def ica_vis(subj_num): # Use the mean as a background mean_img_1 = image.mean_img(BOLD_file_1) mean_img_2 = image.mean_img(BOLD_file_2) mean_img_3 = image.mean_img(BOLD_file_3) plot_stat_map(image.index_img(component_img_1, 5), mean_img_1, output_file=os.path.join(data_path,'sub'+subj_num+'_BOLD','task001_run001'+'ica_1'+'.jpg')) plot_stat_map(image.index_img(component_img_1, 12), mean_img_1, output_file=os.path.join(data_path,'sub'+subj_num+'_BOLD','task001_run001'+'ica_2'+'.jpg')) plot_stat_map(image.index_img(component_img_2, 5), mean_img_2, output_file=os.path.join(data_path,'sub'+subj_num+'_BOLD','task002_run001'+'ica_1'+'.jpg')) plot_stat_map(image.index_img(component_img_2, 12), mean_img_2, output_file=os.path.join(data_path,'sub'+subj_num+'_BOLD','task002_run001'+'ica_2'+'.jpg'))
def test_coregister():
anat_file = os.path.join(os.path.dirname(testing_data.__file__),
'anat.nii.gz')
func_file = os.path.join(os.path.dirname(testing_data.__file__),
'func.nii.gz')
mean_func_file = os.path.join(tst.tmpdir, 'mean_func.nii.gz')
mean_img(func_file).to_filename(mean_func_file)
bunch = func.coregister(anat_file,
mean_func_file,
tst.tmpdir,
slice_timing=False,
verbose=False,
reorient_only=True)
assert_true(
_check_same_fov(nibabel.load(bunch.coreg_func_),
nibabel.load(bunch.coreg_anat_)))
assert_true(_check_same_obliquity(bunch.coreg_anat_, bunch.coreg_func_))
assert_true(os.path.isfile(bunch.coreg_transform_))
assert_less(0, len(bunch.coreg_warps_))
assert_true(bunch.coreg_warps_[-1] is None) # Last slice in functional
# is without signal
for warp_file in bunch.coreg_warps_[:-1]:
assert_true(os.path.isfile(warp_file))
# Check environement variables setting
assert_raises_regex(RuntimeError,
"3dcopy",
func.coregister,
anat_file,
mean_func_file,
tst.tmpdir,
slice_timing=False,
verbose=False,
reorient_only=True,
AFNI_DECONFLICT='NO')
# Check caching does not change the paths
bunch2 = func.coregister(anat_file,
mean_func_file,
tst.tmpdir,
slice_timing=False,
verbose=False,
caching=True,
reorient_only=True,
AFNI_DECONFLICT='OVERWRITE')
assert_equal(bunch.coreg_func_, bunch2.coreg_func_)
assert_equal(bunch.coreg_anat_, bunch2.coreg_anat_)
assert_equal(bunch.coreg_transform_, bunch2.coreg_transform_)
for warp_file, warp_file2 in zip(bunch.coreg_warps_, bunch2.coreg_warps_):
assert_equal(warp_file, warp_file2)
def init(subject,layer,filename_irm,filename_mask,filename_stimuli):
#we transform the layer and subject variables in order to use them in the input path
if subject < 10:
subject = '0' + str(subject)
else:
subject = str(subject)
if layer < 10:
layer = '0' + str(layer)
else:
layer = str(layer)
print("Initializing tests for subject " + subject + " and layer " + layer + " ...")
#we dig out our data from these files and we create the mask in order to have a better rendering in the future plots
meanepi = (mean_img(filename_irm))
loaded_stimuli = np.load(filename_stimuli)
masker = NiftiMasker(mask_img=filename_mask, detrend=True,standardize=True)
masker.fit()
fmri_data = masker.transform(filename_irm)
fmri_ready = fmri_data[17:-(fmri_data.shape[0]-17-loaded_stimuli.shape[0])]
# building the encoding models
middle = int(loaded_stimuli.shape[0]/2)
y_train = fmri_ready[:middle]
y_test = fmri_ready[middle:]
X_train = (loaded_stimuli[:middle])
X_test = (loaded_stimuli[middle:])
print("Init done")
return X_train,X_test,y_train,y_test,masker,meanepi
def p_map(task, run, p_values_3d, threshold=0.05):
"""
Generate three thresholded p-value maps.
Parameters
----------
task: int
Task number
run: int
Run number
p_value_3d: 3D array of p_value.
threshold: The cutoff value to determine significant voxels.
Returns
-------
threshold p-value images
"""
fmri_img = image.smooth_img('../../../data/sub001/BOLD/' + 'task00' +
str(task) + '_run00' + str(run) +
'/filtered_func_data_mni.nii.gz',
fwhm=6)
mean_img = image.mean_img(fmri_img)
log_p_values = -np.log10(p_values_3d)
log_p_values[np.isnan(log_p_values)] = 0.
log_p_values[log_p_values > 10.] = 10.
log_p_values[log_p_values < -np.log10(threshold)] = 0
plot_stat_map(nib.Nifti1Image(log_p_values, fmri_img.get_affine()),
mean_img, title="Thresholded p-values",
annotate=False, colorbar=True)
def _run_interface(self, runtime):
import nibabel as nib
from nilearn import plotting, datasets, image
from nipype.interfaces.base import isdefined
import numpy as np
import pylab as plt
import os
wra_img = nib.load(self.inputs.wra_img)
canonical_img = nib.load(self.inputs.canonical_img)
title = self.inputs.title
mean_wraimg = image.mean_img(wra_img)
if title != "":
filename = title.replace(" ", "_") + ".pdf"
else:
filename = "plot.pdf"
fig = plotting.plot_anat(mean_wraimg,
title="wrafunc & canonical single subject",
cut_coords=range(-40, 40, 10),
display_mode='z')
fig.add_edges(canonical_img)
fig.savefig(filename)
fig.close()
self._plot = filename
runtime.returncode = 0
return runtime
def make_img(dataset, svc):
print("Making Image.....")
# Here is the image
coef = svc.coef_
# reverse feature selection
coef = feature_selection.inverse_transform(coef)
# reverse masking
weight_img = masker.inverse_transform(coef)
# Use the mean image as a background to avoid relying on anatomical data
from nilearn import image
mean_img = image.mean_img(dataset)
mean_img.to_filename(
'projects/niblab/bids_projects/Experiments/ChocoData/derivatives/code/decoding/milkshake_vs_h2O/images/exclusive/p2_mean_nimask.nii'
)
# Create the figure
from nilearn.plotting import plot_stat_map, show
display = plot_stat_map(weight_img, mean_img, title='Milkshake vs. H2O')
display.savefig(
'/projects/niblab/bids_projects/Experiments/ChocoData/derivatives/code/decoding/milkshake_vs_h2O/images/exclusive/p2_SVM_nimask.png'
)
# Saving the results as a Nifti file may also be important
weight_img.to_filename(
'/projects/niblab/bids_projects/Experiments/ChocoData/derivatives/code/decoding/milkshake_vs_h2O/images/exclusive/p2_SVM_nimask.nii'
)
def plot_region_overlay(roi_img, func_img, fname, cmap):
"""Overlay mask/atlas on mean functional image.
Parameters
----------
roi_img : str
File name of atlas/mask image
func_img : str
File name of 4D functional image that was used in extraction.
cmap : matplotlib.colors.LinearSegmentedColormap
Colormap to use.
