def test_check_niimg_3d():
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'nibabel format',
_utils.check_niimg, 0)
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'empty object',
_utils.check_niimg, [])
# Test dimensionality error
img = Nifti1Image(np.zeros((10, 10, 10)), np.eye(4))
assert_raises_regex(TypeError,
"Input data has incompatible dimensionality: "
"Expected dimension is 3D and you provided a list "
"of 3D images \(4D\).",
_utils.check_niimg_3d, [img, img])
# Check that a filename does not raise an error
data = np.zeros((40, 40, 40, 1))
data[20, 20, 20] = 1
data_img = Nifti1Image(data, np.eye(4))
with testing.write_tmp_imgs(data_img, create_files=True) as filename:
_utils.check_niimg_3d(filename)
# check data dtype equal with dtype='auto'
img_check = _utils.check_niimg_3d(img, dtype='auto')
assert_equal(img.get_data().dtype.kind, img_check.get_data().dtype.kind)
def test_check_niimg_3d():
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'nibabel format', _utils.check_niimg, 0)
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'empty object', _utils.check_niimg, [])
# Test dimensionality error
img = Nifti1Image(np.zeros((10, 10, 10)), np.eye(4))
assert_raises_regex(
TypeError, "Input data has incompatible dimensionality: "
"Expected dimension is 3D and you provided a list "
"of 3D images \(4D\).", _utils.check_niimg_3d, [img, img])
# Check that a filename does not raise an error
data = np.zeros((40, 40, 40, 1))
data[20, 20, 20] = 1
data_img = Nifti1Image(data, np.eye(4))
with testing.write_tmp_imgs(data_img, create_files=True) as filename:
_utils.check_niimg_3d(filename)
# check data dtype equal with dtype='auto'
img_check = _utils.check_niimg_3d(img, dtype='auto')
assert_equal(img.get_data().dtype.kind, img_check.get_data().dtype.kind)
def _apply_mask(imgs, mask_img): mask_img = _utils.check_niimg_3d(mask_img) mask_img = _utils.check_niimg_3d(mask_img) mask = mask_img.get_data() mask = _utils.as_ndarray(mask, dtype=bool) mask_img = new_img_like(mask_img, mask, mask_img.affine) return _apply_mask_fmri(imgs, mask_img, dtype='f', smoothing_fwhm=None, ensure_finite=True)
def transform(self, imgs, confounds=None):
if self.smoothing_fwhm is not None or self.target_affine is not None:
if self.smoothing_fwhm is not None:
imgs = smooth_img(imgs, self.smoothing_fwhm)
if self.target_affine is not None:
imgs = resample_img(imgs, target_affine=self.target_affine)
else:
imgs = [check_niimg_3d(img) for img in imgs] if isinstance(
imgs, list) else check_niimg_3d(imgs)
return imgs
def test_check_niimg_3d():
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'nibabel format', _utils.check_niimg, 0)
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'empty object', _utils.check_niimg, [])
# Check that a filename does not raise an error
data = np.zeros((40, 40, 40, 1))
data[20, 20, 20] = 1
data_img = Nifti1Image(data, np.eye(4))
with testing.write_tmp_imgs(data_img, create_files=True) as filename:
_utils.check_niimg_3d(filename)
def concat_3D_imgs(in_files, out_file=None):
""" Use nilearn.image.concat_imgs to concat 3D volumes into one 4D volume.
If `in_files` is a list of 3D volumes the return value is the path to one 4D volume.
Else if `in_files` is a list of 4D volumes the return value is `in_files`.
Returns
-------
out_file: str
The absolute path to the output file.
"""
import nilearn.image as niimg
from nilearn._utils import check_niimg_3d
all_3D = True
for idx, img in enumerate(in_files):
try:
_ = check_niimg_3d(img)
except Exception:
all_3D = False
break
if not all_3D:
# raise AttributeError('Expected all input images to be 3D volumes, but '
# ' at least the {}th is not.'.format(idx))
return in_files
else:
return niimg.concat_imgs(in_files)
def concat_3D_imgs(in_files, out_file=None):
""" Use nilearn.image.concat_imgs to concat 3D volumes into one 4D volume.
If `in_files` is a list of 3D volumes the return value is the path to one 4D volume.
Else if `in_files` is a list of 4D volumes the return value is `in_files`.
Returns
-------
out_file: str
The absolute path to the output file.
