Hello y’all !!!
We have just released Nilearn 0.14.0! 
This is a major release with some new features:
- Nilearn can leverage scikit-learn’s Array API-supported estimators to speed up neuroimaging ML analyses using GPU acceleration. See user guide page.
- Interactive visualization with view_surf can now be done using niivue as a backend engine.
- All maskers can now output to pandas or polars dataframe when using transform or accept such dataframes as input to inverse_transform.
- smooth_img can now work with surfaces.
- We had a very successful docathon at the OHBM hackathon to include an Examples section in the docstrings of many of our functions
Update from PyPi:
pip install --upgrade nilearn
Thanks to our new contributors !!!
- @jpaillard
- @jyeatman
- @likeajumprope
- @Rishikakaps
- @XichunXu
- @laurapiro17
- @KoseiTanno
- @ferponcem
- @BastienCagna
- @RDoerfel
- @gamorosino
- @marco7877
- @aliswh
- @mbedini
- @thibaultdvx
- @nirmitee-mulay
- @HugoDelhaye
You can see the full changelog of this release here: https://nilearn.github.io/stable/changes/whats_new.html#id1
The full list of pull requests included in this version:
The full “diff” since last version:
Nilearn links:
- Github: https://github.com/nilearn/nilearn
- Bluesky: https://bsky.app/profile/nilearn.bsky.social
- Mastodon: https://fosstodon.org/@nilearn
- Pypi: https://pypi.org/project/nilearn/
- Documentation: https://nilearn.github.io
- Discord: https://discord.gg/SsQABEJHkZ
- Zenodo DOI: https://doi.org/10.5281/zenodo.8397156
- Youtube: https://www.youtube.com/channel/UCU6BMAi2zOhNFnDkbdevmPw