mne-icalabel is a Python package for labeling independent components that stem from an Independent Component Analysis (ICA).

Scalp electroencephalography (EEG) and magnetoencephalography (MEG) analysis is typically very noisy and contains various non-neural signals, such as heartbeat artifacts. Independent Component Analysis (ICA) is a common procedure to remove these artifacts. However, removing artifacts requires manual annotation of ICA components, which is subject to human error and very laborious when operating on large datasets. The first few versions of mne-icalabel replicated the popular ICLabel model for Python (previously only available in MATLAB’s EEGLab). In future versions, the package aims to develop more robust models that build upon the ICLabel model.

We encourage you to use the package for your research and also build on top with relevant Pull Requests (PR). See our examples for walk-throughs of how to use the package and see our contributing guide for contributions.

mne-icalabel is licensed under the BSD license. A full copy of the license can be found on GitHub.


See our Changelog for a full list of changes.