"""
import nilearn.image as niimg
from nilearn._utils import check_niimg_3d
all_3D = True
for idx, img in enumerate(in_files):
try:
_ = check_niimg_3d(img)
except Exception:
all_3D = False
break
if not all_3D:
#raise AttributeError('Expected all input images to be 3D volumes, but '
# ' at least the {}th is not.'.format(idx))
return in_files
else:
return niimg.concat_imgs(in_files)
def transform(self, imgs, confounds=None):
"""
Parameters
----------
imgs: list of Niimg-like objects
"""
self._check_fitted()
if self.smoothing_fwhm:
imgs = smooth_img(imgs, self.smoothing_fwhm)
imgs = [_utils.check_niimg_3d(img) for img in imgs]
for i, roi in enumerate(self.mask_img_):
masker = NiftiMasker(mask_img=roi)
x = masker.fit_transform(imgs)
if self.extract_funcs is not None:
x = np.array([
FDICT[f][0](x, **FDICT[f][1]) for f in self.extract_funcs
])
if i == 0:
X = x
else:
X = np.concatenate((X, x), axis=0)
return X.swapaxes(0, 1)
def transform(self, imgs, confounds=None):
smooth_prefix = '' if self.smoothing_fwhm is None else 's%g' % self.smoothing_fwhm
resample_prefix = '' if self.smoothing_fwhm is None else 'r%g' % self.smoothing_fwhm
if not isinstance(imgs, list):
imgs = [imgs]
path_first = imgs[0] if isinstance(imgs[0], str) else imgs[0].get_filename()
path_first_resampled = os.path.join(os.path.dirname(path_first), resample_prefix + os.path.basename(path_first))
path_first_smoothed = os.path.join(os.path.dirname(path_first), smooth_prefix + resample_prefix + os.path.basename(path_first))
if self.resampling is not None and self.smoothing_fwhm is not None:
if self.resampling is not None:
if not os.path.exists(path_first_resampled) and not os.path.exists(path_first_smoothed):
imgs = resample_img(imgs, target_affine=np.diag(self.resampling * np.ones(3)))
else:
imgs = []
if self.smoothing_fwhm is not None:
if not os.path.exists(path_first_smoothed):
imgs = smooth_img(imgs, self.smoothing_fwhm)
else:
imgs = []
else:
imgs = [check_niimg_3d(img) for img in imgs]
return self.masker.transform(imgs)
def transform(self, imgs, confounds=None):
"""
Parameters
----------
imgs: list of Niimg-like objects
"""
self._check_fitted()
if self.smoothing_fwhm:
imgs = smooth_img(imgs, self.smoothing_fwhm)
imgs = [_utils.check_niimg_3d(img) for img in imgs]
for i, roi in enumerate(self.mask_img_):
masker = NiftiMasker(mask_img=roi)
x = masker.fit_transform(imgs)
if self.extract_funcs is not None:
x = np.array([FDICT[f][0](x, **FDICT[f][1]) for f in self.extract_funcs])
if i == 0:
X = x
else:
X = np.concatenate((X, x), axis=0)
return X.swapaxes(0, 1)
def test_check_niimg_3d():
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'nibabel format',
_utils.check_niimg, 0)
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, 'empty object',
_utils.check_niimg, [])
# Check that a filename does not raise an error
data = np.zeros((40, 40, 40, 1))
data[20, 20, 20] = 1
data_img = Nifti1Image(data, np.eye(4))
with testing.write_tmp_imgs(data_img, create_files=True) as filename:
_utils.check_niimg_3d(filename)
def preprocess(self, imgs):
smooth_prefix = '' if self.smoothing_fwhm is None else 's%g' % self.smoothing_fwhm
resample_prefix = '' if self.resampling is None else 'r%g' % self.resampling
if not isinstance(imgs, list):
imgs = [imgs]
path_first = imgs[0] if isinstance(imgs[0], str) else imgs[0].get_filename()
path_first_resampled = os.path.join(os.path.dirname(path_first), resample_prefix + os.path.basename(path_first))
path_first_smoothed = os.path.join(os.path.dirname(path_first), smooth_prefix + resample_prefix + os.path.basename(path_first))
if self.resampling is not None or self.smoothing_fwhm is not None:
if self.resampling is not None and not os.path.exists(path_first_smoothed):
if not os.path.exists(path_first_resampled):
imgs = resample_img(imgs, target_affine=np.diag(self.resampling * np.ones(3)))
else:
imgs = [os.path.join(os.path.dirname(img), resample_prefix + os.path.basename(img)) if isinstance(img, str)
else os.path.join(os.path.dirname(img.get_filename()), resample_prefix + os.path.basename(img.get_filename())) for img in imgs]
if self.smoothing_fwhm is not None:
if not os.path.exists(path_first_smoothed):
imgs = smooth_img(imgs, self.smoothing_fwhm)
else:
imgs = [os.path.join(os.path.dirname(img), smooth_prefix + resample_prefix + os.path.basename(img)) if isinstance(img, str)
else os.path.join(os.path.dirname(img.get_filename()), smooth_prefix + resample_prefix + os.path.basename(img.get_filename())) for img in imgs]
else:
imgs = [check_niimg_3d(img) for img in imgs]
return imgs
def test_check_niimg_3d():
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, "nibabel format", _utils.check_niimg, 0)
# check error for non-forced but necessary resampling
assert_raises_regex(TypeError, "empty object", _utils.check_niimg, [])
# Test dimensionality error
img = Nifti1Image(np.zeros((10, 10, 10)), np.eye(4))
assert_raises_regex(TypeError, "Data must be a 3D", _utils.check_niimg_3d, [img, img])
# Check that a filename does not raise an error
data = np.zeros((40, 40, 40, 1))
data[20, 20, 20] = 1
data_img = Nifti1Image(data, np.eye(4))
with testing.write_tmp_imgs(data_img, create_files=True) as filename:
_utils.check_niimg_3d(filename)
def check_atlas_info(atlas, atlas_info, labels=None):
"""
Checks whether provided `info` on `atlas` is sufficient for processing
Parameters
----------
atlas : niimg-like object
Parcel image, where each parcel should be identified with a unique
integer ID
atlas_info : str or pandas.DataFrame
Filepath or dataframe containing information about `atlas`. Must have
at least columns 'id', 'hemisphere', and 'structure' containing
information mapping atlas IDs to hemisphere and broad structural class
(e.g., "cortex", "subcortex", "cerebellum").
labels : array_like, optional
List of values containing labels to compare between `atlas` and
`atlas_info`, if they don't all match. If not specified this function
will attempt to confirm that all IDs present in `atlas` have entries in
`atlas_info` and vice versa. Default: None
Returns
-------
atlas_info : pandas.DataFrame
Loaded dataframe with information on atlas
"""
atlas = check_niimg_3d(atlas)
# load info, if not already
try:
atlas_info = pd.read_csv(atlas_info)
except ValueError:
pass
try:
if 'id' in atlas_info.columns:
atlas_info = atlas_info.set_index('id')
except AttributeError:
raise ValueError('Provided atlas_info must be a filepath or pandas.'
