def demo_nyu_rest(data_dir="/tmp/nyu_data", n_subjects=1,
output_dir="/tmp/nyu_rest_output"):
"""Demo for FSL Feeds data.
Parameters
----------
data_dir: string, optional
where the data is located on your disk, where it will be
downloaded to
output_dir: string, optional
where output will be written to
"""
# fetch data
nyu_data = fetch_nyu_rest(data_dir=data_dir, n_subjects=n_subjects)
# subject data factory
def subject_factory(session=1):
session_func = [x for x in nyu_data.func if "session%i" % session in x]
for subject_id in set([os.path.basename(
os.path.dirname
(os.path.dirname(x))) for x in session_func]):
func = [x for x in session_func if subject_id in x]
assert len(func) == 1
func = func[0]
yield SubjectData(subject_id=subject_id, func=func,
output_dir=os.path.join(
output_dir, "session%i" % session,
subject_id))
# invoke demon to run de demo
_fmri_demo_runner(subject_factory(), "NYU Resting State")
def _nyu_rest_factory(session=1):
from pypreprocess.nipype_preproc_spm_utils import SubjectData
nyu_data = fetch_nyu_rest(sessions=[session], n_subjects=7)
session_func = [x for x in nyu_data.func if "session%i" % session in x]
session_anat = [
x for x in nyu_data.anat_skull if "session%i" % session in x]
for subject_id in set([os.path.basename(os.path.dirname
(os.path.dirname(x)))
for x in session_func]):
# instantiate subject_data object
subject_data = SubjectData()
subject_data.subject_id = subject_id
subject_data.session_id = session
# set func
subject_data.func = [x for x in session_func if subject_id in x]
assert len(subject_data.func) == 1
subject_data.func = subject_data.func[0]
# set anat
subject_data.anat = [x for x in session_anat if subject_id in x]
assert len(subject_data.anat) == 1
subject_data.anat = subject_data.anat[0]
# set subject output directory
subject_data.output_dir = "/tmp/%s" % subject_id
subject_data.sanitize(deleteorient=True, niigz2nii=False)
yield (subject_data.subject_id, subject_data.func[0],
subject_data.anat)
def demo_nyu_rest(output_dir):
"""Demo for FSL Feeds data.
Parameters
----------
output_dir: string
where output will be written to
"""
output_dir = os.path.join(output_dir, 'nyu_mrimc_output')
# fetch data
nyu_data = fetch_nyu_rest()
# subject data factory
subjects = []
session = 1
session_func = [x for x in nyu_data.func if "session%i" % session in x]
for subject_id in set([
os.path.basename(os.path.dirname(os.path.dirname(x)))
for x in session_func
]):
# set func
func = [x for x in session_func if subject_id in x]
assert len(func) == 1
func = func[0]
subjects.append(
SubjectData(subject_id=subject_id,
func=func,
output_dir=os.path.join(output_dir,
"session%i" % session,
subject_id)))
# invoke demon to run de demo
_demo_runner(subjects, "NYU resting state")
def _nyu_rest_factory(session=1):
from pypreprocess.nipype_preproc_spm_utils import SubjectData
nyu_data = fetch_nyu_rest(sessions=[session], n_subjects=7)
session_func = [x for x in nyu_data.func if "session%i" % session in x]
session_anat = [
x for x in nyu_data.anat_skull if "session%i" % session in x]
for subject_id in set([os.path.basename(os.path.dirname
(os.path.dirname(x)))
for x in session_func]):
# instantiate subject_data object
subject_data = SubjectData()
subject_data.subject_id = subject_id
subject_data.session_id = session
# set func
subject_data.func = [x for x in session_func if subject_id in x]
assert len(subject_data.func) == 1
subject_data.func = subject_data.func[0]
# set anat
subject_data.anat = [x for x in session_anat if subject_id in x]
assert len(subject_data.anat) == 1
subject_data.anat = subject_data.anat[0]
# set subject output directory
subject_data.output_dir = "/tmp/%s" % subject_id
subject_data.sanitize(deleteorient=True, niigz2nii=False)
yield (subject_data.subject_id, subject_data.func[0],
subject_data.anat)
def demo_nyu_rest(output_dir="/tmp/nyu_mrimc_output",):
"""Demo for FSL Feeds data.
