Back to EOSS Proposals List

Back to All Open Science Grantees

Improving Standard Practice for Neuroimaging Analyses with Nilearn

Project Nilearn
Funding Cycle 5

Proposal Summary

To scale technical and social support for new analyses in Nilearn including the general linear model, giving access to a broad statistical framework for neuroimagers within the open source Python ecosystem.



Nilearn is a well-established open source Python package for fast and easy analysis of brain images, with a focus on functional Magnetic Resonance Imaging (fMRI) data and machine learning. Key statistical frameworks for these programs such as the General Linear Model (GLM) have remained behind proprietary languages such as MATLAB. In 2020, Nilearn expanded to include the GLM, but is still stretched thin. This project will restructure Nilearn’s development process to better distribute support across existing functionality, stabilizing GLM support while creating opportunities to interface with other community tools.

Key Personnel

Jean-Baptiste Poline, Jerome Dockès, and the Nilearn core developer team