DeepReducer: A linear transformer-based model for MEG denoising

Measuring event-related magnetic fields (ERFs) in magnetoencephalography (MEG) is crucial for investigating perceptual and cognitive information processing in both neuroscience research and clinical practice. However, the magnitude of the ERF in cortical sources is comparable to the noise in a single trial. Consequently, numerous repetitive recordings are needed to distinguish these sources from background noise, requiring lengthy time for data acquisition. Herein, we introduce DeepReducer, a linear transformer-based deep learning model designed to reliably and efficiently denoise ERFs, thereby reducing the number of required trials. DeepReducer was trained on a mix of limited-trial and multi-trial averaged ERFs, employing mean squared error as the loss function to effectively capture and model the complex signal fluctuations inherent in MEG recordings. Validation on both semi-synthetic and experimental task-related MEG data showed that DeepReducer outperforms conventional trial-averaging techniques, significantly improving the signal-to-noise ratio of ERFs and reducing source localization errors. The practical significance of DeepReducer encompasses optimizing MEG data acquisition by reducing participant stress (particularly for patients) and minimizing associated artifacts.