6.1. Input and output: neuroimaging data representation#
6.1.1. Inputing data: file names or image objects#
18.104.22.168. File names and objects, 3D and 4D images#
All Nilearn functions accept file names as arguments:
>>> from nilearn import image >>> smoothed_img = image.smooth_img('/home/user/t_map001.nii')
Nilearn can operate on either file names or NiftiImage objects. The later represent the
data loaded in memory. In the example above, the
smooth_img returns a Nifti1Image object, which can then
be readily passed to other nilearn functions.
In nilearn, we often use the term “niimg” as abbreviation that denotes either a file name or a NiftiImage object.
Niimgs can be 3D or 4D. A 4D niimg may for instance represent a time series of 3D images. It can be a list of file names, if these contain 3D information:
>>> # dataset folder contains subject1.nii and subject2.nii >>> from nilearn.image import smooth_img >>> result_img = smooth_img(['dataset/subject1.nii', 'dataset/subject2.nii'])
result_img is a 4D in-memory image, containing the data of both
22.214.171.124. File name matching: “globbing” and user path expansion#
You can specify files with wildcard matching patterns (as in Unix shell):
Matching multiple files: suppose the dataset folder contains subject_01.nii, subject_03.nii, and subject_03.nii;
dataset/subject_*.niiis a glob expression matching all filenames:>>> # Example with a smoothing process: >>> from nilearn.image import smooth_img >>> result_img = smooth_img("dataset/subject_*.nii")
Note that the resulting is a 4D image.
Expanding the home directory
~is expanded to your home directory:>>> result_img = smooth_img("~/dataset/subject_01.nii")
~rather than specifying the details of the path is good practice, as it will make it more likely that your script work on different computers.
For more complicated use cases, Python also provides functions to work
with file paths, in particular,
Unlike nilearn’s path expansion, the result of
not sorted and, depending on the computer you are running, they
might not be in alphabetic order. We advise you to rely on
nilearn’s path expansion.
To load data with globbing, we suggest that you use
6.1.2. Fetching open datasets from Internet#
Nilearn provides dataset fetching function that
automatically downloads reference
datasets and atlases. They can be imported from
>>> from nilearn import datasets >>> haxby_dataset = datasets.fetch_haxby()
They return a data structure that contains different pieces of information on the retrieved dataset, including the file names on hard disk:
>>> # The different files >>> print(sorted(list(haxby_dataset.keys()))) ['anat', 'description', 'func', 'mask', 'mask_face', 'mask_face_little', 'mask_house', 'mask_house_little', 'mask_vt', 'session_target'] >>> # Path to first functional file >>> print(haxby_dataset.func) /.../nilearn_data/haxby2001/subj1/bold.nii.gz
Explanation and further resources of the dataset at hand can be retrieved as follows:
>>> print(haxby_dataset.description) Haxby 2001 results Notes ----- Results from a classical fMRI study that...
For a list of all the data fetching functions in nilearn, see nilearn.datasets: Automatic Dataset Fetching.
nilearn_data: Where is the downloaded data stored?
The fetching functions download the reference datasets to the disk. They save it locally for future use, in one of the following directories (in order of priority, if present):
the folder specified by data_dir parameter in the fetching function
the global environment variable NILEARN_SHARED_DATA
the user environment variable NILEARN_DATA
the nilearn_data folder in the user home folder
The two different environment variables (NILEARN_SHARED_DATA and NILEARN_DATA) are provided for multi-user systems, to distinguish a global dataset repository that may be read-only at the user-level. Note that you can copy that folder to another user’s computers to avoid the initial dataset download on the first fetching call.
You can check in which directory nilearn will store the data with the
6.1.3. Understanding neuroimaging data#
126.96.36.199. Nifti and Analyze data#
For volumetric data, nilearn works with data stored as in the Nifti structure (via the nibabel package).
The NifTi data structure (also used in Analyze files) is the standard way of sharing data in neuroimaging research. Three main components are:
raw scans in form of a numpy array:
data = nilearn.image.get_data(img)
returns the transformation matrix that maps from voxel indices of the numpy array to actual real-world locations of the brain:
affine = img.affine
low-level information about the data (slice duration, etc.):
header = img.header
If you need to load the data without using nilearn, read the nibabel documentation.
Note: For older versions of nibabel, affine and header can be retrieved
if you create images directly with nibabel, beware of int64 images. the default integer type used by Numpy is (signed) 64-bit. Several popular neuroimaging tools do not handle int64 Nifti images, so if you build Nifti images directly from Numpy arrays it is recommended to specify a smaller integer type, for example:
np.array([1, 2000, 7], dtype="int32")
Dataset formatting: data shape
It is important to appreciate two main representations for storing and accessing more than one Nifti images, that is sets of MRI scans:
188.8.131.52. Niimg-like objects#
Nilearn functions take as input argument what we call “Niimg-like objects”:
Niimg: A Niimg-like object can be one of the following:
A string or pathlib.Path object with a file path to a Nifti or Analyse image
SpatialImagefrom nibabel, ie an object exposing
affineattribute, typically a
Niimg-4D: Similarly, some functions require 4D Nifti-like data, which we call Niimgs or Niimg-4D. Accepted input arguments are:
A path to a 4D Nifti image
List of paths to 3D Nifti images
4D Nifti-like object
List of 3D Nifti-like objects
If you provide a sequence of Nifti images, all of them must have the same affine.
Decreasing memory used when loading Nifti images
When Nifti images are stored compressed (.nii.gz), loading them directly consumes more memory. As a result, large 4D images may raise “MemoryError”, especially on smaller computers and when using Nilearn routines that require intensive 4D matrix operations. One step to improve the situation may be to decompress the data onto disk as an initial step. If multiple images are loaded into memory sequentially, another solution may be to uncache one before loading and performing operations on another.
184.108.40.206. Text files: phenotype or behavior#
Phenotypic or behavioral data are often provided as text or CSV (Comma Separated Values) file. They can be loaded with pd.read_csv but you may have to specify some options (typically sep if fields aren’t delimited with a comma).
For the Haxby datasets, we can load the categories of the images presented to the subject:
>>> from nilearn import datasets >>> haxby_dataset = datasets.fetch_haxby() >>> import pandas as pd >>> labels = pd.read_csv(haxby_dataset.session_target, sep=" ") >>> stimuli = labels['labels'] >>> print(stimuli.unique()) ['bottle' 'cat' 'chair' 'face' 'house' 'rest' 'scissors' 'scrambledpix' 'shoe']
Reading CSV with pandas
Pandas is a powerful package to read data from CSV files and manipulate them.