Nilearn

Nilearn enables approachable and versatile analyses of brain volumes. It provides statistical and machine-learning tools, with instructive documentation & open community.

It supports general linear model (GLM) based analysis and leverages the scikit-learn Python toolbox for multivariate statistics with applications such as predictive modeling, classification, decoding, or connectivity analysis.

Quickstart

Get started with Nilearn

Quickstart

Examples

Discover functionalities by reading examples

auto_examples/index.html

User guide

Learn about neuroimaging analysis

User guide

Featured examples

Glass brain plotting

Explore how to retrieve data and plot whole brain cuts in glass mode.

auto_examples/01_plotting/plot_demo_glass_brain.html

Computing a connectome with sparse inverse covariance

Construct a functional connectome using the sparse inverse covariance, and display the corresponding graph and matrix.

auto_examples/03_connectivity/plot_inverse_covariance_connectome.html

Making a surface plot of a 3D statistical map

Project a 3D statistical map onto a cortical mesh and display the surface map as png or in interactive mode.

auto_examples/01_plotting/plot_3d_map_to_surface_projection.html

Introduction tutorial to fMRI decoding

Learn to perform decoding with nilearn. Reproduce the Haxby 2001 study on a face vs cat discrimination task in a mask of the ventral stream.

auto_examples/00_tutorials/plot_decoding_tutorial.html

Voxel-Based Morphometry on Oasis dataset

Study the relationship between aging and gray matter density using data from the OASIS project.

auto_examples/02_decoding/plot_oasis_vbm.html

Clustering methods to learn a brain parcellation from fMRI

Use spatially-constrained Ward-clustering, KMeans, Hierarchical KMeans and Recursive Neighbor Agglomeration (ReNA) to create a set of parcels, and display them.

auto_examples/03_connectivity/plot_data_driven_parcellations.html

Deriving spatial maps from group fMRI data using ICA and Dictionary Learning

Derive spatial maps or networks from group fMRI data using two popular decomposition methods, ICA and Dictionary learning on data of children and young adults watching movies.

auto_examples/03_connectivity/plot_compare_decomposition.html

Decoding with FREM: face vs house object recognition

Use fast ensembling of regularized models (FREM) to decode a face vs house discrimination task from Haxby 2001 study.

auto_examples/02_decoding/plot_haxby_frem.html

Searchlight analysis of face vs house recognition

Fit a classifier a large amount of times in order to distinguish between face- and house-related cortical areas.

auto_examples/02_decoding/plot_haxby_searchlight.html

Nilearn is part of the NiPy ecosystem.