Returns
-------
matplotlib.pyplot.figure
Atlas/mask plot
"""
# compute mean of functional image
bg_img = mean_img(func_img)
n_cuts = 7
fig, axes = plt.subplots(3, 1, figsize=(15, 6))
g = plot_roi(roi_img,
bg_img=bg_img,
display_mode='z',
axes=axes[0],
alpha=.66,
cut_coords=np.linspace(-50, 60, num=n_cuts),
cmap=cmap,
black_bg=True,
annotate=False)
g.annotate(size=8)
g = plot_roi(roi_img,
bg_img=bg_img,
display_mode='x',
axes=axes[1],
alpha=.66,
cut_coords=np.linspace(-60, 60, num=n_cuts),
cmap=cmap,
black_bg=True,
annotate=False)
g.annotate(size=8)
g = plot_roi(roi_img,
bg_img=bg_img,
display_mode='y',
axes=axes[2],
alpha=.66,
cut_coords=np.linspace(-90, 60, num=n_cuts),
cmap=cmap,
black_bg=True,
annotate=False)
g.annotate(size=8)
fname += '_mask_overlay.png'
fig.savefig(fname, bbox_inches='tight')
plt.close()
# just get figure directory + file for html
fig_path = os.path.basename(os.path.dirname(fname))
return os.path.join(fig_path, os.path.basename(fname))
def report_flm_fiac(): # pragma: no cover
data = datasets.func.fetch_fiac_first_level()
fmri_img = [data['func1'], data['func2']]
from nilearn.image import mean_img
mean_img_ = mean_img(fmri_img[0])
design_files = [data['design_matrix1'], data['design_matrix2']]
design_matrices = [pd.DataFrame(np.load(df)['X']) for df in design_files]
fmri_glm = FirstLevelModel(mask_img=data['mask'], minimize_memory=True)
fmri_glm = fmri_glm.fit(fmri_img, design_matrices=design_matrices)
n_columns = design_matrices[0].shape[1]
contrasts = {
'SStSSp_minus_DStDSp': _pad_vector([1, 0, 0, -1], n_columns),
'DStDSp_minus_SStSSp': _pad_vector([-1, 0, 0, 1], n_columns),
'DSt_minus_SSt': _pad_vector([-1, -1, 1, 1], n_columns),
'DSp_minus_SSp': _pad_vector([-1, 1, -1, 1], n_columns),
'DSt_minus_SSt_for_DSp': _pad_vector([0, -1, 0, 1], n_columns),
'DSp_minus_SSp_for_DSt': _pad_vector([0, 0, -1, 1], n_columns),
'Deactivation': _pad_vector([-1, -1, -1, -1, 4], n_columns),
'Effects_of_interest': np.eye(n_columns)[:5]
}
report = make_glm_report(
fmri_glm,
contrasts,
bg_img=mean_img_,
height_control='fdr',
)
output_filename = 'generated_report_flm_fiac.html'
output_filepath = os.path.join(REPORTS_DIR, output_filename)
report.save_as_html(output_filepath)
report.get_iframe()
def t2starw(self):
if self._t2starw is None:
self._t2starw = image.mean_img(self.t2starw_echoes)
self._t2starw = image.math_img('im / np.percentile(im, 95) * 4095',
im=self._t2starw)
return self._t2starw
def p_map(task, run, p_values_3d, threshold=0.05):
"""
Generate three thresholded p-value maps.
Parameters
----------
task: int
Task number
run: int
Run number
p_value_3d: 3D array of p_value.
threshold: The cutoff value to determine significant voxels.
Returns
-------
threshold p-value images
"""
fmri_img = image.smooth_img('../../../data/sub001/BOLD/' + 'task00' +
str(task) + '_run00' + str(run) +
'/filtered_func_data_mni.nii.gz',
fwhm=6)
mean_img = image.mean_img(fmri_img)
log_p_values = -np.log10(p_values_3d)
log_p_values[np.isnan(log_p_values)] = 0.
log_p_values[log_p_values > 10.] = 10.
log_p_values[log_p_values < -np.log10(threshold)] = 0
plot_stat_map(nib.Nifti1Image(log_p_values, fmri_img.get_affine()),
mean_img,
title="Thresholded p-values",
annotate=False,
colorbar=True)
def _run_interface(self, runtime):
import matplotlib
matplotlib.use('Agg')
import pylab as plt
wra_img = nib.load(self.inputs.wra_img)
canonical_img = nib.load(self.inputs.canonical_img)
title = self.inputs.title
mean_wraimg = image.mean_img(wra_img)
if title != "":
filename = title.replace(" ", "_") + ".pdf"
else:
filename = "plot.pdf"
fig = plotting.plot_anat(mean_wraimg,
title="wrafunc & canonical single subject",
cut_coords=range(-40, 40, 10),
display_mode='z')
fig.add_edges(canonical_img)
fig.savefig(filename)
fig.close()
self._plot = filename
runtime.returncode = 0
return runtime
def searchlight(x,
y,
m=None,
groups=None,
cv=None,
write=False,
logger=None,
**searchlight_args):
"""
Wrapper to launch searchlight
:param x: Data
:param y: labels
:param m: mask
:param groups: group labels
:param cv: cross validator
:param write: if image for writing is desired or not
:param logger:
:param searchlight_args:(default) process_mask_img(None),
radius(2mm), estimator(svc),
n_jobs(-1), scoring(none), cv(3fold), verbose(0)
:return: trained SL object and SL results
"""
write_to_logger("starting searchlight... ", logger)
from nilearn import image, decoding, masking
if m is None:
m = masking.compute_epi_mask(x)
write_to_logger("searchlight params: " + str(searchlight_args))
sl = decoding.SearchLight(mask_img=m, cv=cv, **searchlight_args)
sl.fit(x, y, groups)
if write:
return sl, image.new_img_like(image.mean_img(x), sl.scores_)
else:
return sl
def _run_interface(self, runtime):
import matplotlib
matplotlib.use('Agg')
import nibabel as nib
from nilearn import plotting, datasets, image
from nipype.interfaces.base import isdefined
import numpy as np
import pylab as plt
import os
wra_img = nib.load(self.inputs.wra_img)
canonical_img = nib.load(self.inputs.canonical_img)
title = self.inputs.title
mean_wraimg = image.mean_img(wra_img)
if title != "":
filename = title.replace(" ", "_")+".pdf"
else:
filename = "plot.pdf"
fig = plotting.plot_anat(mean_wraimg, title="wrafunc & canonical single subject", cut_coords=range(-40, 40, 10), display_mode='z')
fig.add_edges(canonical_img)
fig.savefig(filename)
fig.close()
self._plot = filename
runtime.returncode=0
return runtime
def compute_subj_mask(subj):
num = 0
print 'Loading BOLD subject #%i...' % subj
bold = load(path.join(data_dir, 'sub%03d/BOLD/task001_run00%i/bold_dico.nii.gz' % (subj, num+1)))
print 'Averaging BOLD...'
avg = image.mean_img(bold)
print 'Saving average EPI...'
avg_path = path.join(mask_dir, 'mean_sub%03d_run00%i.nii.gz' % (subj, num+1))
affine = avg.get_affine()
save(avg, avg_path)
print 'Aligning the surface...'
cortex.align.automatic('sub%03d' % subj, 'auto01', avg_path)
m_thick = cortex.db.get_mask('sub%03d' % subj, 'auto01', type='thick')
print 'Thick mask is computed: %i voxels' % m_thick.sum()
m_thin = cortex.db.get_mask('sub%03d' % subj, 'auto01', type='thin')
print 'Thin mask is computed: %i voxels' % m_thin.sum()
# .T is important here, because pycortex and nibabel have different
# assumptions about the axis order
thick = Nifti1Image(np.float32(m_thick.T), affine)
thin = Nifti1Image(np.float32(m_thin.T), affine)
save(thick, path.join(mask_dir, 'sub%03d_mask_thick.nii.gz' % subj))
save(thin, path.join(mask_dir, 'sub%03d_mask_thin.nii.gz' % subj))
def generate_fmri_data_for_subject(subject):
"""
Input : Take as input each fmri file. One file = One block
Load all fmri data and apply a global mask mak on it. The global mask is computed using the mask from each fmri run (block).
