A sparse EEG-informed fMRI model for hybrid EEG-fMRI neurofeedback prediction
Abstract
Measures of brain activity through functional magnetic resonance imaging (fMRI) or Electroencephalography (EEG), two complementary modalities, are ground solutions in the context of neuro-feedback (NF) mechanisms for brain-rehabilitation protocols. Though NF-EEG (real-time neurofeedback scores computed from EEG) have been explored for a very long time, NF-fMRI (real-time neurofeedback scores computed from fMRI) appeared more recently and provides more robust results and more specific brain training. Using simultaneously fMRI and EEG for multimodal neurofeedback sessions (NF-EEG-fMRI, real-time neurofeedback scores computed from fMRI and EEG) is very promising to devise brain rehabilitation protocols. However using fMRI is costly, exhausting and time consuming, and cannot be repeated too many times for the same subject. The original contribution of this paper concerns the prediction of multimodal NF scores from EEG recordings only, using a training phase where both EEG and fMRI synchronous signals, and therefore neurofeedback scores, are available. We propose a sparse regression model able to exploit EEG only to predict NF-fMRI or NF-EEG-fMRI in motor imagery tasks. We compare different NF-predictors steming from the proposed model. We show that one of the proposed NF-predictors significanlty improves over what EEG can provide alone (without the learning phase), and correlates at 0.74 in median with the ground-truth.
Origin | Files produced by the author(s) |
---|
Loading...