A1 Journal article (refereed)
Unsupervised representation learning of spontaneous MEG data with nonlinear ICA (2023)
Zhu, Y., Parviainen, T., Heinilä, E., Parkkonen, L., & Hyvärinen, A. (2023). Unsupervised representation learning of spontaneous MEG data with nonlinear ICA. Neuroimage, 274, Article 120142. https://doi.org/10.1016/j.neuroimage.2023.120142
JYU authors or editors
Publication details
All authors or editors: Zhu, Yongjie; Parviainen, Tiina; Heinilä, Erkka; Parkkonen, Lauri; Hyvärinen, Aapo
Journal or series: Neuroimage
ISSN: 1053-8119
eISSN: 1095-9572
Publication year: 2023
Publication date: 28/04/2023
Volume: 274
Article number: 120142
Publisher: Elsevier BV
Publication country: United States
Publication language: English
DOI: https://doi.org/10.1016/j.neuroimage.2023.120142
Publication open access: Openly available
Publication channel open access: Open Access channel
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/86853
Abstract
Resting-state magnetoencephalography (MEG) data show complex but structured spatiotemporal patterns. However, the neurophysiological basis of these signal patterns is not fully known and the underlying signal sources are mixed in MEG measurements. Here, we developed a method based on the nonlinear independent component analysis (ICA), a generative model trainable with unsupervised learning, to learn representations from resting-state MEG data. After being trained with a large dataset from the Cam-CAN repository, the model has learned to represent and generate patterns of spontaneous cortical activity using latent nonlinear components, which reflects principal cortical patterns with specific spectral modes. When applied to the downstream classification task of audio-visual MEG, the nonlinear ICA model achieves competitive performance with deep neural networks despite limited access to labels. We further validate the generalizability of the model across different datasets by applying it to an independent neurofeedback dataset for decoding the subject's attentional states, providing a real-time feature extraction and decoding mindfulness and thought-inducing tasks with an accuracy of around 70% at the individual level, which is much higher than obtained by linear ICA or other baseline methods. Our results demonstrate that nonlinear ICA is a valuable addition to existing tools, particularly suited for unsupervised representation learning of spontaneous MEG activity which can then be applied to specific goals or tasks when labelled data are scarce.
Keywords: MEG; neurofeedback; signal analysis; signal processing; machine learning; deep learning
Free keywords: nonlinear independent component analysis (ICA); unsupervised learning; deep generative model; resting-state network; non-stationarity; neurofeedback; magnetoencephalography (MEG)
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2023
Preliminary JUFO rating: 3