Applying a global mask for a subject uniformize the data.
Output: Output fmri_runs for a subject, corrected using a global mask
"""
fmri_filenames = sorted(
glob.glob(
os.path.join(paths.rootpath, "fmri-data/en", "sub-%03d" % subject,
"func", "resample*.nii")))
masks_filenames = sorted(
glob.glob(
os.path.join(paths.path2Data, "en/fmri_data/masks",
"sub_{}".format(subject), "resample*.pkl")))
masks = []
for file in masks_filenames:
with open(file, 'rb') as f:
mask = pickle.load(f)
masks.append(mask)
global_mask = math_img('img>0.5', img=mean_img(masks))
masker = MultiNiftiMasker(global_mask, detrend=True, standardize=True)
masker.fit()
fmri_runs = [masker.transform(f) for f in tqdm(fmri_filenames)]
print(fmri_runs[0].shape)
return fmri_runs
def _run_interface(self, runtime):
import matplotlib
matplotlib.use("Agg")
import pylab as plt
wra_img = nib.load(self.inputs.wra_img)
canonical_img = nib.load(self.inputs.canonical_img)
title = self.inputs.title
mean_wraimg = image.mean_img(wra_img)
if title != "":
filename = title.replace(" ", "_") + ".pdf"
else:
filename = "plot.pdf"
fig = plotting.plot_anat(
mean_wraimg, title="wrafunc & canonical single subject", cut_coords=range(-40, 40, 10), display_mode="z"
)
fig.add_edges(canonical_img)
fig.savefig(filename)
fig.close()
self._plot = filename
runtime.returncode = 0
return runtime
def spikes_mask(in_file, in_mask=None, out_file=None):
"""
Utility function to calculate a mask in which check
for :abbr:`EM (electromagnetic)` spikes.
"""
import os.path as op
import nibabel as nb
import numpy as np
from nilearn.image import mean_img
from nilearn.plotting import plot_roi
from scipy import ndimage as nd
if out_file is None:
fname, ext = op.splitext(op.basename(in_file))
if ext == '.gz':
fname, ext2 = op.splitext(fname)
ext = ext2 + ext
out_file = op.abspath('{}_spmask{}'.format(fname, ext))
out_plot = op.abspath('{}_spmask.pdf'.format(fname))
in_4d_nii = nb.load(in_file)
orientation = nb.aff2axcodes(in_4d_nii.affine)
if in_mask:
mask_data = nb.load(in_mask).get_data()
a = np.where(mask_data != 0)
bbox = np.max(a[0]) - np.min(a[0]), np.max(a[1]) - \
np.min(a[1]), np.max(a[2]) - np.min(a[2])
longest_axis = np.argmax(bbox)
# Input here is a binarized and intersected mask data from previous section
dil_mask = nd.binary_dilation(mask_data,
iterations=int(
mask_data.shape[longest_axis] / 9))
rep = list(mask_data.shape)
rep[longest_axis] = -1
new_mask_2d = dil_mask.max(axis=longest_axis).reshape(rep)
rep = [1, 1, 1]
rep[longest_axis] = mask_data.shape[longest_axis]
new_mask_3d = np.logical_not(np.tile(new_mask_2d, rep))
else:
new_mask_3d = np.zeros(in_4d_nii.shape[:3]) == 1
if orientation[0] in ['L', 'R']:
new_mask_3d[0:2, :, :] = True
new_mask_3d[-3:-1, :, :] = True
else:
new_mask_3d[:, 0:2, :] = True
new_mask_3d[:, -3:-1, :] = True
mask_nii = nb.Nifti1Image(new_mask_3d.astype(np.uint8),
in_4d_nii.get_affine(), in_4d_nii.get_header())
mask_nii.to_filename(out_file)
plot_roi(mask_nii, mean_img(in_4d_nii), output_file=out_plot)
return out_file, out_plot
def plot(self, downsample=1, out_base="."):
out_path = os.path.join(out_base, self.subject, self.name, self.task)
os.makedirs(out_path, exist_ok=True)
raw = nib.load(self.path)
M = np.max(raw.get_data())
n = raw.shape[3]
mean = nimage.mean_img(raw)
xyzcuts = nilplot.find_xyz_cut_coords(mean)
xcuts = nilplot.find_cut_slices(mean, "x")
ycuts = nilplot.find_cut_slices(mean, "y")
zcuts = nilplot.find_cut_slices(mean, "z")
del raw
nrange = range(0, n, downsample)
for i, img in enumerate(nimage.iter_img(self.path)):
if i in nrange:
nilplot.plot_epi(nimage.math_img("img / %f" % (M), img=img),
colorbar=False,
output_file="%s/orth_epi%0d.png" %
(out_path, i),
annotate=True,
cut_coords=xyzcuts,
cmap="gist_heat")
nilplot.plot_epi(nimage.math_img("img / %f" % (M), img=img),
colorbar=False,
output_file="%s/x_epi%0d.png" % (out_path, i),
annotate=True,
display_mode="x",
cut_coords=xcuts,
cmap="gist_heat")
nilplot.plot_epi(nimage.math_img("img / %f" % (M), img=img),
colorbar=False,
output_file="%s/y_epi%0d.png" % (out_path, i),
annotate=True,
display_mode="y",
cut_coords=ycuts,
cmap="gist_heat")
nilplot.plot_epi(nimage.math_img("img / %f" % (M), img=img),
colorbar=False,
output_file="%s/z_epi%0d.png" % (out_path, i),
annotate=True,
display_mode="z",
cut_coords=zcuts,
cmap="gist_heat")
slice_names = ["orth_epi", "x_epi", "y_epi", "z_epi"]
for slic in slice_names:
filenames = ["%s/%s%0d.png" % (out_path, slic, i) for i in nrange]
with imageio.get_writer('%s/%s.gif' % (out_path, slic),
mode='I') as writer:
for i, filename in zip(nrange, filenames):
image = Image.open(filename)
draw = ImageDraw.Draw(image)
fnt = ImageFont.truetype('Pillow/Tests/fonts/FreeMono.ttf',
16)
draw.text((2, 2), str(i), font=fnt, fill=(255, 0, 0, 255))
image.save(filename, "PNG")
image = imageio.imread(filename)
writer.append_data(image)
def correlation_searchlight(A,
B,
mask=None,
radius=2,
interpolate=False,
n_jobs=1,
data_dir=None):
"""
Parameters
----------
A : list
list of (even_trials, odd_trials) tuples for the first condition (A);
each tuple represents a subject's mean fMRI data for both trials, and
even/odd_trials should be a 3D niimg or path (string) to a NIfTI file
B : list
list of (even_trials, odd_trials) tuples for the second condition (B);
formatted the same as A
mask : Niimg-like object
boolean image giving location of voxels containing usable signals
radius : int
radius of the searchlight sphere
interpolate : bool
whether or not to skip every other sphere and interpolate the results;
used to speed up the analysis
n_jobs : int
number of CPUs to split the work up between (-1 means "all CPUs")
data_dir : string
path to directory where MVPA results should be stored
Returns
-------
score_map_fpaths : list
list of paths to NIfTI files representing the MVPA scores for each
subject
"""
if not mask:
niimgs = [niimg for trials in A + B for niimg in trials]
mask = compute_epi_mask(mean_img(concat_imgs(niimgs)))
spheres = extract_spheres(get_data(mask), radius, interpolate)
_analyze_subject = partial(analyze_subject,
spheres=spheres,
interpolate=interpolate,
mask=mask,
data_dir=data_dir)
if n_jobs > 1 or n_jobs == -1:
score_map_fpaths = concurrent_exec(
_analyze_subject,
[(i, _A, _B) for i, (_A, _B) in enumerate(zip(A, B))], n_jobs)
else:
score_map_fpaths = []
for subject_id, (_A, _B) in enumerate(zip(A, B)):
score_map_fpath = _analyze_subject(subject_id, _A, _B)
score_map_fpaths.append(score_map_fpath)
return score_map_fpaths
def spikes_mask(in_file, in_mask=None, out_file=None):
"""
Utility function to calculate a mask in which check
for :abbr:`EM (electromagnetic)` spikes.
