Пример #1
0
def fetch_atlas(atlas_name, rois=False):
    """Retruns selected atlas path
    """

    if atlas_name == 'msdl':
        atlas = fetch_msdl_atlas()['maps']
    elif atlas_name == 'harvard_oxford':
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'HarvardOxford-cortl-maxprob-thr0-2mm.nii.gz')
    elif atlas_name == 'juelich':
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'Juelich-maxprob-thr0-2mm.nii.gz')
    elif atlas_name == 'mayo':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_68_rois.nii.gz')
    elif atlas_name == 'canica':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_canica_61_rois.nii.gz')
    elif atlas_name == 'canica141':
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'atlas_canica_141_rois.nii.gz')
    elif atlas_name == 'tvmsdl':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_tv_msdl.nii.gz')

    dmn = None
    if (atlas_name in ['msdl', 'mayo', 'canica']) and rois:
        dmn = fetch_dmn_atlas(atlas_name, atlas)
        atlas_img = index_img(atlas, dmn['rois'])
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_dmn.nii.gz')
        atlas_img.to_filename(atlas)
    return atlas, dmn
Пример #2
0
def fetch_atlas(atlas_name):
    """Retruns selected atlas path
    """
    if atlas_name == 'msdl':
        atlas = fetch_msdl_atlas()['maps']
    elif atlas_name == 'harvard_oxford':
        #        atlas = os.path.join(CACHE_DIR, 'atlas',
        #                             'HarvardOxford-cortl-prob-2mm.nii.gz')
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'HarvardOxford-cortl-maxprob-thr0-2mm.nii.gz')
    elif atlas_name == 'juelich':
        #        atlas = os.path.join(CACHE_DIR, 'atlas',
        #                             'Juelich-prob-2mm.nii.gz')
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'Juelich-maxprob-thr0-2mm.nii.gz')

    elif atlas_name == 'mayo':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_68_rois.nii.gz')
    elif atlas_name == 'canica':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_canica_61_rois.nii.gz')
    elif atlas_name == 'canica141':
        atlas = os.path.join(CACHE_DIR, 'atlas',
                             'atlas_canica_141_rois.nii.gz')
    elif atlas_name == 'tvmsdl':
        atlas = os.path.join(CACHE_DIR, 'atlas', 'atlas_tv_msdl.nii.gz')
    return atlas
Пример #3
0
def load_msdl_names_and_coords():
    """ Returns msdl atlas ROIs
    """
    atlas = fetch_msdl_atlas()
    roi_coords = np.loadtxt(atlas['labels'], dtype=np.float,
                            delimiter=',', skiprows=1, usecols=(0,1,2))

    roi_names = np.loadtxt(atlas['labels'], dtype=np.str,
                            delimiter=',', skiprows=1, usecols=(3,))

    for i in range(len(roi_names)):
        roi_names[i] = roi_names[i].strip()
    roi_names[-1] = roi_names[-1][:10]
    roi_names[-2] = roi_names[-2][:10]
    return roi_names, roi_coords
Пример #4
0
def load_msdl_names_and_coords():
    """ Returns msdl atlas ROIs
    """
    atlas = fetch_msdl_atlas()
    roi_coords = np.loadtxt(atlas['labels'],
                            dtype=np.float,
                            delimiter=',',
                            skiprows=1,
                            usecols=(0, 1, 2))

    roi_names = np.loadtxt(atlas['labels'],
                           dtype=np.str,
                           delimiter=',',
                           skiprows=1,
                           usecols=(3, ))

    for i in range(len(roi_names)):
        roi_names[i] = roi_names[i].strip()
    roi_names[-1] = roi_names[-1][:10]
    roi_names[-2] = roi_names[-2][:10]
    return roi_names, roi_coords
    plt.colorbar()
    plt.title("%s / covariance" % title)

    # Display precision matrix
    plt.figure()
    plt.imshow(prec, interpolation="nearest",
               vmin=-span, vmax=span,
               cmap=plotting.cm.bwr)
    plt.colorbar()
    plt.title("%s / precision" % title)


# Fetching datasets ###########################################################
print("-- Fetching datasets ...")
from nilearn import datasets
msdl_atlas_dataset = datasets.fetch_msdl_atlas()
adhd_dataset = datasets.fetch_adhd(n_subjects=1)


# Extracting region signals ###################################################
import nilearn.image
import nilearn.input_data

from sklearn.externals.joblib import Memory
mem = Memory('nilearn_cache')

masker = nilearn.input_data.NiftiMapsMasker(
    msdl_atlas_dataset.maps, resampling_target="maps", detrend=True,
    low_pass=None, high_pass=0.01, t_r=2.5, standardize=True,
    memory=mem, memory_level=1, verbose=2)
masker.fit()
Пример #6
0
    # Display precision matrix
    plt.figure()
    plt.imshow(prec, interpolation="nearest",
              vmin=-span, vmax=span,
              cmap=plt.cm.get_cmap("bwr"))
    plt.colorbar()
    plt.title("%s / precision" % title)

###############################################################################
###############################################################################