'DataFrame. Please confirm inputs and try again.')
ids = get_unique_labels(atlas) if labels is None else labels
cols = ['hemisphere', 'structure']
try:
assert all(c in atlas_info.columns for c in cols)
assert ('id' == atlas_info.index.name)
assert len(np.intersect1d(ids, atlas_info.index)) == len(ids)
except AssertionError:
raise ValueError('Provided `atlas_info` does not have adequate '
'information on supplied `atlas`. Please confirm '
'that `atlas_info` has columns [\'id\', '
'\'hemisphere\', \'structure\'], and that the region '
'IDs listed in `atlas_info` account for all those '
'found in `atlas.')
return atlas_info
def transform(self, imgs, confounds=None):
if self.smoothing_fwhm is not None or self.target_affine is not None:
if self.smoothing_fwhm is not None:
imgs = smooth_img(imgs, self.smoothing_fwhm)
if self.target_affine is not None:
imgs = resample_img(imgs, target_affine=self.target_affine)
else:
imgs = [check_niimg_3d(img) for img in imgs] if isinstance(imgs, list) else check_niimg_3d(imgs)
return imgs
def fit(self, imgs=None, y=None):
"""Compute the mask corresponding to the data
Parameters
----------
imgs: list of Niimg-like objects
See http://nilearn.github.io/manipulating_visualizing/manipulating_images.html#niimg.
Data on which the mask must be calculated. If this is a list,
the affine is considered the same for all.
"""
# y=None is for scikit-learn compatibility (unused here).
# Load data (if filenames are given, load them)
if self.verbose > 0:
print("[%s.fit] Loading data from %s" % (
self.__class__.__name__,
_utils._repr_niimgs(imgs)[:200]))
# Compute the mask if not given by the user
if self.mask_img is None:
mask_args = (self.mask_args if self.mask_args is not None
else {})
if self.mask_strategy == 'background':
compute_mask = masking.compute_background_mask
elif self.mask_strategy == 'epi':
compute_mask = masking.compute_epi_mask
else:
raise ValueError("Unknown value of mask_strategy '%s'. "
"Acceptable values are 'background' and "
"'epi'." % self.mask_strategy)
if self.verbose > 0:
print("[%s.fit] Computing the mask" % self.__class__.__name__)
self.mask_img_ = self._cache(compute_mask, ignore=['verbose'])(
imgs, verbose=max(0, self.verbose - 1), **mask_args)
else:
self.mask_img_ = _utils.check_niimg_3d(self.mask_img)
# If resampling is requested, resample also the mask
# Resampling: allows the user to change the affine, the shape or both
if self.verbose > 0:
print("[%s.fit] Resampling mask" % self.__class__.__name__)
self.mask_img_ = self._cache(image.resample_img)(
self.mask_img_,
target_affine=self.target_affine,
target_shape=self.target_shape,
copy=False)
if self.target_affine is not None:
self.affine_ = self.target_affine
else:
self.affine_ = self.mask_img_.get_affine()
# Load data in memory
self.mask_img_.get_data()
if self.verbose > 10:
print("[%s.fit] Finished fit" % self.__class__.__name__)
return self
def _get_volume(img,
threshold=0,
atlas=None,
stride=1,
t_start=0,
t_end=-1,
n_t=50,
t_r=None,
marker_size=3,
cmap=cm.cold_hot,
symmetric_cmap=True,
vmax=None,
vmin=None):
connectome = {}
img = check_niimg_4d(img)
t_unit = "" if not t_r else " s"
if not t_r:
t_r = 1
if t_end < 0:
t_end = img.shape[3] + t_end
if not n_t:
n_t = t_end - t_start
t_idx = np.round(np.linspace(t_start, t_end, n_t)).astype(int)
t_labels = [str(t_r * t) + t_unit for t in t_idx]
data = _safe_get_data(img)[::stride, ::stride, ::stride, t_idx]
mask = np.abs(data[:, :, :, 0]) > threshold
i, j, k = mask.nonzero()
x, y, z = coord_transform(i * stride, j * stride, k * stride, img.affine)
for coord, cname in [(x, "x"), (y, "y"), (z, "z")]:
connectome["_con_{}".format(cname)] = encode(
np.asarray(coord, dtype='<f4'))
colors = colorscale(cmap,
data.ravel(),
symmetric_cmap=symmetric_cmap,
vmax=vmax,
vmin=vmin)
if atlas:
atlas = check_niimg_3d(atlas)
atlas_data = _safe_get_data(atlas)[::stride, ::stride, ::stride]
connectome['atlas'] = encode(
np.asarray(atlas_data[i, j, k], dtype='<f4'))
connectome['atlas_nb'] = int(np.max(atlas_data))
connectome['colorscale'] = colors['colors']
connectome['cmin'] = float(colors['vmin'])
connectome['cmax'] = float(colors['vmax'])
connectome['n_time'] = n_t
connectome['t_labels'] = t_labels
values = [
encode(np.asarray(data[i, j, k, t], dtype='<f4'))
for t in range(data.shape[3])
]