"""
import os.path as op
import nibabel as nb
import numpy as np
from nilearn.image import mean_img
from nilearn.plotting import plot_roi
from scipy import ndimage as nd
if out_file is None:
fname, ext = op.splitext(op.basename(in_file))
if ext == '.gz':
fname, ext2 = op.splitext(fname)
ext = ext2 + ext
out_file = op.abspath('{}_spmask{}'.format(fname, ext))
out_plot = op.abspath('{}_spmask.pdf'.format(fname))
in_4d_nii = nb.load(in_file)
orientation = nb.aff2axcodes(in_4d_nii.affine)
if in_mask:
mask_data = nb.load(in_mask).get_data()
a = np.where(mask_data != 0)
bbox = np.max(a[0]) - np.min(a[0]), np.max(a[1]) - \
np.min(a[1]), np.max(a[2]) - np.min(a[2])
longest_axis = np.argmax(bbox)
# Input here is a binarized and intersected mask data from previous section
dil_mask = nd.binary_dilation(
mask_data, iterations=int(mask_data.shape[longest_axis] / 9))
rep = list(mask_data.shape)
rep[longest_axis] = -1
new_mask_2d = dil_mask.max(axis=longest_axis).reshape(rep)
rep = [1, 1, 1]
rep[longest_axis] = mask_data.shape[longest_axis]
new_mask_3d = np.logical_not(np.tile(new_mask_2d, rep))
else:
new_mask_3d = np.zeros(in_4d_nii.shape[:3]) == 1
if orientation[0] in ['L', 'R']:
new_mask_3d[0:2, :, :] = True
new_mask_3d[-3:-1, :, :] = True
else:
new_mask_3d[:, 0:2, :] = True
new_mask_3d[:, -3:-1, :] = True
mask_nii = nb.Nifti1Image(new_mask_3d.astype(np.uint8), in_4d_nii.get_affine(),
in_4d_nii.get_header())
mask_nii.to_filename(out_file)
plot_roi(mask_nii, mean_img(in_4d_nii), output_file=out_plot)
return out_file, out_plot
def sbc_group(in_dir, out_dir):
"""
for each session: load sbc (z transformed) of all subjects and calculate mean & sd
"""
os.makedirs(out_dir, exist_ok=True)
niis = glob(os.path.join(in_dir, "*.nii.gz"))
sessions = list(
set(
map(lambda f: os.path.basename(f).split("_")[-1].split(".")[0],
niis)))
sessions.sort()
print("calc mean sbc for {}".format(sessions))
for ses in sessions:
niis = glob(os.path.join(in_dir, "*{}.nii.gz".format(ses)))
niis.sort()
print(niis)
from nilearn import image, plotting
out_filename_mean_nii = os.path.join(
out_dir, "sbc_1_mean_ses-{}.nii.gz".format(ses))
out_filename_sd_nii = os.path.join(
out_dir, "sbc_1_sd_ses-{}.nii.gz".format(ses))
out_filename_mean_png = os.path.join(
out_dir, "sbc_2_mean_ses-{}.png".format(ses))
out_filename_sd_png = os.path.join(out_dir,
"sbc_2_sd_ses-{}.png".format(ses))
out_filename_list = os.path.join(out_dir,
"sbc_ses-{}_scans.txt".format(ses))
mean_sbc = image.mean_img(niis)
mean_sbc.to_filename(out_filename_mean_nii)
concat_img = image.concat_imgs(niis)
sd_sbc = image.math_img("np.std(img, axis=-1)", img=concat_img)
sd_sbc.to_filename(out_filename_sd_nii)
with open(out_filename_list, "w") as fi:
fi.write("\n".join(niis))
display = plotting.plot_stat_map(
mean_sbc,
threshold=0.5,
cut_coords=(0, -52, 18),
title="mean sbc {} (fisher z)".format(ses))
display.add_markers(marker_coords=[(0, -52, 18)],
marker_color='g',
marker_size=300)
display.savefig(out_filename_mean_png)
display.close()
display = plotting.plot_stat_map(
sd_sbc,
cut_coords=(0, -52, 18),
title="sd sbc {} (fisher z)".format(ses))
display.add_markers(marker_coords=[(0, -52, 18)],
marker_color='g',
marker_size=300)
display.savefig(out_filename_sd_png)
display.close()
def mean_img(in_file, out_file=None):
""" Use nilearn.image.mean_img.
Returns
-------
out_file: str
The absolute path to the output file.
"""
import nilearn.image as niimg
return niimg.mean_img(in_file)
def mean_img(in_file, out_file=None):
""" Use nilearn.image.mean_img.
Returns
-------
out_file: str
The absolute path to the output file.
"""
import nilearn.image as niimg
return niimg.mean_img(in_file)
def glass_brain(r2_voxels, subject, current_ROI, ROI_name, name):
"""
Input : Masked results of r2score
Take masked data and project it again in a 3D space
Ouput : 3D glassbrain of r2score
"""
# Get one mask and fit it to the corresponding ROI
if current_ROI != -1 and current_ROI <= 5:
masks_ROIs_filenames = sorted(
glob.glob(os.path.join(paths.path2Data, "en/ROIs_masks/",
"*.nii")))
ROI_mask = masks_ROIs_filenames[current_ROI]
ROI_mask = NiftiMasker(ROI_mask, detrend=True, standardize=True)
ROI_mask.fit()
unmasked_data = ROI_mask.inverse_transform(r2_voxels)
# Get masks and fit a global mask
else:
masks = []
masks_filenames = sorted(
glob.glob(
os.path.join(paths.path2Data, "en/fmri_data/masks",
"sub_{}".format(subject), "resample*.pkl")))
for file in masks_filenames:
with open(file, 'rb') as f:
mask = pickle.load(f)
masks.append(mask)
global_mask = math_img('img>0.5', img=mean_img(masks))
masker = MultiNiftiMasker(global_mask, detrend=True, standardize=True)
masker.fit()
unmasked_data = masker.inverse_transform(r2_voxels)
display = plot_glass_brain(unmasked_data,
display_mode='lzry',
threshold='auto',
colorbar=True,
title='Sub_{}'.format(subject))
if not os.path.exists(
os.path.join(paths.path2Figures, 'glass_brain',
'Sub_{}'.format(subject), ROI_name)):
os.makedirs(
os.path.join(paths.path2Figures, 'glass_brain',
'Sub_{}'.format(subject), ROI_name))
display.savefig(
os.path.join(paths.path2Figures, 'glass_brain',
'Sub_{}'.format(subject), ROI_name,
'R_squared_test_{}.png'.format(name)))
print(
'Figure Path : ',
os.path.join(paths.path2Figures, 'glass_brain',
'Sub_{}'.format(subject), ROI_name,
'R_squared_test_{}.png'.format(name)))
display.close()
def _make_psc(data):
mean_img = image.mean_img(data)
# Replace 0s for numerical reasons
mean_data = mean_img.get_data()
mean_data[mean_data == 0] = 1
denom = image.new_img_like(mean_img, mean_data)
return image.math_img('data / denom[..., np.newaxis] * 100 - 100',
data=data, denom=denom)
def mean_nodiff_fct(in_file, bval_file, nodiff_b=0):
import os, numpy as np
from nilearn import image
bvals = np.loadtxt(bval_file)
nodiff_index = bvals <= nodiff_b
nodiff_img = image.index_img(in_file, nodiff_index)
mean_nodiff_img = image.mean_img(nodiff_img)
out_file = os.path.abspath('mean_nodiff.nii.gz')
mean_nodiff_img.to_filename(out_file)
return out_file
def data_to_img(d, img, copy_header=False):
"""
Wrapper for new_image_like
:param img: Image with header you want to add
:param d: data
:param copy_header: Boolean
:param logger: logger instance
:return: Image file
"""
return image.new_img_like(image.mean_img(img), d, copy_header=copy_header)
def _process_second_level_input(second_level_input):
"""Helper function to process second_level_input."""
