Decoding Dynamic Brain Patterns from Evoked Responses: A Tutorial on Multivariate Pattern Analysis Applied to Time Series Neuroimaging Data

By Tijl Grootswagers, Susan G. Wardle, Thomas A. Carlson. Journal of Cognitive Neuroscience, 2016

622 citations recorded by the source corpus.

Multivariate pattern analysis (MVPA) or brain decoding methods have become standard practice in analyzing fMRI data. Although decoding methods have been extensively applied in brain–computer interfaces, these methods have only recently been applied to time series neuroimaging data such as MEG and EEG to address experimental questions in cognitive neuroscience. In a tutorial style review, we describe a broad set of options to inform future time series decoding studies from a cognitive neuroscience perspective. Using example MEG data, we illustrate the effects that different options in the decoding analysis pipeline can have on experimental results where the aim is to “decode” different perceptual stimuli or cognitive states over time from dynamic brain activation patterns. We show that decisions made at both preprocessing (e.g., dimensionality reduction, subsampling, trial averaging) and decoding (e.g., classifier selection, cross-validation design) stages of the analysis can significantly affect the results. In addition to standard decoding, we describe extensions to MVPA for time-varying neuroimaging data including representational similarity analysis, temporal generalization, and the interpretation of classifier weight maps. Finally, we outline important caveats in the design and interpretation of time series decoding experiments.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/0bc85a6f8effa42c651855bd386b5159f5f6ad52

Citations in the corpus

Insular intracranial activity identifies multiple facial expressions via diverse, intermixed temporal patterns at the single-contact level (2026, unknown): “The present study adopted the similarity-based approach given its simplicity, high efficiency, and particularly favorable interpretability (Haxby, 2012; Grootswagers et al., 2017).”
Simultaneous invasive and non-invasive recordings in humans: A novel Rosetta stone for deciphering brain activity (2024, unknown): “All co-authors have no conflicts of interest to disclose.”
Electrophysiological decoding captures the temporal trajectory of face categorization in infants (2024, unknown): “We also quantified the feature importance for the face categorization comparison by multiplying classifier weights with the data covariance to retrieve spatial activation patterns (Grootswagers et al., 2017; Haufe et al., 2014).”
Aperiodic and oscillatory systems underpinning human domain-general cognition (2024, unknown): “%) providesaneffective trade-off between improving signal-to-noise ratio and maintaining a suf ﬁ - cient number of trials for accurate classi ﬁ cation 51,101 .”
Distractor anticipation during working memory is associated with theta and beta oscillations across spatial scales (2024, unknown): “Decoding was performed at each time bin by training a classiﬁer (e.g., C 1 ) at one time bin (e.g., t = 1) and evaluating it across all time bins of interest (e.g., 1 ≤ t ≤ 12).”