New Nilearn release: 0.10.3

Hello everyone!

We have just released Nilearn 0.10.3!

Update from PyPi

pip install --upgrade nilearn

Experimental Surface API

We are further developing our surface API experimental module and we are interested in getting your feedback on this. We have an example showcasing what can be done here.

Please add comments in this issue: Feedback Request: Experimental Surface API in Nilearn 0.10.2 · Issue #4158 · nilearn/nilearn · GitHub


:warning: WARNING

Support for python 3.7 has been dropped. We recommend moving to python >= 3.11.

Note we have bumped the minimum supported versions of some of our dependencies:

  • Numpy – v1.19.0
  • SciPy – v1.8.0
  • Scikit-learn – v1.0.0
  • Nibabel – v4.0.0
  • Pandas – v1.1.5
  • Joblib – v1.0.0

This is a minor release with some exciting new features:

  • Allow passing arguments to first_level_from_bids to build first level models that include specific set of confounds by relying on the strategies from load_confounds
  • Support passing t and F contrasts to compute_contrast that have fewer columns than the number of estimated parameters. Remaining columns are padded with zero
  • NiftiSpheresMasker now has generate_report method
  • Update the CompCor strategy in load_confounds and load_confounds_strategy to support fmriprep 21.x series and above
  • Combine GLM examples plot_fixed_effect and plot_fiac_analysis into a single example plot_two_runs_model
  • Allow setting vmin in plot_glass_brain and plot_stat_map
  • When plotting thresholded statistical maps with a colorbar, the threshold value(s) will now be displayed as tick labels on the colorbar

You can see the full changelog of this release here: What’s new - Nilearn

The full list of pull requests included in this version:

The full “diff” since last version:

New contributors

Thanks to our 7 new contributors !!!

Nilearn links