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.datasets.fetch_abide_pcp¶
- nilearn.datasets.fetch_abide_pcp(data_dir=None, n_subjects=None, pipeline='cpac', band_pass_filtering=False, global_signal_regression=False, derivatives=None, quality_checked=True, url=None, verbose=1, legacy_format=False, **kwargs)[source]¶
Fetch ABIDE dataset.
Fetch the Autism Brain Imaging Data Exchange (ABIDE) dataset wrt criteria that can be passed as parameter. Note that this is the preprocessed version of ABIDE provided by the preprocess connectome projects (PCP). See Nielsen et al.[1].
- Parameters:
- data_dir
pathlib.Path
orstr
, optional Path where data should be downloaded. By default, files are downloaded in a
nilearn_data
folder in the home directory of the user. See alsonilearn.datasets.utils.get_data_dirs
.- n_subjects
int
, optional The number of subjects to load. If None is given, all available subjects are used (this number depends on the preprocessing pipeline used).
- pipeline
str
{‘cpac’, ‘css’, ‘dparsf’, ‘niak’}, default=’cpac’ Possible pipelines are “ccs”, “cpac”, “dparsf” and “niak”.
- band_pass_filtering
bool
, default=False Due to controversies in the literature, band pass filtering is optional. If true, signal is band filtered between 0.01Hz and 0.1Hz.
- global_signal_regression
bool
, default=False Indicates if global signal regression should be applied on the signals.
- derivatives
list
ofstr
, default=[‘func_preproc’] Types of downloaded files. Possible values are: alff, degree_binarize, degree_weighted, dual_regression, eigenvector_binarize, eigenvector_weighted, falff, func_mask, func_mean, func_preproc, lfcd, reho, rois_aal, rois_cc200, rois_cc400, rois_dosenbach160, rois_ez, rois_ho, rois_tt, and vmhc. Please refer to the PCP site for more details. Will default to
['func_preproc']
ifNone
is passed.- quality_checked
bool
, default=True If true (default), restrict the list of the subjects to the one that passed quality assessment for all raters.
- url
str
, default=None URL of file to download. Override download URL. Used for test only (or if you setup a mirror of the data).
- verbose
int
, default=1 Verbosity level (0 means no message).
- legacy_format
bool
, default=True If set to True, the fetcher will return recarrays. Otherwise, it will return pandas dataframes.
- kwargsparameter list, optional
Any extra keyword argument will be used to filter downloaded subjects according to the CSV phenotypic file. Some examples of filters are indicated below.
- SUB_IDlist of integers in [50001, 50607], optional
Ids of the subjects to be loaded.
- DX_GROUPinteger in {1, 2}, optional
1 is autism, 2 is control.
- DSM_IV_TRinteger in [0, 4], optional
O is control, 1 is autism, 2 is Asperger, 3 is PPD-NOS, 4 is Asperger or PPD-NOS.
- AGE_AT_SCANfloat in [6.47, 64], optional
Age of the subject.
- SEXinteger in {1, 2}, optional
1 is male, 2 is female.
- HANDEDNESS_CATEGORYstring in {‘R’, ‘L’, ‘Mixed’, ‘Ambi’}, optional
R = Right, L = Left, Ambi = Ambidextrous.
- HANDEDNESS_SCOREinteger in [-100, 100], optional
Positive = Right, Negative = Left, 0 = Ambidextrous.
- data_dir
- Returns:
- data
sklearn.utils.Bunch
Dictionary-like object, the keys are described below.
- ‘description’:
str
, description of the dataset.
- ‘description’:
- ‘phenotypic’:
pandas.DataFrame
phenotypic information for each subject.
- ‘phenotypic’:
- Specific Derivative Keys:
Additional keys,’func_preproc’ being the default, are introduced based on the provided ‘derivatives’ parameter during fetching. Any combination of the parameters below may occur.
‘func_preproc’ (default):
numpy.ndarray
, paths to preprocessed functional MRI data in NIfTI format. This key is present by default when fetching the dataset.‘alff’:
numpy.ndarray
, amplitude values of low-frequency fluctuations in functional MRI data.‘degree_binarize’:
numpy.ndarray
, data specific to binarized node degree in brain networks.‘degree_weighted’:
numpy.ndarray
, data specific to weighted node degree, considering connectivity strength in brain networks.‘dual_regression’:
numpy.ndarray
, results from dual regression analysis, often involving the identification of resting-state networks.‘eigenvector_binarize’:
numpy.ndarray
, data specific to binarized eigenvector centrality, a measure of node influence in brain networks.‘eigenvector_weighted’:
numpy.ndarray
, data specific to weighted eigenvector centrality, reflecting node influence with consideration of connectivity strength.‘falff’:
numpy.ndarray
, data specific to fractional amplitude values of low-frequency fluctuations.‘func_mask’:
numpy.ndarray
, functional mask data, often used to define regions of interest.‘func_mean’:
numpy.ndarray
, mean functional MRI data, representing average activity across the brain.‘lfcd’:
numpy.ndarray
, data specific to local functional connectivity density in brain networks.‘reho’:
numpy.ndarray
, data specific to regional homogeneity in functional MRI data.‘rois_aal’:
numpy.ndarray
, data specific to anatomical regions defined by the Automatic Anatomical Labeling atlas.‘rois_cc200’:
numpy.ndarray
data specific to regions defined by the Craddock 200 atlas.‘rois_cc400’:
numpy.ndarray
, data specific to regions defined by the Craddock 400 atlas.‘rois_dosenbach160’:
numpy.ndarray
, data specific to regions defined by the Dosenbach 160 atlas.‘rois_ez’:
numpy.ndarray
, data specific to regions defined by the EZ atlas.‘rois_ho’:
numpy.ndarray
, data specific to regions defined by the Harvard-Oxford atlas.‘rois_tt’:
numpy.ndarray
, data specific to regions defined by the Talairach atlas.‘vmhc’:
numpy.ndarray
, data specific to voxel-mirrored homotopic connectivity in functional MRI data.
- data
Notes
Code and description of preprocessing pipelines are provided on the PCP website.
References