if isinstance(second_level_input, pd.DataFrame):
return _process_second_level_input_as_dataframe(second_level_input)
elif (hasattr(second_level_input, "__iter__")
and isinstance(second_level_input[0], FirstLevelModel)):
return _process_second_level_input_as_firstlevelmodels(
second_level_input)
else:
return mean_img(second_level_input), None
def gm_mask(db, ref_affine, ref_shape, threshold=.25):
""" Utility to create a gm mask by averaging glm images from the db """
from nilearn.image import mean_img
import nibabel as nib
gm_imgs = db[db.contrast == 'gm'].path.values
mean_gm = mean_img(gm_imgs,
target_affine=ref_affine,
target_shape=ref_shape)
gm_mask = nib.Nifti1Image((mean_gm.get_data() > .25).astype('uint8'),
ref_affine)
return mean_gm, gm_mask
def refvol(self): #create reference bold, bold mask, and mask the ref
refs = [nib.load( os.path.join(self.subj.prep_dir,folder[0],file) )
for folder in os.walk(self.subj.prep_dir)
for file in folder[2]
if '%s_boldref.nii.gz'%(self.space) in file]
ref = mean_img(refs)
nib.save(ref,self.subj.refvol)
masks = [nib.load( os.path.join(self.subj.prep_dir,folder[0],file) )
for folder in os.walk(self.subj.prep_dir)
for file in folder[2]
if '%s_desc-brain_mask.nii.gz'%(self.space) in file]
mask = mean_img(masks)
mask = threshold_img(mask,.1)
nib.save(mask,self.subj.refvol_mask)
os.system('fslmaths %s -bin %s'%(self.subj.refvol_mask,self.subj.refvol_mask))
os.system('fslmaths %s -mas %s %s'%(self.subj.refvol,self.subj.refvol_mask,self.subj.refvol_brain))
def compute_global_masker(rootdir, subjects):
masks = [
compute_epi_mask(
glob.glob(
os.path.join(rootdir, "fmri-data/en", "sub-%03d" % s, "func",
"*.nii"))) for s in subjects
]
global_mask = math_img('img>0.5', img=mean_img(masks))
masker = MultiNiftiMasker(global_mask, detrend=True, standardize=True)
masker.fit()
return masker
def compute_global_masker(files): # [[path, path2], [path3, path4]]
# return a MultiNiftiMasker object
masks = [compute_epi_mask(f) for f in files]
global_mask = math_img(
'img>0.5',
img=mean_img(masks)) # take the average mask and threshold at 0.5
masker = MultiNiftiMasker(
global_mask, detrend=True, standardize=True
) # return a object that transforms a 4D barin into a 2D matrix of voxel-time and can do the reverse action
masker.fit()
return masker
def create_group_mask(mask_loc, fmriprep_dir, threshold=.8, verbose=True):
if verbose:
print('Creating Group mask...')
makedirs(path.dirname(mask_loc), exist_ok=True)
brainmasks = glob(
path.join(fmriprep_dir, 'sub-s???', '*', 'func',
'*MNI152NLin2009cAsym_brainmask*'))
mean_mask = image.mean_img(brainmasks)
group_mask = image.math_img("a>=%s" % str(threshold), a=mean_mask)
group_mask.to_filename(mask_loc)
if verbose:
print('Finished creating group mask')
def compute_mean_epi(fmri_filenames, output_pathway):
fmri_img = smooth_img(fmri_filenames, fwhm=5)
mean_epi = mean_img(fmri_img)
# Save
mean_epi.to_filename(os.path.join(output_pathway, 'mean_epi.nii.gz'))
# Plot
plotting.plot_epi(mean_epi, title='Smoothed mean EPI',
output_file=os.path.join(output_pathway, 'mean_epi.png'))
return mean_epi
def compute_global_masker(files, **kwargs): # [[path, path2], [path3, path4]]
"""Returns a NiftiMasker object from list (of list) of files.
Arguments:
- files: list (of list of str)
Returns:
- masker: NiftiMasker
"""
masks = [compute_epi_mask(f) for f in files]
global_mask = math_img('img>0.95', img=mean_img(masks)) # take the average mask and threshold at 0.5
masker = NiftiMasker(global_mask, **kwargs)
masker.fit()
return masker
def dataToImg(d, img, copy_header=False, logger=None):
"""
Wrapper for new_image_like
:param img: Image with header you want to add
:param d: data
:param copy_header: Boolean
:param logger: logger instance
:return: Image file
"""
from nilearn import image
write_to_logger("converting data to image...", logger)
return image.new_img_like(image.mean_img(img), d, copy_header=copy_header)
def plot_segmentation(
img, gm_filename, wm_filename=None, csf_filename=None,
output_filename=None, cut_coords=None, display_mode='ortho',
cmap=None, title='GM + WM + CSF segmentation', close=False):
"""
Plot a contour mapping of the GM, WM, and CSF of a subject's anatomical.
Parameters
----------
img_filename: string or image object
path of file containing image data, or image object simply
gm_filename: string
path of file containing Grey Matter template
wm_filename: string (optional)
path of file containing White Matter template
csf_filename: string (optional)
path of file containing Cerebro-Spinal Fluid template
"""
# misc
if cmap is None:
cmap = plt.cm.gray
if cut_coords is None:
cut_coords = (-10, -28, 17)
if display_mode in ['x', 'y', 'z']:
cut_coords = (cut_coords['xyz'.index(display_mode)],)
# plot img
img = mean_img(img)
img = reorder_img(img, resample="continuous")
_slicer = plot_img(img, cut_coords=cut_coords, display_mode=display_mode,
cmap=cmap, black_bg=True)
# add TPM contours
gm = nibabel.load(gm_filename)
_slicer.add_contours(gm, levels=[.51], colors=["r"])
if not wm_filename is None:
_slicer.add_contours(wm_filename, levels=[.51], colors=["g"])
if not csf_filename is None:
_slicer.add_contours(csf_filename, levels=[.51], colors=['b'])
# misc
_slicer.title(title, size=12, color='w', alpha=0)
if not output_filename is None:
plt.savefig(output_filename, bbox_inches='tight', dpi=200,
facecolor="k",
edgecolor="k")
if close:
plt.close()
def loader(anat, downsample, target_affine, dataroot, subject, maskpath, nrun,
niifilename, labels, **kwargs):
'''
All parameters are submitted as cfg dictionary.
