4.1.1.9. nilearn.datasets.load_harvard_oxford

nilearn.datasets.load_harvard_oxford(atlas_name, dirname='/usr/share/data/harvard-oxford-atlases/HarvardOxford/', symmetric_split=False)

Load Harvard-Oxford parcellation.

This function does not download anything, files must all be already on disk. They are distributed with FSL.

Parameters :

atlas_name: string :

Name of atlas to load. Can be: cort-maxprob-thr0-1mm, cort-maxprob-thr0-2mm, cort-maxprob-thr25-1mm, cort-maxprob-thr25-2mm, cort-maxprob-thr50-1mm, cort-maxprob-thr50-2mm, sub-maxprob-thr0-1mm, sub-maxprob-thr0-2mm, sub-maxprob-thr25-1mm, sub-maxprob-thr25-2mm, sub-maxprob-thr50-1mm, sub-maxprob-thr50-2mm, cort-prob-1mm, cort-prob-2mm, sub-prob-1mm, sub-prob-2mm

dirname: string, optional :

This is the neurodebian’s directory for FSL data. It may be different with another distribution / installation.

symmetric_split: bool, optional :

If True, split every symmetric region in left and right parts. Effectively doubles the number of regions. Default: False. Not implemented for probabilistic atlas (-prob- atlases)

Returns :

regions: nibabel.Nifti1Image :

regions definition, as a label image.