mne_icalabel.megnet.get_megnet_features#

mne_icalabel.megnet.get_megnet_features(raw, ica)#

Extract time series and topomaps for each ICA component.

MEGNet uses topomaps from BrainStorm exported as 120x120x3 RGB images. Thus, we need to replicate the ‘appearance’/’look’ of a BrainStorm topomap.

Parameters:
rawRaw

Raw MEG recording used to fit the ICA decomposition. The raw instance should be bandpass filtered between 1 and 100 Hz and notch filtered at 50 or 60 Hz to remove line noise, and downsampled to 250 Hz.

icaICA

ICA decomposition of the provided instance. The ICA decomposition should use the infomax method.

Returns:
time_seriesarray of shape (n_components, n_samples)

The time series for each ICA component.

topomapsarray of shape (n_components, 120, 120, 3)

The topomap RGB images for each ICA component.