Controllable spatio-temporal smoothness constraints for EEG source localization

We present a new spatio-temporal regularization approach for EEG source localization. Using separable spatial and temporal smoothing constraints, we are able to construct a computationally feasible maximum a posteriori (MAP) solution. The smoothing is achieved using a Helmholtz-type functional which allows explicit control over the distance at which correlation between voxels is present. Temporal variation in signal to noise ratio is incorporated as a column-wise of the temporal regularization matrix. Using both simulated and experimental EEG data, we show that this approach allows for improvements in both the spatial and temporal accuracy of the resulting solutions.