connectome['values'] = values
return connectome
def preprocess(self, imgs):
smooth_prefix = '' if self.smoothing_fwhm is None else 's%g' % self.smoothing_fwhm
resample_prefix = '' if self.resampling is None else 'r%g' % self.resampling
if not isinstance(imgs, list):
imgs = [imgs]
path_first = imgs[0] if isinstance(imgs[0],
str) else imgs[0].get_filename()
path_first_resampled = os.path.join(
os.path.dirname(path_first),
resample_prefix + os.path.basename(path_first))
path_first_smoothed = os.path.join(
os.path.dirname(path_first),
smooth_prefix + resample_prefix + os.path.basename(path_first))
if self.resampling is not None or self.smoothing_fwhm is not None:
if self.resampling is not None and not os.path.exists(
path_first_smoothed):
if not os.path.exists(path_first_resampled):
imgs = resample_img(imgs,
target_affine=np.diag(self.resampling *
np.ones(3)))
else:
imgs = [
os.path.join(os.path.dirname(img), resample_prefix +
os.path.basename(img))
if isinstance(img, str) else os.path.join(
os.path.dirname(
img.get_filename()), resample_prefix +
os.path.basename(img.get_filename()))
for img in imgs
]
if self.smoothing_fwhm is not None:
if not os.path.exists(path_first_smoothed):
imgs = smooth_img(imgs, self.smoothing_fwhm)
else:
imgs = [
os.path.join(
os.path.dirname(img), smooth_prefix +
resample_prefix + os.path.basename(img))
if isinstance(img, str) else os.path.join(
os.path.dirname(img.get_filename()),
smooth_prefix + resample_prefix +
os.path.basename(img.get_filename()))
for img in imgs
]
else:
imgs = [check_niimg_3d(img) for img in imgs]
return imgs
def apply_mask(self, series, mask_img):
"""
Apply mask on series.
:param series: np.ndarray, data working on
:param mask_img:
:return:
"""
mask_img = _utils.check_niimg_3d(mask_img)
mask, mask_affine = masking._load_mask_img(mask_img)
mask_img = image.new_img_like(mask_img, mask, mask_affine)
mask_data = _utils.as_ndarray(mask_img.get_fdata(),
dtype=np.bool)
return series[mask_data].T
def compute_confounds(imgs, mask_img, n_confounds=5, get_randomized_svd=False,
compute_not_mask=False):
"""
"""
confounds = []
if not isinstance(imgs, collections.Iterable) or \
isinstance(imgs, _basestring):
imgs = [imgs, ]
img = _utils.check_niimg_4d(imgs[0])
shape = img.shape[:3]
affine = get_affine(img)
if isinstance(mask_img, _basestring):
mask_img = _utils.check_niimg_3d(mask_img)
if not _check_same_fov(img, mask_img):
mask_img = resample_img(
mask_img, target_shape=shape, target_affine=affine,
interpolation='nearest')
if compute_not_mask:
print("Non mask based confounds extraction")
not_mask_data = np.logical_not(mask_img.get_data().astype(np.int))
whole_brain_mask = masking.compute_multi_epi_mask(imgs)
not_mask = np.logical_and(not_mask_data, whole_brain_mask.get_data())
mask_img = new_img_like(img, not_mask.astype(np.int), affine)
for img in imgs:
print("[Confounds Extraction] {0}".format(img))
img = _utils.check_niimg_4d(img)
print("[Confounds Extraction] high ariance confounds computation]")
high_variance = high_variance_confounds(img, mask_img=mask_img,
n_confounds=n_confounds)
if compute_not_mask and get_randomized_svd:
signals = masking.apply_mask(img, mask_img)
non_constant = np.any(np.diff(signals, axis=0) != 0, axis=0)
signals = signals[:, non_constant]
signals = signal.clean(signals, detrend=True)
print("[Confounds Extraction] Randomized SVD computation")
U, s, V = randomized_svd(signals, n_components=n_confounds,
random_state=0)
if high_variance is not None:
confound_ = np.hstack((U, high_variance))
else:
confound_ = U
else:
confound_ = high_variance
confounds.append(confound_)
return confounds
def extract_confounds(imgs, mask_img, n_confounds=10):
"""To extract confounds on list of subjects
See nilearn.image.high_variance_confounds for technical details.
Parameters
----------
imgs : list of Nifti images, either str or nibabel.Nifti1Image
Functional images on which confounds should be extracted
mask_img : str or nibabel.Nifti1Image
Mask image with binary values. This image is imposed on
each functional image for confounds extraction..
n_confounds : int, optional
By default, 10 high variance confounds are extracted. Otherwise,
confounds as specified are extracted.
Returns
-------
confounds : list of Numpy arrays.
Each numpy array is a confound corresponding to imgs provided.