Given parameters in cfg, return masked and concatenated over runs data
Input
anat: MNI template
downsample: 1 or 0
target_affine: downsampling matrix
dataroot: element of path to data
subject: folder in dataroot with subject data
maskpath: path to mask
nrun: number of runs
niifilename: how is the data file called
labels: labels from load_labels function
Output
dict(nii_func=nii_func,nii_mean=nii_mean,masker=masker,nii_mask=nii_mask)
nii_func: 4D data
nii_mean: mean over 4th dimension
masker: masker object from nibabel
nii_mask: 3D mask
'''
nii_func = list()
for r in range(nrun):
fname = '{0}/{1}/run{2}/{3}'.format(dataroot, subject, r+1, niifilename) # Assumption about file location
nii_img = load(fname, mmap=False)
nii_img.set_sform(anat.get_sform())
# Get mean over 4D
nii_mean = mean_img(nii_img)
# Masking
nii_mask = load(maskpath)
nii_mask.set_sform(anat.get_sform())
# Binarize the mask
nii_mask = check_binary(nii_mask)
if downsample:
nii_img = resample_img(nii_img, target_affine=target_affine)
nii_mask = resample_img(nii_mask, target_affine=target_affine, interpolation='nearest')
masker = NiftiMasker(nii_mask, standardize=True)
nii_img = masker.fit_transform(nii_img)
# Drop zero timepoints, zscore
nii_img = drop_labels(nii_img, labels.get('to_drop_zeros')[r])
nii_func.append(stats.zscore(nii_img, axis=0)) # zscore over time
# throw data together
nii_func = np.concatenate(nii_func)
return dict(nii_func=nii_func, nii_mean=nii_mean, masker=masker, nii_mask=nii_mask)
def multi_session_time_slice_diffs(img_list):
""" time slice difference on several 4D images
Parameters
----------
img_list: list of 4D Niimg-like
Input multi-session images
returns
-------
results : dict
see time_slice_diffs docstring for details.
note
----
The results are accumulated across sessions
"""
results = {}
for i, img in enumerate(img_list):
results_ = time_slice_diffs(img)
if i == 0:
for key, val in results_.items():
# special case for 'session_length' to make
# aggregation easier later on
results[key] = val if key != 'session_length' else [val]
else:
results['volume_mean_diff2'] = np.hstack((
results['volume_mean_diff2'],
results_['volume_mean_diff2']))
results['slice_mean_diff2'] = np.vstack((
results['slice_mean_diff2'],
results_['slice_mean_diff2']))
results['volume_means'] = np.hstack((
results['volume_means'],
results_['volume_means']))
results['diff2_mean_vol'] = mean_img(
[results['diff2_mean_vol'], results_['diff2_mean_vol']])
results['slice_diff2_max_vol'] = nib.Nifti1Image(
np.maximum(results_['slice_diff2_max_vol'].get_data(),
results['slice_diff2_max_vol'].get_data()),
results['slice_diff2_max_vol'].get_affine()
)
results['session_length'].append(results_['session_length'])
return results
# 'aws' == amazon web services also OK
dataset = HcpDataset(fetcher_type='aws')
# only fetch anatomical files.
files = dataset.fetch(n_subjects=2, data_types=['task'])
# Filter subject 2 only
nii_files = filter(lambda fil: fil and '100408' in fil and fil.endswith('_LR.nii.gz'), files)
tasks = ['emotion', 'gambling', 'language', 'motor', 'social', 'wm']
# Compute mean images
mean_imgs = dict()
for task in tasks:
mean_imgs[task] = mean_img(filter(lambda fil: task.upper() in fil, nii_files)[0])
# Now make a matrix.
fh = plt.figure(figsize=(18, 10))
for ti1, task1 in enumerate(tasks):
for ti2 in range(0, ti1 - 1):
task2 = tasks[ti2]
ax = fh.add_subplot(5, 5, (ti1 - 1) * 5 + ti2 + 1)
img = math_img("img1 - img2", img1=mean_imgs[task1], img2=mean_imgs[task2])
plot_stat_map(
img,
title='%s - %s' % (task1, task2),
symmetric_cbar=True,
black_bg=True,
display_mode='yz',
y_train=np.array(y_train.astype('double'))
y_test[y_test=='scissors']=1
y_test[y_test=='scrambledpix']=-1
y_test=np.array(y_test.astype('double'))
masker = NiftiMasker(mask_strategy='epi',standardize=True)
X_train = masker.fit_transform(X_train)
X_test = masker.transform(X_test)
mask = masker.mask_img_.get_data().astype(np.bool)
mask= _crop_mask(mask)
background_img = mean_img(data_files.func[0])
X_train, y_train, _, y_train_mean, _ = center_data(X_train, y_train, fit_intercept=True, normalize=False,copy=False)
X_test-=X_train.mean(axis=0)
X_test/=np.std(X_train,axis=0)
alpha=1
ratio=0.5
k=200
solver_params = dict(tol=1e-6, max_iter=5000,prox_max_iter=100)
init=None
w,obj,init=tvksp_solver(X_train,y_train,alpha,ratio,k,mask=mask,init=init,loss="logistic",verbose=1,**solver_params)
coef=w[:-1]
intercept=w[-1]
import numpy as np
import pandas as pd
import nibabel as nib
from nilearn.plotting import plot_stat_map, show
from nilearn.image import mean_img
from nistats.design_matrix import make_design_matrix
from nistats.glm import FirstLevelGLM
from nistats.datasets import fetch_spm_auditory
# fetch spm auditory data
subject_data = fetch_spm_auditory()
fmri_img = nib.concat_images(subject_data.func)
# compute bg unto which activation will be projected
mean_img = mean_img(fmri_img)
# construct experimental paradigm
tr = 7.
