T; Translational Research Center, University Hospital of Psychiatry, University of Bern, Bern, Switzerland., Bathula DR; Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Rupnagar, Punjab, India., Walter M; Department of Psychiatry and Psychotherapy, Division for Translational Psychiatry, University of Tübingen, Tübingen, Germany.; Clinical Affective Neuroimaging Laboratory, Magdeburg, Germany.; Leibniz Institute for Neurobiology, Magdeburg, Germany.; Max Planck Institute for biological cybernetics, Tübingen, Germany.; Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, Germany. |
| المصدر: | Human brain mapping [Hum Brain Mapp] 2020 Jun 15; Vol. 41 (9), pp. 2334-2346. Date of Electronic Publication: 2020 Feb 24. |
| نوع المنشور: | Journal Article; Research Support, Non-U.S. Gov't |
| اللغة: | English |
| بيانات الدورية: | Publisher: Wiley Country of Publication: United States NLM ID: 9419065 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1097-0193 (Electronic) Linking ISSN: 10659471 NLM ISO Abbreviation: Hum Brain Mapp Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: New York : Wiley Original Publication: New York : Wiley-Liss, c1993- |
| مواضيع طبية MeSH: | Neural Networks, Computer*, Cerebral Cortex/*physiology , Connectome/*methods , Electroencephalography/*methods , Magnetic Resonance Imaging/*methods , Stress, Psychological/*physiopathology, Adult ; Cerebral Cortex/diagnostic imaging ; Datasets as Topic ; Humans ; Male ; Middle Aged ; Stress, Psychological/diagnostic imaging ; Time Factors |
| مستخلص: | Electroencephalogram (EEG) microstates that represent quasi-stable, global neuronal activity are considered as the building blocks of brain dynamics. Therefore, the analysis of microstate sequences is a promising approach to understand fast brain dynamics that underlie various mental processes. Recent studies suggest that EEG microstate sequences are non-Markovian and nonstationary, highlighting the importance of the sequential flow of information between different brain states. These findings inspired us to model these sequences using Recurrent Neural Networks (RNNs) consisting of long-short-term-memory (LSTM) units to capture the complex temporal dependencies. Using an LSTM-based auto encoder framework and different encoding schemes, we modeled the microstate sequences at multiple time scales (200-2,000 ms) aiming to capture stably recurring microstate patterns within and across subjects. We show that RNNs can learn underlying microstate patterns with high accuracy and that the microstate trajectories are subject invariant at shorter time scales (≤400 ms) and reproducible across sessions. Significant drop in the reconstruction accuracy was observed for longer sequence lengths of 2,000 ms. These findings indirectly corroborate earlier studies which indicated that EEG microstate sequences exhibit long-range dependencies with finite memory content. Furthermore, we find that the latent representations learned by the RNNs are sensitive to external stimulation such as stress while the conventional univariate microstate measures (e.g., occurrence, mean duration, etc.) fail to capture such changes in brain dynamics. While RNNs cannot be configured to identify the specific discriminating patterns, they have the potential for learning the underlying temporal dynamics and are sensitive to sequence aberrations characterized by changes in metal processes. Empowered with the macroscopic understanding of the temporal dynamics that extends beyond short-term interactions, RNNs offer a reliable alternative for exploring system level brain dynamics using EEG microstate sequences. (© 2020 The Authors. Human Brain Mapping published by Wiley Periodicals, Inc.) |
| References: | Neuroimage. 2016 Jan 15;125:643-656. (PMID: 26285079) Neural Comput. 1997 Nov 15;9(8):1735-80. (PMID: 9377276) Clin Neurophysiol. 2011 Jun;122(6):1073-4. (PMID: 21126907) Wiley Interdiscip Rev Cogn Sci. 2013 May;4(3):245-261. (PMID: 26304203) Neuroimage. 2017 Feb 1;146:533-543. (PMID: 27742598) Eur Arch Psychiatry Clin Neurosci. 1999;249(4):205-11. (PMID: 10449596) Neuroimage. 2017 Sep;158:99-111. (PMID: 28673879) Hum Brain Mapp. 2018 Oct 27;:. (PMID: 30367727) Neuroimage. 2016 Nov 1;141:442-451. (PMID: 27485754) Proc Natl Acad Sci U S A. 2010 Oct 19;107(42):18179-84. (PMID: 20921381) Front Psychiatry. 2019 Aug 09;10:548. (PMID: 31474881) Stress Health. 2015 Apr;31(2):115-23. (PMID: 24395182) Stress. 2014 Jul;17(4):352-61. (PMID: 24800784) Front Behav Neurosci. 2014 May 14;8:163. (PMID: 24860450) Clin Neurophysiol. 2013 Jun;124(6):1106-14. (PMID: 23403263) Philos Trans R Soc Lond B Biol Sci. 2005 May 29;360(1457):1015-23. (PMID: 16087445) Front Psychiatry. 2016 Feb 26;7:22. (PMID: 26955358) Neurosci Biobehav Rev. 2015 Feb;49:105-13. (PMID: 25526823) Neurobiol Stress. 2016 Feb 12;3:83-95. (PMID: 27981181) Hum Brain Mapp. 2020 Jun 15;41(9):2334-2346. (PMID: 32090423) Neuroimage. 2016 Jan 15;125:880-894. (PMID: 26505301) Psychiatry Res. 2005 Feb 28;138(2):141-56. (PMID: 15766637) Schizophr Res. 2014 Feb;152(2-3):513-20. (PMID: 24389056) Neuroimage. 2002 May;16(1):41-8. (PMID: 11969316) Neuroimage. 2015 Aug 15;117:449-55. (PMID: 26032884) J Neural Transm Gen Sect. 1995;99(1-3):213-22. (PMID: 8579806) Neuroimage. 2010 Oct 1;52(4):1162-70. (PMID: 20188188) Neuroimage. 2018 Oct 15;180(Pt B):577-593. (PMID: 29196270) J Neurosci Methods. 2004 Mar 15;134(1):9-21. (PMID: 15102499) Neuroimage. 2009 May 1;45(4):1144-50. (PMID: 19349230) |
| فهرسة مساهمة: | Keywords: EEG; microstates; recurrent neural networks; stress |
| تواريخ الأحداث: | Date Created: 20200225 Date Completed: 20211108 Latest Revision: 20211108 |
| رمز التحديث: | 20221213 |
| مُعرف محوري في PubMed: | PMC7267981 |
| DOI: | 10.1002/hbm.24949 |
| PMID: | 32090423 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 1097-0193 |
|---|---|
| DOI: | 10.1002/hbm.24949 |