Each numpy array will have shape (n_timepoints, n_confounds)
"""
confounds = []
if not isinstance(imgs, collections.Iterable) or \
isinstance(imgs, _basestring):
imgs = [imgs, ]
img = _utils.check_niimg_4d(imgs[0])
shape = img.shape[:3]
affine = img.affine
if isinstance(mask_img, _basestring):
mask_img = _utils.check_niimg_3d(mask_img)
if not _check_same_fov(img, mask_img):
mask_img = resample_img(
mask_img, target_shape=shape, target_affine=affine,
interpolation='nearest')
for img in imgs:
print("[Confounds Extraction] Image selected {0}".format(img))
img = _utils.check_niimg_4d(img)
print("Extracting high variance confounds")
high_variance = high_variance_confounds(img, mask_img=mask_img,
n_confounds=n_confounds)
confounds.append(high_variance)
return confounds
def get_unique_labels(label_image):
"""
Returns all possible ROI labels from ``label_image``
Parameters
----------
label_image : niimg-like object
ROI image, where each ROI is identified with a unique integer ID
Returns
-------
labels : np.ndarray
Integer labels of all ROIS found within ``label_image``
"""
label_image = check_niimg_3d(label_image)
return np.trim_zeros(np.unique(label_image.get_data())).astype(int)
def inverse_transform(self, img, mask):
"""Transform data back to its original space.
In other words, return an input X_original whose transform would be X.
Parameters
----------
img : 4D niimg_like
Component weight maps.
mask : 3D niimg_like
Mask to apply on ``img``.
Returns
-------
img_orig : 4D niimg_like
Reconstructed original data, with fourth axis corresponding to time.
Notes
-----
This is different from scikit-learn's approach, which ignores explained variance.
"""
img = check_niimg_4d(img)
mask = check_niimg_3d(mask)
data = img.get_fdata()
mask = mask.get_fdata()
[n_x, n_y, n_z, n_components] = data.shape
data_nib_V = np.reshape(data, (n_x * n_y * n_z, n_components),
order="F")
mask_vec = np.reshape(mask, n_x * n_y * n_z, order="F")
X = data_nib_V[mask_vec == 1, :]
X_orig = np.dot(np.dot(X, np.diag(self.explained_variance_)),
self.components_)
if self.normalize:
X_orig = self.scaler_.inverse_transform(X_orig.T).T
n_t = X_orig.shape[1]
out_data = np.zeros((n_x * n_y * n_z, n_t))
out_data[mask_vec == 1, :] = X_orig
out_data = np.reshape(out_data, (n_x, n_y, n_z, n_t), order="F")
img_orig = nib.Nifti1Image(out_data, img.affine, img.header)
return img_orig
def transform(self, imgs, confounds=None):
smooth_prefix = '' if self.smoothing_fwhm is None else 's%g' % self.smoothing_fwhm
resample_prefix = '' if self.smoothing_fwhm is None else 'r%g' % self.smoothing_fwhm
if not isinstance(imgs, list):
imgs = [imgs]
path_first = imgs[0] if isinstance(imgs[0],
str) else imgs[0].get_filename()
path_first_resampled = os.path.join(
os.path.dirname(path_first),
resample_prefix + os.path.basename(path_first))
path_first_smoothed = os.path.join(
os.path.dirname(path_first),
smooth_prefix + resample_prefix + os.path.basename(path_first))
if self.resampling is not None and self.smoothing_fwhm is not None:
if self.resampling is not None:
if not os.path.exists(
path_first_resampled) and not os.path.exists(
path_first_smoothed):
imgs = resample_img(imgs,
target_affine=np.diag(self.resampling *
np.ones(3)))
else:
imgs = []
if self.smoothing_fwhm is not None:
if not os.path.exists(path_first_smoothed):
imgs = smooth_img(imgs, self.smoothing_fwhm)
else:
imgs = []
else:
imgs = [check_niimg_3d(img) for img in imgs]
return self.masker.transform(imgs)
def get_centroids(img, labels=None, image_space=False):
"""
Finds centroids of `labels` in `img`
Parameters
----------
img : niimg-like object
3D image containing integer label at each point
labels : array_like, optional
List of labels for which to find centroids. If not specified all
labels present in `img` will be used. Zero will be ignored as it is
considered "background." Default: None
image_space : bool, optional
Whether to return xyz (image space) coordinates for centroids based
on transformation in `img.affine`. Default: False
Returns
-------
centroids : (N, 3) np.ndarray
Coordinates of centroids for ROIs in input data
"""
from nilearn._utils import check_niimg_3d
img = check_niimg_3d(img)
data = img.get_data()
if labels is None:
labels = np.trim_zeros(np.unique(data))
centroids = np.row_stack(
ndimage.center_of_mass(data, labels=data, index=labels))
if image_space:
centroids = nib.affines.apply_affine(img.affine, centroids)
return centroids
def get_centroids(image, labels=None, image_space=False):
"""
Finds centroids of ``labels`` in ``label_image``
Parameters
----------
label_image : niimg-like object
3D image containing integer label at each point
labels : array_like, optional
List of values containing labels of which to find centroids. Default:
all possible labels
image_space : bool, optional
Whether to return xyz (image space) coordinates for centroids based
on transformation in ``label_image.affine``. Default: False
Returns
-------
centroids : (N, 3) np.ndarray
Coordinates of centroids for ROIs in input data
"""
image = check_niimg_3d(image)
data = image.get_data()
# if no labels of interest provided, get all possible labels
if labels is None:
labels = np.trim_zeros(np.unique(data))
# get centroids for all possible labels
centroids = np.row_stack(center_of_mass(data, labels=data, index=labels))
# return xyz if desired; otherwise, ijk
if image_space:
centroids = ijk_to_xyz(centroids, image.affine)
return centroids
def plot_carpet(img, mask_img=None, detrend=True, output_file=None,
figure=None, axes=None, title=None):
"""Plot an image representation of voxel intensities across time also know
as the "carpet plot" or "Power plot". See Jonathan Power Neuroimage
2017 Jul 1; 154:150-158.
Parameters
----------
img : Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
4D input image
mask_img : Niimg-like object, optional
See http://nilearn.github.io/manipulating_images/input_output.html
Limit plotted voxels to those inside the provided mask. If not
specified a new mask will be derived from data.