n_scans = 96
epoch_duration = 6 * tr # duration in seconds
conditions = ['rest', 'active'] * 8
n_blocks = len(conditions)
duration = epoch_duration * np.ones(n_blocks)
onset = np.linspace(0, (n_blocks - 1) * epoch_duration, n_blocks)
paradigm = pd.DataFrame(
{'onset': onset, 'duration': duration, 'name': conditions})
# construct design matrix
frame_times = np.linspace(0, (n_scans - 1) * tr, n_scans)
drift_model = 'Cosine'
from nilearn.image import mean_img
import nibabel as nib
from nistats.glm import FirstLevelGLM
from nistats import datasets
# write directory
write_dir = path.join(getcwd(), 'results')
if not path.exists(write_dir):
mkdir(write_dir)
# Data and analysis parameters
data = datasets.fetch_fiac_first_level()
fmri_img = [data['func1'], data['func2']]
mean_img_ = mean_img(fmri_img[0])
design_files = [data['design_matrix1'], data['design_matrix2']]
design_matrices = [pd.DataFrame(np.load(df)['X']) for df in design_files]
# GLM specification
fmri_glm = FirstLevelGLM(data['mask'], standardize=False, noise_model='ar1')
# GLM fitting
fmri_glm.fit(fmri_img, design_matrices)
# compute fixed effects of the two runs and compute related images
n_columns = design_matrices[0].shape[1]
def pad_vector(contrast_, n_columns):
return np.hstack((contrast_, np.zeros(n_columns - len(contrast_))))
contrasts = {'SStSSp_minus_DStDSp': pad_vector([1, 0, 0, -1], n_columns),
### Look at the SVC's discriminating weights coef = svc.coef_ # reverse feature selection coef = feature_selection.inverse_transform(coef) # reverse masking weight_img = nifti_masker.inverse_transform(coef) ### Create the figure from nilearn import image import matplotlib.pyplot as plt from nilearn.plotting import plot_stat_map # Plot the mean image because we have no anatomic data mean_img = image.mean_img(dataset_files.func) plot_stat_map(weight_img, mean_img, title='SVM weights') ### Saving the results as a Nifti file may also be important import nibabel nibabel.save(weight_img, 'haxby_face_vs_house.nii') ### Cross validation ########################################################## from sklearn.cross_validation import LeaveOneLabelOut ### Define the cross-validation scheme used for validation. # Here we use a LeaveOneLabelOut cross-validation on the session label # divided by 2, which corresponds to a leave-two-session-out cv = LeaveOneLabelOut(session // 2)
# Apply this sample mask to X (fMRI data) and y (behavioral labels)
# Because the data is in one single large 4D image, we need to use
# index_img to do the split easily
from nilearn.image import index_img
func_filenames = data_files.func[0]
X_train = index_img(func_filenames, condition_mask_train)
X_test = index_img(func_filenames, condition_mask_test)
y_train = target[condition_mask_train]
y_test = target[condition_mask_test]
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(func_filenames)
##############################################################################
# Fit SpaceNet with a Graph-Net penalty
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(memory="nilearn_cache", penalty="graph-net")
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.0
print("Graph-net classification accuracy : %g%%" % accuracy)
# Visualization
from nilearn.plotting import plot_stat_map, show
memory_level=1)
fmri_masked = nifti_masker.fit_transform(fmri_img)
from sklearn.feature_selection import f_classif
f_values, p_values = f_classif(fmri_masked, y)
p_values = -np.log10(p_values)
p_values[p_values > 10] = 10
p_unmasked = nifti_masker.inverse_transform(p_values).get_data()
### Visualization #############################################################
import matplotlib.pyplot as plt
# Use the fmri mean image as a surrogate of anatomical data
from nilearn import image
from nilearn.plotting import plot_stat_map
mean_fmri = image.mean_img(fmri_img)
plot_stat_map(nibabel.Nifti1Image(searchlight.scores_,
mean_fmri.get_affine()), mean_fmri,
title="Searchlight", display_mode="z", cut_coords=[-16],
colorbar=False)
### F_score results
p_ma = np.ma.array(p_unmasked, mask=np.logical_not(process_mask))
plot_stat_map(nibabel.Nifti1Image(p_ma,
mean_fmri.get_affine()), mean_fmri,
title="F-scores", display_mode="z", cut_coords=[-16],
colorbar=False)
plt.show()
# Normalize estimated components, for thresholding to make sense components_masked -= components_masked.mean(axis=0) components_masked /= components_masked.std(axis=0) # Threshold components_masked[components_masked < 0.8] = 0 # Now invert the masking operation, going back to a full 3D # representation component_img = masker.inverse_transform(components_masked) components = component_img.get_data() # Using a masked array is important to have transparency in the figures components = np.ma.masked_equal(components, 0, copy=False) ### Visualize the results ##################################################### # Show some interesting components # Use the mean as a background import nibabel import pylab as plt from nilearn import image from nilearn.plotting import plot_stat_map mean_img = image.mean_img(dataset.func[0]) plot_stat_map(nibabel.Nifti1Image(component_img.get_data()[:, :, :, 5], component_img.get_affine()), mean_img) plot_stat_map(nibabel.Nifti1Image(component_img.get_data()[:, :, :, 12], component_img.get_affine()), mean_img) plt.show()
get_tmaps=True)
localizer_anat_filename = localizer_dataset.anats[1]
localizer_cmap_filename = localizer_dataset.cmaps[1]
localizer_tmap_filename = localizer_dataset.tmaps[1]
###############################################################################
# demo the different plotting functions
# Plotting statistical maps
plotting.plot_stat_map(localizer_cmap_filename, bg_img=localizer_anat_filename,
threshold=3, title="plot_stat_map",
cut_coords=(36, -27, 66))
# Plotting glass brain
plotting.plot_glass_brain(localizer_tmap_filename, title='plot_glass_brain',
threshold=3)
# Plotting anatomical maps
plotting.plot_anat(haxby_anat_filename, title="plot_anat")
# Plotting ROIs (here the mask)
plotting.plot_roi(haxby_mask_filename, bg_img=haxby_anat_filename,
title="plot_roi")
# Plotting EPI haxby
mean_haxby_img = image.mean_img(haxby_func_filename)
plotting.plot_epi(mean_haxby_img, title="plot_epi")
import matplotlib.pyplot as plt
plt.show()
contrast['SStSSp_minus_DStDSp'] = _pad_vector([1, 0, 0, -1], n_columns)
contrast['DStDSp_minus_SStSSp'] = - contrast['SStSSp_minus_DStDSp']
contrast['DSt_minus_SSt'] = _pad_vector([- 1, - 1, 1, 1], n_columns)
contrast['DSp_minus_SSp'] = _pad_vector([- 1, 1, - 1, 1], n_columns)
contrast['DSt_minus_SSt_for_DSp'] = _pad_vector([0, - 1, 0, 1], n_columns)
contrast['DSp_minus_SSp_for_DSt'] = _pad_vector([0, 0, - 1, 1], n_columns)
contrast['Deactivation'] = _pad_vector([- 1, - 1, - 1, - 1, 4], n_columns)
contrast['Effects_of_interest'] = np.eye(n_columns)[:5]
return contrast
# compute fixed effects of the two runs and compute related images
n_columns = np.load(design_files[0])['X'].shape[1]
contrasts = make_fiac_contrasts(n_columns)
print('Computing contrasts...')
mean_ = mean_img(data['func1'])
for index, (contrast_id, contrast_val) in enumerate(contrasts.items()):
print(' Contrast % 2i out of %i: %s' % (
index + 1, len(contrasts), contrast_id))
z_image_path = path.join(write_dir, '%s_z_map.nii' % contrast_id)
z_map, = multi_session_model.transform(
[contrast_val] * 2, contrast_name=contrast_id, output_z=True)
nib.save(z_map, z_image_path)
# make a snapshot of the contrast activation
if contrast_id == 'Effects_of_interest':
vmax = max(- z_map.get_data().min(), z_map.get_data().max())
vmin = - vmax
display = plot_stat_map(z_map, bg_img=mean_, threshold=2.5,
title=contrast_id)
display.savefig(path.join(write_dir, '%s_z_map.png' % contrast_id))
###############################################################################
# From already masked data
from nilearn.input_data import NiftiMasker
import nilearn.image as image
from nilearn.plotting.img_plotting import plot_roi
# Load Miyawaki dataset
miyawaki_dataset = datasets.fetch_miyawaki2008()
# print basic information on the dataset
print('First functional nifti image (4D) is located at: %s' %
miyawaki_dataset.func[0]) # 4D data
miyawaki_filename = miyawaki_dataset.func[0]
miyawaki_mean_img = image.mean_img(miyawaki_filename)
# This time, we can use the NiftiMasker without changing the default mask
# strategy, as the data has already been masked, and thus lies on a
# homogeneous background
masker = NiftiMasker()
masker.fit(miyawaki_filename)
plot_roi(masker.mask_img_, miyawaki_mean_img,
title="Mask from already masked data")
###############################################################################
# From raw EPI data
As we vary the smoothing FWHM, note how we decrease the amount of noise,
but also loose spatial details. In general, the best amount of smoothing
for a given analysis depends on the spatial extent of the effects that
are expected.