Parameters
----------
data_dir: string, optional
where the data is located on your disk, where it will be
downloaded to
output_dir: string, optional
where output will be written to
"""
# fetch data
nyu_data = fetch_nyu_rest()
# subject data factory
subjects = []
session = 1
session_func = [x for x in nyu_data.func if "session%i" % session in x]
for subject_id in set([os.path.basename(os.path.dirname(os.path.dirname(x))) for x in session_func]):
# set func
func = [x for x in session_func if subject_id in x]
assert len(func) == 1
func = func[0]
subjects.append(
SubjectData(
subject_id=subject_id, func=func, output_dir=os.path.join(output_dir, "session%i" % session, subject_id)
)
)
# invoke demon to run de demo
_demo_runner(subjects, "NYU resting state")
def test_fetch_nyu_rest():
# First session, all subjects
nyu = datasets.fetch_nyu_rest(data_dir=tmpdir, verbose=0)
assert_equal(len(url_request.urls), 2)
assert_equal(len(nyu.func), 25)
assert_equal(len(nyu.anat_anon), 25)
assert_equal(len(nyu.anat_skull), 25)
assert_true(np.all(np.asarray(nyu.session) == 1))
# All sessions, 12 subjects
url_request.reset()
nyu = datasets.fetch_nyu_rest(data_dir=tmpdir, sessions=[1, 2, 3],
n_subjects=12, verbose=0)
# Session 1 has already been downloaded
assert_equal(len(url_request.urls), 2)
assert_equal(len(nyu.func), 36)
assert_equal(len(nyu.anat_anon), 36)
assert_equal(len(nyu.anat_skull), 36)
s = np.asarray(nyu.session)
assert_true(np.all(s[:12] == 1))
assert_true(np.all(s[12:24] == 2))
assert_true(np.all(s[24:] == 3))
def test_fetch_nyu_rest():
# First session, all subjects
nyu = datasets.fetch_nyu_rest(data_dir=tmpdir, verbose=0)
assert_equal(len(url_request.urls), 2)
assert_equal(len(nyu.func), 25)
assert_equal(len(nyu.anat_anon), 25)
assert_equal(len(nyu.anat_skull), 25)
assert_true(np.all(np.asarray(nyu.session) == 1))
# All sessions, 12 subjects
url_request.reset()
nyu = datasets.fetch_nyu_rest(data_dir=tmpdir,
sessions=[1, 2, 3],
n_subjects=12,
verbose=0)
# Session 1 has already been downloaded
assert_equal(len(url_request.urls), 2)
assert_equal(len(nyu.func), 36)
assert_equal(len(nyu.anat_anon), 36)
assert_equal(len(nyu.anat_skull), 36)
s = np.asarray(nyu.session)
assert_true(np.all(s[:12] == 1))
assert_true(np.all(s[12:24] == 2))
assert_true(np.all(s[24:] == 3))
def get_dataset(dataset, max_images=np.inf, **kwargs):
"""Retrieve & normalize dataset from nilearn"""
# Download
if dataset == 'neurovault':
images, term_scores = fetch_neurovault(max_images=max_images, **kwargs)
elif dataset == 'abide':
dataset = datasets.fetch_abide_pcp(
n_subjects=min(94, max_images), **kwargs)
images = [{'absolute_path': p} for p in dataset['func_preproc']]
term_scores = None
elif dataset == 'nyu':
dataset = datasets.fetch_nyu_rest(
n_subjects=min(25, max_images), **kwargs)
images = [{'absolute_path': p} for p in dataset['func']]
term_scores = None
else:
raise ValueError("Unknown dataset: %s" % dataset)
return images, term_scores
"""
Simple example of NiftiMasker use
==================================
Here is a simple example of automatic mask computation using the nifti masker.
The mask is computed and visualized.
"""
### Load nyu_rest dataset #####################################################
from nilearn import datasets
from nilearn.input_data import NiftiMasker
nyu_dataset = datasets.fetch_nyu_rest(n_subjects=1)
# print basic information on the dataset
print('First anatomical nifti image (3D) is at: %s' % nyu_dataset.anat_anon[0])
print('First functional nifti image (4D) is at: %s' %
nyu_dataset.func[0]) # 4D data
### Compute the mask ##########################################################
# As this is raw resting-state EPI, the background is noisy and we cannot
# rely on the 'background' masking strategy. We need to use the 'epi' one
nifti_masker = NiftiMasker(standardize=False,
mask_strategy='epi',
memory="nilearn_cache",
memory_level=2)
func_filename = nyu_dataset.func[0]
nifti_masker.fit(func_filename)
mask_img = nifti_masker.mask_img_
"""
Independent component analysis of resting-state fMRI
=====================================================
An example applying ICA to resting-state data.