detrend : boolean, optional
Detrend and standardize the data prior to plotting.
output_file : string, or None, optional
The name of an image file to export the plot to. Valid extensions
are .png, .pdf, .svg. If output_file is not None, the plot
is saved to a file, and the display is closed.
figure : matplotlib figure, optional
Matplotlib figure used. If None is given, a
new figure is created.
axes : matplotlib axes, optional
The axes used to display the plot. If None, the complete
figure is used.
title : string, optional
The title displayed on the figure.
"""
img_nii = _utils.check_niimg_4d(img, dtype='auto')
img_data = _safe_get_data(img_nii, ensure_finite=True)
# Define TR and number of frames
tr = img_nii.header.get_zooms()[-1]
ntsteps = img_nii.shape[-1]
if not mask_img:
nifti_masker = NiftiMasker(mask_strategy='epi', standardize=False)
nifti_masker.fit(img_nii)
mask_data = nifti_masker.mask_img_.get_data().astype(bool)
else:
mask_nii = _utils.check_niimg_3d(mask_img, dtype='auto')
mask_data = _safe_get_data(mask_nii, ensure_finite=True)
data = img_data[mask_data > 0].reshape(-1, ntsteps)
# Detrend data
if detrend:
data = clean(data.T, t_r=tr).T
if not figure:
if not axes:
figure = plt.figure()
else:
figure = axes.figure
if not axes:
axes = figure.add_subplot(1, 1, 1)
else:
assert axes.figure is figure, ("The axes passed are not "
"in the figure")
# Avoid segmentation faults for long acquisitions by decimating the input
# data
long_cutoff = 800
if data.shape[1] > long_cutoff:
data = data[:, ::2]
else:
data = data[:, :]
axes.imshow(data, interpolation='nearest',
aspect='auto', cmap='gray', vmin=-2, vmax=2)
axes.grid(False)
axes.set_yticks([])
axes.set_yticklabels([])
# Set 10 frame markers in X axis
interval = max(
(int(data.shape[-1] + 1) // 10, int(data.shape[-1] + 1) // 5, 1))
xticks = list(range(0, data.shape[-1])[::interval])
axes.set_xticks(xticks)
axes.set_xlabel('time (s)')
axes.set_ylabel('voxels')
if title:
axes.set_title(title)
labels = tr * (np.array(xticks))
if data.shape[1] > long_cutoff:
labels *= 2
axes.set_xticklabels(['%.02f' % t for t in labels.tolist()])
# Remove and redefine spines
for side in ["top", "right"]:
# Toggle the spine objects
axes.spines[side].set_color('none')
axes.spines[side].set_visible(False)
axes.yaxis.set_ticks_position('left')
axes.xaxis.set_ticks_position('bottom')
axes.spines["bottom"].set_position(('outward', 20))
axes.spines["left"].set_position(('outward', 20))
if output_file is not None:
figure.savefig(output_file)
figure.close()
figure = None
return figure
def check_embedded_atlas_masker(estimator, atlas_type=None, img=None,
multi_subject=True, seeds=None, radius=None,
t_r=None, low_pass=None, high_pass=None):
"""Base function to return masker type and its parameters
Accepts all Nilearn masker types but returns only Maps or Labels masker.
The idea being that this function returns an object with essential
parameters embedded in it such as repetition time, low pass, high pass,
standardize, detrend for resting state fMRI data analysis.
Mostly useful for pipelined analysis.
Parameters
----------
estimator : object, instance of all masker types
Accepts any instance masker type from nilearn.input_data
img : maps_img or labels_img
Used in initialization of instance masker object depending upon
the length/type of the image. If maps_img related then used in
NiftiMapsMasker instance or labels_img then NiftiLabelsMasker.
seeds : List of triplet of coordinates in native space
Used in NiftiSpheresMasker initialization.
atlas_type : str {'maps', 'labels'}
'maps' implies NiftiMapsMasker
'labels' implies NiftiLabelsMasker
multi_subject : bool, optional
Indicates whether to return masker of multi subject type.
List of subjects.
Returns
-------
masker : NiftiMapsMasker, NiftiLabelsMasker
Depending upon atlas type.
params : dict
Masker parameters
"""
if atlas_type is not None:
if atlas_type not in ['maps', 'labels', 'spheres', 'auto']:
raise ValueError(
"You provided unsupported masker type for atlas_type={0} "
"selection. Choose one among them ['maps', 'labels', 'spheres']"
"for atlas type masker. Otherwise atlas_type=None for general "
"Nifti or MultiNifti Maskers.".format(atlas_type))
if not isinstance(estimator, (NiftiMasker, MultiNiftiMasker, NiftiMapsMasker,
NiftiLabelsMasker, NiftiSpheresMasker)):
raise ValueError("Unsupported 'estimator' instance of masker is "
"provided".format(estimator))
if atlas_type == 'spheres' and seeds is None:
raise ValueError("'seeds' must be specified for atlas_type='spheres'."
