Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the user guide for the big picture.

nilearn.image.index_img

nilearn.image.index_img(imgs, index)

Indexes into a 4D Niimg-like object in the fourth dimension.

Common use cases include extracting a 3D image out of img or creating a 4D image whose data is a subset of img data.

Parameters

imgs4D Niimg-like object

See http://nilearn.github.io/manipulating_images/input_output.html.

indexAny type compatible with numpy array indexing

Used for indexing the 4D data array in the fourth dimension.

Returns

Nifti1Image

Indexed image.

See also

nilearn.image.concat_imgs

nilearn.image.iter_img

Examples

First we concatenate two MNI152 images to create a 4D-image:

>>> from nilearn import datasets
>>> from nilearn.image import concat_imgs, index_img
>>> joint_mni_image = concat_imgs([datasets.load_mni152_template(),
...                                datasets.load_mni152_template()])
>>> print(joint_mni_image.shape)
(99, 117, 95, 2)

We can now select one slice from the last dimension of this 4D-image:

>>> single_mni_image = index_img(joint_mni_image, 1)
>>> print(single_mni_image.shape)
(99, 117, 95)

We can also select multiple frames using the slice constructor:

>>> five_mni_images = concat_imgs([datasets.load_mni152_template()] * 5)
>>> print(five_mni_images.shape)
(99, 117, 95, 5)

>>> first_three_images = index_img(five_mni_images,
...                                slice(0, 3))
>>> print(first_three_images.shape)
(99, 117, 95, 3)

Examples using nilearn.image.index_img

Advanced decoding using scikit learn

Advanced decoding using scikit learn