documentation suggests they can (says "imgs: 3D/4D Niimg-like object").
example:

from nilearn import datasets
from nilearn.input_data import NiftiMapsMasker, NiftiLabelsMasker


img = datasets.load_mni152_template()

atlas_img = datasets.fetch_atlas_destrieux_2009()["maps"]
labels_masker = NiftiLabelsMasker(atlas_img)

prob_atlas_img = datasets.fetch_atlas_harvard_oxford("cort-prob

The date and time on the output of the running docker container isn't correct, adding a volume "-v /etc/localtime:/etc/localtime:ro" might fix this?

This would help me know how long a process

Summary

The component table in the docs (reproduced below) does a good job of describing the role of the accepted and rejected components in the outputs, but the role of ignored component is ambiguous.

Based on the table, I expected the denoised timeseries to only contain accepted components and the high-Ka