Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 35 min ago
Peer-reviewedCC BYImaging Neuroscience

MEG-GPT: A transformer-based foundation model for magnetoencephalography data

4 affiliations
  1. 1Department of Psychiatry, University of Oxford, Oxford, United Kingdom
  2. 2Oxford Centre for Integrative Neuroimaging (OxCIN), University of Oxford, Oxford, United Kingdom
  3. 3Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
  4. 4Department of Engineering Science, University of Oxford, Oxford, United Kingdom

Abstract

Modelling the complex spatio-temporal patterns of large-scale brain dynamics is crucial for neuroscience, but traditional methods fail to capture the rich structure in modalities such as magnetoencephalography (MEG). Recent advances in deep learning have enabled significant progress in other domains, such as language and vision, by using foundation models at scale. Here, we introduce MEG-GPT, a transformer-based foundation model that uses time-attention and next time-point prediction. To facilitate this, we also introduce a novel data-driven tokeniser for continuous MEG data, which preserves the high temporal resolution of continuous MEG signals without lossy transformations. We trained MEG-GPT on tokenised brain region time courses extracted from a large-scale MEG dataset (N = 612, eyes-closed rest, Cam-CAN data), and show that the learnt model can generate data with realistic spatio-spectral properties, including transient events and population variability. Critically, it performs well in downstream decoding tasks, improving downstream supervised prediction task, showing improved zero-shot generalisation across sessions (improving accuracy from 0.56 to 0.59) and subjects (improving accuracy from 0.45 to 0.49) compared with a PCA baseline method. Furthermore, we show the model can be efficiently fine-tuned on a smaller labelled dataset to boost performance in cross-subject decoding scenarios. This work establishes a powerful foundation model for electrophysiological data, paving the way for applications in computational neuroscience and neural decoding.

Related

  1. MEG-Mamba: A Scalable State-Space Foundation Model for Magnetoencephalography
    Chetan Gohil, SungJun Cho, Oiwi Parker Jones +1
    arXivPreprintCC BY 4.0Full textNeurosciencearXiv
  2. Transductive Learning From a Transformer Foundation Model Improves the Taxonomic Classification of eDNA Metabarcodes
    Simon Bettinger, Auguste Verdier, Morgane Bruno +6
    Molecular Ecology ResourcesPeer-reviewedCC BY 4.0Full textEcologyPMC
  3. Neural oscillations and network specialisation in early childhood captured with next-generation magnetoencephalography
    Natalie Rhodes, Julian Bandhan, Marlee M. Vandewouw +5
    Communications BiologyPeer-reviewedCC BY-NC-ND 4.0Full textNeuroscienceCrossref
  4. Variance of human cortical synaptic transmission inferred from non-invasive magnetoencephalography of somatosensory evoked population spikes
    Lukasz Radzinski, Rainer Körber, Jim Barnes +4
    iSciencePeer-reviewedCC BY 4.0Full textNeuroscienceNeurologyCell PressCrossrefEurope PMCEurope PMC+1
  5. Spatiotemporal dynamics of lexical and morphosyntactic planning during language production revealed by magnetoencephalography
    Y. Wei, L. R. Slevc, C. Brodbeck +1
    bioRxivPreprintCC BY-NC-NDFull textNeurosciencebioRxiv
BibTeX
@article{huang2026meggpt,
  title = {{MEG-GPT: A transformer-based foundation model for magnetoencephalography data}},
  author = {Rukuang Huang and Sungjun Cho and Chetan Gohil and Ōiwi Parker Jones and Mark W. Woolrich},
  journal = {Imaging Neuroscience},
  year = {2026},
  month = jun,
  doi = {10.1162/imag.a.1301},
  url = {https://doi.org/10.1162/imag.a.1301},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - MEG-GPT: A transformer-based foundation model for magnetoencephalography data
AU  - Rukuang Huang
AU  - Sungjun Cho
AU  - Chetan Gohil
AU  - Ōiwi Parker Jones
AU  - Mark W. Woolrich
PY  - 2026
DA  - 2026/06/26
JO  - Imaging Neuroscience
DO  - 10.1162/imag.a.1301
UR  - https://doi.org/10.1162/imag.a.1301
AB  - Modelling the complex spatio-temporal patterns of large-scale brain dynamics is crucial for neuroscience, but traditional methods fail to capture the rich structure in modalities such as magnetoencephalography (MEG). Recent advances in deep learning have enabled significant progress in other domains, such as language and vision, by using foundation models at scale. Here, we introduce MEG-GPT, a transformer-based foundation model that uses time-attention and next time-point prediction. To facilitate this, we also introduce a novel data-driven tokeniser for continuous MEG data, which preserves the high temporal resolution of continuous MEG signals without lossy transformations. We trained MEG-GPT on tokenised brain region time courses extracted from a large-scale MEG dataset (N = 612, eyes-closed rest, Cam-CAN data), and show that the learnt model can generate data with realistic spatio-spectral properties, including transient events and population variability. Critically, it performs well in downstream decoding tasks, improving downstream supervised prediction task, showing improved zero-shot generalisation across sessions (improving accuracy from 0.56 to 0.59) and subjects (improving accuracy from 0.45 to 0.49) compared with a PCA baseline method. Furthermore, we show the model can be efficiently fine-tuned on a smaller labelled dataset to boost performance in cross-subject decoding scenarios. This work establishes a powerful foundation model for electrophysiological data, paving the way for applications in computational neuroscience and neural decoding.
SN  - 2837-6056
ER  -