CACHE_DIR = os.path.join('/', 'disk4t', 'mehdi',
                         'data', 'tmp')

dataset = fetch_adni_rs_fmri()
atlas = fetch_msdl_atlas()
func_files = dataset['func']
dx_group = np.array(dataset['dx_group'])
idx = {}
for g in ['AD', 'LMCI', 'EMCI', 'Normal']:
    idx[g] = np.where(dx_group == g)

atlas4d = nib.load(atlas['maps'])
atlas4d_data = atlas4d.get_data()
atlas3d_data = np.sum(atlas4d_data, axis=3)
atlas3d = nib.Nifti1Image(atlas3d_data, atlas4d.get_affine())

n_subjects = len(func_files)
subjects = []
cov_feat = []
Пример #7
0
of functional regions in rest, and the
:class:`nilearn.input_data.NiftiMapsMasker` to extract time series.

Note that the inverse covariance (or precision) contains values that can
be linked to *negated* partial correlations, so we negated it for
display.

As the MSDL atlas comes with (x, y, z) MNI coordinates for the different
regions, we can visualize the matrix as a graph of interaction in a
brain. To avoid having too dense a graph, we represent only the 20% edges
with the highest values.

"""

from nilearn import datasets
atlas = datasets.fetch_msdl_atlas()
atlas_filename = atlas['maps']

# Load the labels
import numpy as np
csv_filename = atlas['labels']

# The recfromcsv function can load a csv file
labels = np.recfromcsv(csv_filename)
names = labels['name']

from nilearn.input_data import NiftiMapsMasker
masker = NiftiMapsMasker(maps_img=atlas_filename,
                         standardize=True,
                         memory='nilearn_cache',
                         verbose=5)
<https://team.inria.fr/parietal/research/spatial_patterns/spatial-patterns-in-resting-state/>`_
of functional regions in rest.

The key to extract signals is to use the
:class:`nilearn.input_data.NiftiMapsMasker` that can transform nifti
objects to time series using a probabilistic atlas.

As the MSDL atlas comes with (x, y, z) MNI coordinates for the different
regions, we can visualize the matrix as a graph of interaction in a
brain. To avoid having too dense a graph, we represent only the 20% edges
with the highest values.

"""

from nilearn import datasets
atlas = datasets.fetch_msdl_atlas()
atlas_filename = atlas['maps']

# Load the labels
import numpy as np
csv_filename = atlas['labels']

# The recfromcsv function can load a csv file
labels = np.recfromcsv(csv_filename)
names = labels['name']

from nilearn.input_data import NiftiMapsMasker
masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True,
                         memory='nilearn_cache', verbose=5)

data = datasets.fetch_adhd(n_subjects=1)
    # Display precision matrix
    plt.figure()
    plt.imshow(prec,
               interpolation="nearest",
               vmin=-span,
               vmax=span,
               cmap=plotting.cm.bwr)
    plt.colorbar()
    plt.title("%s / precision" % title)


# Fetching datasets ###########################################################
print("-- Fetching datasets ...")
from nilearn import datasets
msdl_atlas_dataset = datasets.fetch_msdl_atlas()
adhd_dataset = datasets.fetch_adhd(n_subjects=n_subjects)

# print basic information on the dataset
print('First subject functional nifti image (4D) is at: %s' %
      adhd_dataset.func[0])  # 4D data

# Extracting region signals ###################################################
from nilearn import image
from nilearn import input_data

from sklearn.externals.joblib import Memory
mem = Memory('nilearn_cache')

masker = input_data.NiftiMapsMasker(msdl_atlas_dataset.maps,
                                    resampling_target="maps",
Пример #10
0
def test_fetch_msdl_atlas():
    dataset = datasets.fetch_msdl_atlas(data_dir=tmpdir, verbose=0)
    assert_true(isinstance(dataset.labels, _basestring))
    assert_true(isinstance(dataset.maps, _basestring))
    assert_equal(len(url_request.urls), 1)
# -*- coding: utf-8 -*-
"""
Created on Wed Apr  1 10:11:24 2015

@author: mr243268
"""

import os, time
import numpy as np
from loader import load_dynacomp
from nilearn.datasets import fetch_msdl_atlas
from nilearn.input_data import NiftiMapsMasker

dataset = load_dynacomp(preprocessing_folder='pipeline_2',
                        prefix='resampled_wr')
atlas = fetch_msdl_atlas()

# add mask, smoothing, filtering and detrending
masker = NiftiMapsMasker(maps_img=atlas['maps'],
                         mask_img=dataset.mask,
                         low_pass=.1,
                         high_pass=.01,
                         t_r=1.05,
                         smoothing_fwhm=6.,
                         detrend=True,
                         standardize=False,
                         resampling_target='data',
                         memory_level=0,
                         verbose=5)

for i in range(len(dataset.subjects)):
Пример #12
0
def test_fetch_msdl_atlas():
    dataset = datasets.fetch_msdl_atlas(data_dir=tmpdir, verbose=0)
    assert_true(isinstance(dataset.labels, _basestring))
    assert_true(isinstance(dataset.maps, _basestring))
    assert_equal(len(url_request.urls), 1)