A pretrained foundation model for headache disorders based on magnetoencephalography
- 8 January 2026
- journal article
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 23 (1) , 016005
Abstract
Objective. Foundation models have demonstrated transformative potential in medical artificial intelligence but remain underexplored in functional neuroimaging, particularly magnetoencephalography (MEG). This study aims to develop a domain-specific, self-supervised MEG clinical foundation model tailored for headache disorders to address the challenges of high-dimensional data and limited labeled datasets in clinical research. Approach . We developed a transformer-based model pretrained on a large-scale dataset comprising multi-state MEG recordings (resting-state, auditory, and somatosensory stimulation) from 416 participants (362 headache patients and 54 healthy controls). The model utilized a self-supervised masked-signal reconstruction strategy to learn latent spatiotemporal representations of neural activity. We evaluated the model’s performance through signal reconstruction, visualization of attention weights, and downstream classification tasks comparing model-derived features against original MEG signals for migraine diagnosis. Main results . The pretrained model successfully reconstructed both continuous MEG signals and stimulus-specific evoked responses, effectively capturing intrinsic spatiotemporal brain dynamics. Visualization of the model’s attention weights demonstrated spatial alignment with corresponding sensory brain regions, confirming its neurophysiological interpretability. Furthermore, classifiers trained on features extracted from the pretrained model significantly outperformed those using original MEG signals in identifying migraine patients, revealing distinct neural response patterns. Significance . This study introduces a scalable, data-efficient framework for clinical MEG analysis that significantly reduces reliance on manual feature extraction and labeled data. It demonstrates the efficacy of foundation models in decoding complex neural dynamics, offering promising implications for understanding neuropathology and facilitating precision diagnostics in neurology.Keywords
Funding Information
- Changping Laboratory (2021B-03-01)
- National Science and Technology Innovation 2030 Major Program and Project of China (2021ZD0200500)
- National Natural Science Foundation of China (82327806)
This publication has 42 references indexed in Scilit:
- Medical image foundation models in assisting diagnosis of brain tumors: a pilot studyEuropean Radiology, 2024
- On the challenges and perspectives of foundation models for medical image analysisMedical Image Analysis, 2023
- Structural and Functional Brain Changes in MigrainePain and Therapy, 2021
- Auditory attention alterations in migraine: A behavioral and MEG/EEG studyClinical Neurophysiology, 2020
- Global, regional, and national burden of neurological disorders, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016The Lancet Neurology, 2019
- Magnetoencephalography for brain electrophysiology and imagingNature Neuroscience, 2017
- Migraine is Associated With Altered Processing of Sensory StimuliCurrent Pain and Headache Reports, 2014
- Adding dynamics to the Human Connectome Project with MEGNeuroImage, 2013
- What we can do and what we cannot do with fMRINature, 2008
- Statistical Approaches to Functional Neuroimaging DataNeuroimaging Clinics Of North America, 2007