"See documentation nilearn.input_data.NiftiSpheresMasker.")
if (atlas_type == 'maps' or atlas_type == 'labels') and img is None:
raise ValueError("'img' should not be None for atlas_type={0} related "
"instance of masker. Atlas related maskers is created "
"by provided a valid atlas image. See documenation in "
"nilearn.input_data for specific "
"masker related either maps or labels".format(atlas_type))
if atlas_type == 'auto' and img is not None:
img = check_niimg(img)
if len(img.shape) > 3:
atlas_type = 'maps'
else:
atlas_type = 'labels'
if atlas_type == 'maps' and img is not None:
img = check_niimg_4d(img)
if atlas_type == 'labels' and img is not None:
img = check_niimg_3d(img)
new_masker = check_embedded_nifti_masker(estimator,
multi_subject=multi_subject)
mask = getattr(new_masker, 'mask_img', None)
estimator_mask = getattr(estimator, 'mask_img', None)
if mask is None and estimator_mask is not None:
new_masker.mask_img = estimator.mask_img
if atlas_type is None:
return new_masker
else:
masker_params = new_masker.get_params()
new_masker_params = dict()
_ignore = set(('mask_strategy', 'mask_args', 'n_jobs', 'target_affine',
'target_shape'))
for param in masker_params:
if param in _ignore:
continue
if hasattr(new_masker, param):
new_masker_params[param] = getattr(new_masker, param)
# Append atlas extraction related parameters
if t_r is not None:
new_masker_params['t_r'] = t_r
if low_pass is not None:
new_masker_params['low_pass'] = low_pass
if high_pass is not None:
new_masker_params['high_pass'] = high_pass
if atlas_type is not None:
if len(img.shape) > 3 and atlas_type == 'maps':
new_masker_params['maps_img'] = img
new_masker = NiftiMapsMasker(**new_masker_params)
elif len(img.shape) == 3 and atlas_type == 'labels':
new_masker_params['labels_img'] = img
new_masker = NiftiLabelsMasker(**new_masker_params)
return new_masker
if seeds is not None and atlas_type == 'spheres':
if radius is not None:
new_masker_params['radius'] = radius
new_masker_params['seeds'] = seeds
new_masker = NiftiSpheresMasker(**new_masker_params)
return new_masker
def get_expression_data(atlas,
atlas_info=None,
*,
exact=True,
tolerance=2,
metric='mean',
ibf_threshold=0.5,
corrected_mni=True,
reannotated=True,
return_counts=False,
return_donors=False,
donors='all',
data_dir=None):
"""
Assigns microarray expression data to ROIs defined in `atlas`
This function aims to provide a workflow for generating pre-processed,
microarray expression data for abitrary `atlas` designations. First, some
basic filtering of genetic probes is performed, including:
1. Intensity-based filtering of microarray probes to remove probes that
do not exceed a certain level of background noise (specified via the
`ibf_threshold` parameter), and
2. Selection of a single, representative probe for each gene via a
differential stability metric, wherein the probe that has the most
consistent regional variation across donors is retained.
Tissue samples are then matched to parcels in the defined `atlas` for each
donor. If `atlas_info` is provided then this matching is constrained by
both hemisphere and tissue class designation (e.g., cortical samples from
the left hemisphere are only matched to ROIs in the left cortex,
subcortical samples from the right hemisphere are only matched to ROIs in
the left subcortex); see the `atlas_info` parameter description for more
information.
Matching of microarray samples to parcels in `atlas` is done via a multi-
step process:
1. Determine if the sample falls directly within a parcel,
2. Check to see if there are nearby parcels by slowly expanding the
search space to include nearby voxels, up to a specified distance
(specified via the `tolerance` parameter),
3. If there are multiple nearby parcels, the sample is assigned to the
closest parcel, as determined by the parcel centroid.
If at any step a sample can be assigned to a parcel the matching process is
terminated. If multiple sample are assigned to the same parcel they are
aggregated with the metric specified via the `metric` parameter. More
control over the sample matching can be obtained by setting the `exact`
parameter; see the parameter description for more information.
Once all samples have been matched to parcels for all supplied donors, the
microarray expression data are normalized within-donor via a scaled robust
sigmoid (SRS) procedure before being combined across donors via the
supplied `metric`.
Parameters
----------
atlas : niimg-like object
A parcellation image in MNI space, where each parcel is identified by a
unique integer ID
atlas_info : str or :class:`pandas.DataFrame`, optional
Filepath to or pre-loaded dataframe containing information about
`atlas`. Must have at least columns 'id', 'hemisphere', and 'structure'
containing information mapping atlas IDs to hemisphere (i.e, "L", "R")
and broad structural class (i.e., "cortex", "subcortex", "cerebellum").
Default: None
exact : bool, optional
Whether to use exact matching of donor tissue samples to parcels in
`atlas`. If True, this function will match tissue samples to parcels
within `threshold` mm of the sample; any samples that are beyond
`threshold` mm of a parcel will be discarded. This may result in some
parcels having no assigned sample / expression data. If False, the
default matching procedure will be performed and followed by a check
for parcels with no assigned samples; any such parcels will be matched
to the nearest sample (nearest defined as the sample with the closest
Euclidean distance to the parcel centroid). Default: True
tolerance : int, optional
Distance (in mm) that a sample must be from a parcel for it to be
matched to that parcel. This is only considered if the sample is not
directly within a parcel. Default: 2
metric : str or func, optional
Mechanism by which to collapse across donors, if input `files` provides
multiple donor datasets. If a str, should be in ['mean', 'median']; if
a function, should be able to accept an `N`-dimensional input and the
`axis` keyword argument and return an `N-1`-dimensional output.