"""
from nilearn import datasets, plotting, image
data = datasets.fetch_development_fmri(n_subjects=1)
# Print basic information on the dataset
print('First subject functional nifti image (4D) are located at: %s' %
data.func[0])
first_epi_file = data.func[0]
# First the compute the mean image, from the 4D series of image
mean_func = image.mean_img(first_epi_file)
# Then we smooth, with a varying amount of smoothing, from none to 20mm
# by increments of 5mm
for smoothing in range(0, 25, 5):
smoothed_img = image.smooth_img(mean_func, smoothing)
plotting.plot_epi(smoothed_img,
title="Smoothing %imm" % smoothing)
plotting.show()
grouped_fmri_masked,
grouped_conditions_encoded) # f_regression implicitly adds intercept
pvals_bonferroni *= fmri_masked.shape[1]
pvals_bonferroni[np.isnan(pvals_bonferroni)] = 1
pvals_bonferroni[pvals_bonferroni > 1] = 1
neg_log_pvals_bonferroni = -np.log10(pvals_bonferroni)
neg_log_pvals_bonferroni_unmasked = nifti_masker.inverse_transform(
neg_log_pvals_bonferroni).get_data()
### Visualization #############################################################
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import ImageGrid
# Use the fmri mean image as a surrogate of anatomical data
from nilearn import image
mean_fmri = image.mean_img(dataset_files.func).get_data()
# Various plotting parameters
picked_slice = 27 # plotted slice
vmin = -np.log10(0.1) # 10% corrected
vmax = min(np.amax(neg_log_pvals), np.amax(neg_log_pvals_bonferroni))
grid = ImageGrid(plt.figure(), 111, nrows_ncols=(1, 2), direction="row",
axes_pad=0.05, add_all=True, label_mode="1",
share_all=True, cbar_location="right", cbar_mode="single",
cbar_size="7%", cbar_pad="1%")
# Plot thresholded p-values map corresponding to F-scores
ax = grid[0]
p_ma = np.ma.masked_less(neg_log_pvals_bonferroni_unmasked, vmin)
ax.imshow(np.rot90(mean_fmri[..., picked_slice]), interpolation='nearest',
cmap=plt.cm.gray)
# Smooth the data using image processing module from nilearn from nilearn import image # Functional data fmri_filename = haxby_dataset.func[0] # smoothing: first argument as functional data filename and smoothing value # (integer) in second argument. Output returns in Nifti image. fmri_img = image.smooth_img(fmri_filename, fwhm=6) # Visualize the mean of the smoothed EPI image using plotting function # `plot_epi` from nilearn.plotting import plot_epi # First, compute the voxel-wise mean of smooth EPI image (first argument) using # image processing module `image` mean_img = image.mean_img(fmri_img) # Second, we visualize the mean image with coordinates positioned manually plot_epi(mean_img, title='Smoothed mean EPI', cut_coords=cut_coords) ############################################################################## # Given the smoothed functional data stored in variable 'fmri_img', we then # select two features of interest with face and house experimental conditions. # The method we will be using is a simple Student's t-test. The below section # gives us brief motivation example about why selecting features in high # dimensional FMRI data setting. ############################################################################## # Functional MRI data can be considered "high dimensional" given the p-versus-n # ratio (e.g., p=~20,000-200,000 voxels for n=1000 samples or less). In this # setting, machine-learning algorithms can perform poorly due to the so-called # curse of dimensionality. However, simple means from the realms of classical
memory_level=1)
fmri_masked = nifti_masker.fit_transform(fmri_img)
from sklearn.feature_selection import f_classif
f_values, p_values = f_classif(fmri_masked, y)
p_values = -np.log10(p_values)
p_values[np.isnan(p_values)] = 0
p_values[p_values > 10] = 10
p_unmasked = nifti_masker.inverse_transform(p_values).get_data()
### Visualization #############################################################
import matplotlib.pyplot as plt
# Use the fmri mean image as a surrogate of anatomical data
from nilearn import image
mean_fmri = image.mean_img(fmri_img).get_data()
### Searchlight results
plt.figure(1)
# searchlight.scores_ contains per voxel cross validation scores
s_scores = np.ma.array(searchlight.scores_, mask=np.logical_not(process_mask))
plt.imshow(np.rot90(mean_fmri[..., picked_slice]), interpolation='nearest',
cmap=plt.cm.gray)
plt.imshow(np.rot90(s_scores[..., picked_slice]), interpolation='nearest',
cmap=plt.cm.hot, vmax=1)
plt.axis('off')
plt.title('Searchlight')
### F_score results
plt.figure(2)
p_ma = np.ma.array(p_unmasked, mask=np.logical_not(process_mask))
#
# First we display the labels of the clustering in the brain.
#
# To visualize results, we need to transform the clustering's labels back
# to a neuroimaging volume. For this, we use the NiftiMasker's
# inverse_transform method.
from nilearn.plotting import plot_roi, plot_epi, show
# Unmask the labels
# Avoid 0 label
labels = ward.labels_ + 1
labels_img = nifti_masker.inverse_transform(labels)
from nilearn.image import mean_img
mean_func_img = mean_img(func_filename)
first_plot = plot_roi(labels_img, mean_func_img, title="Ward parcellation",
display_mode='xz')
# common cut coordinates for all plots
cut_coords = first_plot.cut_coords
##################################################################
# labels_img is a Nifti1Image object, it can be saved to file with the
# following code:
labels_img.to_filename('parcellation.nii')
##################################################################
"""
Plot Haxby masks
=================
Small script to plot the masks of the Haxby dataset.
"""
from scipy import linalg
import matplotlib.pyplot as plt
from nilearn import datasets
data = datasets.fetch_haxby()
# Build the mean image because we have no anatomic data
from nilearn import image
mean_img = image.mean_img(data.func[0])
z_slice = -24
from nilearn.image.resampling import coord_transform
affine = mean_img.get_affine()
_, _, k_slice = coord_transform(0, 0, z_slice,
linalg.inv(affine))
k_slice = round(k_slice)
fig = plt.figure(figsize=(4, 5.4), facecolor='k')
from nilearn.plotting import plot_anat
display = plot_anat(mean_img, display_mode='z', cut_coords=[z_slice],
figure=fig)
display.add_contours(data.mask_vt[0], contours=1, antialiased=False,
linewidths=4., levels=[0], colors=['red'])
display.add_contours(data.mask_house[0], contours=1, antialiased=False,
from sklearn.decomposition import FastICA n_components = 20 ica = FastICA(n_components=n_components, random_state=42) components_masked = ica.fit_transform(data_masked.T).T # Normalize estimated components, for thresholding to make sense components_masked -= components_masked.mean(axis=0) components_masked /= components_masked.std(axis=0) # Threshold components_masked[components_masked < .8] = 0 # Now invert the masking operation, going back to a full 3D # representation component_img = masker.inverse_transform(components_masked) ### Visualize the results ##################################################### # Show some interesting components import matplotlib.pyplot as plt from nilearn import image from nilearn.plotting import plot_stat_map # Use the mean as a background mean_img = image.mean_img(func_filename) plot_stat_map(image.index_img(component_img, 5), mean_img) plot_stat_map(image.index_img(component_img, 12), mean_img) plt.show()
hrf_model = 'spm + derivative' # The hemodunamic response finction is the SPM canonical one
#########################################################################
# Resample the images.
#
# This is achieved by the concat_imgs function of Nilearn.
from nilearn.image import concat_imgs, resample_img, mean_img
fmri_img = [concat_imgs(subject_data.func1, auto_resample=True),
concat_imgs(subject_data.func2, auto_resample=True)]
affine, shape = fmri_img[0].affine, fmri_img[0].shape
print('Resampling the second image (this takes time)...')
fmri_img[1] = resample_img(fmri_img[1], affine, shape[:3])
#########################################################################
# Create mean image for display
mean_image = mean_img(fmri_img)
#########################################################################
# Make design matrices
import numpy as np
import pandas as pd
from nistats.design_matrix import make_first_level_design_matrix
design_matrices = []
#########################################################################
# loop over the two sessions
for idx, img in enumerate(fmri_img, start=1):
# Build experimental paradigm
n_scans = img.shape[-1]
events = pd.read_table(subject_data['events{}'.format(idx)])
# Define the sampling times for the design matrix
