Unsupervised representation learning of spontaneous MEG data with nonlinear ICA

Zhu, Yongjie; Parviainen, Tiina; Heinilä, Erkka; Parkkonen, Lauri; Hyvärinen, Aapo

doi:10.1016/j.neuroimage.2023.120142

Cited by 4 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This highlights the remarkable individual variability in the continuous MEG activation underlying these conditions. It may also be one reason why it has appeared difficult to build group-level classifiers for the purpose of brain-computer interfaces with this type of data, as we attempted using these same recordings in two previous studies (Zhigalov et al, 2019;Zhu et al, 2023). Similar large individual differences have been witnessed before in the mind-wandering research (Golchert et al, 2017).…”

Section: Canonical Correlation Analysismentioning

confidence: 89%

Penalized canonical correlation analysis reveals a relationship between temperament traits and brain oscillations during mind wandering

Heinilä,

Hyvärinen,

Parkkonen

et al. 2024

Brain and Behavior

Self Cite

View full text Add to dashboard Cite

IntroductionThere has been a growing interest in studying brain activity under naturalistic conditions. However, the relationship between individual differences in ongoing brain activity and psychological characteristics is not well understood. We investigated this connection, focusing on the association between oscillatory activity in the brain and individually characteristic dispositional traits. Given the variability of unconstrained resting states among individuals, we devised a paradigm that could harmonize the state of mind across all participants.MethodsWe constructed task contrasts that included focused attention (FA), self‐centered future planning, and rumination on anxious thoughts triggered by visual imagery. Magnetoencephalography was recorded from 28 participants under these 3 conditions for a duration of 16 min. The oscillatory power in the alpha and beta bands was converted into spatial contrast maps, representing the difference in brain oscillation power between the two conditions. We performed permutation cluster tests on these spatial contrast maps. Additionally, we applied penalized canonical correlation analysis (CCA) to study the relationship between brain oscillation patterns and behavioral traits.ResultsThe data revealed that the FA condition, as compared to the other conditions, was associated with higher alpha and beta power in the temporal areas of the left hemisphere and lower alpha and beta power in the parietal areas of the right hemisphere. Interestingly, the penalized CCA indicated that behavioral inhibition was positively correlated, whereas anxiety was negatively correlated, with a pattern of high oscillatory power in the bilateral precuneus and low power in the bilateral temporal regions. This unique association was found in the anxious‐thoughts condition when contrasted with the focused‐attention condition.ConclusionOur findings suggest individual temperament traits significantly affect brain engagement in naturalistic conditions. This research underscores the importance of considering individual traits in neuroscience and offers an effective method for analyzing brain activity and psychological differences.

show abstract

Section: Canonical Correlation Analysismentioning

confidence: 89%

Penalized canonical correlation analysis reveals a relationship between temperament traits and brain oscillations during mind wandering

Heinilä,

Hyvärinen,

Parkkonen

et al. 2024

Brain and Behavior

Self Cite

View full text Add to dashboard Cite

show abstract

“…We hope that our work can inspire the development of novel end-to-end solutions for disentangling brain and non-brain sources, ideally directly built into the prediction models. Promising directions for this effort may lay in the nonlinear ICA (Monti et al, 2020;Zhu et al, 2023), self-supervision (Banville et al, 2020;Tong et al, 2023;Yang et al, 2021) and disentanglement literature (Chen et al, 2018;Lynch et al, 2023;Mathieu et al, 2019;Shu et al, 2018).…”

Section: Limitations and Future Directionsmentioning

confidence: 99%

“…We chose this EEG dataset as it represents a heterogeneous sample of the general population of patients from the Philadelphia area seeking medical counseling. Furthermore, the dataset has been popular among applied machine learning researchers (Banville et al, 2020;Darvishi-Bayazi et al, 2023;Gemein et al, 2023Gemein et al, , 2020Sabbagh et al, 2020;Wagh and Varatharajah, 2020;Zhu et al, 2023) and therefore provides a point of reference for algorithmic benchmarking.…”

Section: Tuab Datasetmentioning

confidence: 99%

Machine learning of brain-specific biomarkers from EEG

Bomatter,

Paillard,

Garces

et al. 2023

Preprint

View full text Add to dashboard Cite

Electroencephalography (EEG) has a long history as a clinical tool to study brain function, and its potential to derive biomarkers for various applications is far from exhausted. Machine learning (ML) can guide future innovation by harnessing the wealth of complex EEG signals to isolate relevant brain activity. Yet, ML studies in EEG tend to ignore physiological artifacts, which may cause problems for deriving biomarkers specific to the central nervous system (CNS). We present a framework for conceptualizing machine learning from CNS versus peripheral signals measured with EEG. A common signal representation across the frequency spectrum based on Morlet wavelets allowed us to define traditional brain activity features (e.g. log power) and alternative inputs used by state-of-the-art ML approaches (covariance matrices). Using more than 2600 EEG recordings from large public databases (TUAB, TDBRAIN), we studied the impact of peripheral signals and artifact removal techniques on ML models in exemplary age and sex prediction analyses. Across benchmarks, basic artifact rejection improved model performance whereas further removal of peripheral signals using ICA decreased performance. Our analyses revealed that peripheral signals enable age and sex prediction. However, they explained only a fraction of the performance provided by brain signals. We show that brain signals and body signals, both reflected in the EEG, allow for prediction of personal characteristics. While these results may depend on specific prediction problems, our work suggests that great care is needed to separate these signals when the goal is to develop CNS-specific biomarkers using ML.

show abstract