This repository is a conversion of the popular Matlab-based
ICLabel classifier for Python.
In addition, mne-icalabel provides extensions and improvements in the form of other models.
EEG and MEG recordings include artifacts, such as heartbeat, eyeblink, muscle, and movement activity. Independent component analysis (ICA) is a common method to remove artifacts, but typically relies on manual annotations labelling which independent components (IC) reflect noise and which reflect brain activity.
This package aims at automating this process, using the popular MNE-Python API for EEG, MEG and iEEG data.
MNE-ICALabel estimates the labels of ICA components given a MNE-Python Raw or Epochs object and an ICA instance using the ICA decomposition available in MNE-Python.
from mne_icalabel import label_components
# assuming you have a Raw and ICA instance previously fitted
label_components(raw, ica, method='iclabel')
The only current available method is 'iclabel'.
Stable version documentation. Dev version documentation.
The current stable release of mne-icalabel can be installed with pip, for example, by running:
pip install mne-icalabel
For further details about installation, see the install page.
To get the latest (development) version, using git, open a terminal and type:
git clone git://github.com/mne-tools/mne-icalabel.git
cd mne-icalabel
pip install -e .
The development version can also be installed directly using pip:
pip install https://api.github.com/repos/mne-tools/mne-icalabel/zipball/main
Alternatively, you can also download a zip file of the latest development version.
If you are interested in contributing, please read the contributing guidelines.
For any usage questions, please post to the
MNE Forum. Be sure to add the mne-icalabel tag to
your question.