"""
### Load nyu_rest dataset #####################################################
from nilearn import datasets
# Here we use only 3 subjects to get faster-running code. For better
# results, simply increase this number
# XXX: must get the code to run for more than 1 subject
nyu_dataset = datasets.fetch_nyu_rest(n_subjects=1)
func_filename = nyu_dataset.func[0]
# print basic information on the dataset
print('First subject anatomical nifti image (3D) is at: %s' %
nyu_dataset.anat_anon[0])
print('First subject functional nifti image (4D) is at: %s' %
nyu_dataset.func[0]) # 4D data
### Preprocess ################################################################
from nilearn.input_data import NiftiMasker
# This is resting-state data: the background has not been removed yet,
# thus we need to use mask_strategy='epi' to compute the mask from the
# EPI images
masker = NiftiMasker(smoothing_fwhm=8, memory='nilearn_cache', memory_level=1,
mask_strategy='epi', standardize=False)
data_masked = masker.fit_transform(func_filename)
def get_nyu_data(data_dir='./datas/brain', n_subjects=1):
dataset = datasets.fetch_nyu_rest(n_subjects=n_subjects, data_dir=data_dir)
imgs = dataset.func
return imgs
ind = np.tril_indices(len(roi_names), k=-1)
dyn_fc = []
for subject in dyn_dataset.subjects:
dyn_fc.append(
loader.load_dynacomp_fc(subject_id=subject,
session='func1',
metric='pc',
msdl=False,
preprocessing_folder='pipeline_1')[ind])
dyn_fc = np.asarray(dyn_fc)
##############################################################################
# NYU rs-fMRI
##############################################################################
nyu_func = fetch_nyu_rest()['func']
masker = NiftiMapsMasker(maps_img=roi_imgs,
low_pass=.1,
high_pass=.01,
t_r=2.,
smoothing_fwhm=6.,
detrend=True,
standardize=False,
resampling_target='maps',
memory_level=0,
verbose=5)
masker.fit()
def mask_and_covariance(f):
x = masker.transform(f)
# -*- coding: utf-8 -*- """ Created on Mon Jun 1 10:21:42 2015 @author: mr243268 """ from embedding import CovEmbedding, vec_to_sym from nilearn.datasets import fetch_nyu_rest, fetch_msdl_atlas from nilearn.input_data import NiftiMapsMasker dataset = fetch_nyu_rest(n_subjects=1) atlas = fetch_msdl_atlas() masker = NiftiMapsMasker(atlas['maps'], detrend=True, standardize=True) masker.fit() ts = masker.transform(dataset.func[0]) cov_embed = CovEmbedding(kind='tangent') output = cov_embed.fit_transform([ts]) m = vec_to_sym(output)
roi_imgs = loader.dict_to_list(loader.load_dynacomp_rois()[0])
roi_names, roi_coords = loader.load_roi_names_and_coords(dyn_dataset.subjects[0])
ind = np.tril_indices(len(roi_names), k=-1)
dyn_fc = []
for subject in dyn_dataset.subjects:
dyn_fc.append(loader.load_dynacomp_fc(subject_id=subject, session='func1',
metric='pc', msdl=False,
preprocessing_folder='pipeline_1')[ind])
dyn_fc = np.asarray(dyn_fc)
##############################################################################
# NYU rs-fMRI
##############################################################################
nyu_func = fetch_nyu_rest()['func']
masker = NiftiMapsMasker(maps_img=roi_imgs,
low_pass=.1,
high_pass=.01,
t_r=2.,
smoothing_fwhm=6., detrend=True, standardize=False,
resampling_target='maps', memory_level=0,
verbose=5)
masker.fit()
def mask_and_covariance(f):
x = masker.transform(f)
return np.corrcoef(x.T)[ind]
# gl = GraphLassoCV(verbose=2)
# gl.fit(x)
# return gl.covariance_[ind]
"""
:Author: DOHMATOB Elvis Dopgima
:Synopsis: Preprocessing of NYU rest data.
"""
import sys
import os
# import API for preprocessing business
from pypreprocess.nipype_preproc_spm_utils import do_subjects_preproc
# input data-grabber for SPM Auditory (single-subject) data
from nilearn.datasets import fetch_nyu_rest
# file containing configuration for preprocessing the data
jobfile = os.path.join(os.path.dirname(sys.argv[0]), "nyu_rest_preproc.ini")
# fetch spm auditory data
sd = fetch_nyu_rest()
# preprocess the data
dataset_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.dirname(sd.anat_skull[0]))))
results = do_subjects_preproc(jobfile, dataset_dir=dataset_dir)
"""
:Author: DOHMATOB Elvis Dopgima
:Synopsis: Preprocessing of NYU rest data.
"""
import sys
import os
# import API for preprocessing business
from pypreprocess.nipype_preproc_spm_utils import do_subjects_preproc
# input data-grabber for SPM Auditory (single-subject) data
from nilearn.datasets import fetch_nyu_rest
# file containing configuration for preprocessing the data
jobfile = os.path.join(os.path.dirname(sys.argv[0]),
"nyu_rest_preproc.ini")
# fetch spm auditory data
sd = fetch_nyu_rest()
# preprocess the data
dataset_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.dirname(
sd.anat_skull[0]))))
results = do_subjects_preproc(jobfile, dataset_dir=dataset_dir)