Default: 'mean'
ibf_threshold : [0, 1] float, optional
Threshold for intensity-based filtering specifying. This number should
specify the ratio of samples, across all supplied donors, for which a
probe must have signal above background noise in order to be retained.
Default: 0.5
corrected_mni : bool, optional
Whether to use the "corrected" MNI coordinates shipped with the
`alleninf` package instead of the coordinates provided with the AHBA
data when matching tissue samples to anatomical regions. Default: True
reannotated : bool, optional
Whether to use reannotated probe information provided by [1]_ instead
of the default probe information from the AHBA dataset. Using
reannotated information will discard probes that could not be reliably
matched to genes. Default: True
return_counts : bool, optional
Whether to return how many samples were assigned to each parcel in
`atlas` for each donor. Default: False
return_donors : bool, optional
Whether to return donor-level expression arrays instead of aggregating
expression across donors with provided `metric`. Default: False
donors : list, optional
List of donors to use as sources of expression data. Can be either
donor numbers or UID. If not specified will use all available donors.
Default: 'all'
data_dir : str, optional
Directory where expression data should be downloaded (if it does not
already exist) / loaded. If not specified will use the current
directory. Default: None
Returns
-------
expression : (R, G) :class:`pandas.DataFrame`
Microarray expression for `R` regions in `atlas` for `G` genes,
aggregated across donors, where the index corresponds to the unique
integer IDs of `atlas` and the columns are gene names.
counts : (R, D) :class:`pandas.DataFrame`
Number of samples assigned to each of `R` regions in `atlas` for each
of `D` donors (if multiple donors were specified); only returned if
`return_counts=True`.
References
----------
.. [1] Arnatkevic̆iūtė, A., Fulcher, B. D., & Fornito, A. (2019). A
practical guide to linking brain-wide gene expression and neuroimaging
data. NeuroImage, 189, 353-367.
.. [2] Hawrylycz, M.J. et al. (2012) An anatomically comprehensive atlas of
the adult human transcriptome. Nature, 489, 391-399.
"""
# fetch files
files = datasets.fetch_microarray(data_dir=data_dir, donors=donors)
for key in ['microarray', 'probes', 'annotation', 'pacall', 'ontology']:
if key not in files:
raise KeyError('Provided `files` dictionary is missing {}. '
'Please check inputs.'.format(key))
# load atlas_info, if provided
atlas = check_niimg_3d(atlas)
if atlas_info is not None:
atlas_info = utils.check_atlas_info(atlas, atlas_info)
# get combination functions
metric = utils.check_metric(metric)
# get some info on the number of subjects, labels in `atlas_img`
num_subj = len(files.microarray)
all_labels = utils.get_unique_labels(atlas)
if not exact:
centroids = utils.get_centroids(atlas, labels=all_labels)
# reannotate probes based on updates from Arnatkeviciute et al., 2018 then
# perform intensity-based filter of probes and select probe with highest
# differential stability for each gene amongst remaining probes
if reannotated:
probes = process.reannotate_probes(files.probes[0])
else:
probes = io.read_probes(files.probes[0])
probes = process.filter_probes(files.pacall,
probes,
threshold=ibf_threshold)
probes = process.get_stable_probes(files.microarray, files.annotation,
probes)
expression, missing = [], []
counts = pd.DataFrame(np.zeros((len(all_labels) + 1, num_subj)),
index=np.append([0], all_labels))
for subj in range(num_subj):
# get rid of samples whose coordinates don't match ontological profile
annotation = process.drop_mismatch_samples(files.annotation[subj],
files.ontology[subj],
corrected=corrected_mni)
# subset representative probes + samples from microarray data
microarray = io.read_microarray(files.microarray[subj])
samples = microarray.loc[probes.index, annotation.index].T
samples.columns = probes.gene_symbol
# assign samples to regions and aggregate samples w/i the same region
sample_labels = label_samples(annotation,
atlas,
atlas_info=atlas_info,
tolerance=tolerance)
expression += [
group_by_label(samples, sample_labels, all_labels, metric=metric)
]
# get counts of samples collapsed into each ROI
labs, num = np.unique(sample_labels, return_counts=True)
counts.loc[labs, subj] = num
# if we don't want to do exact matching then cache which parcels are
# missing data and the expression data for the closest sample to that
# parcel; we'll use this once we've iterated through all donors
if not exact:
coords = utils.xyz_to_ijk(annotation[['mni_x', 'mni_y', 'mni_z']],
atlas.affine)
empty = ~np.in1d(all_labels, labs)
closest, dist = utils.closest_centroid(coords,
centroids[empty],
return_dist=True)
closest = samples.loc[annotation.iloc[closest].index]
empty = all_labels[empty]
closest.index = pd.Series(empty, name='label')
missing += [(closest, dict(zip(empty, np.diag(dist))))]
# check for missing ROIs and fill in, as needed
if not exact:
# find labels that are missing across all donors
empty = reduce(set.intersection, [set(f.index) for f, d in missing])
for roi in empty:
# find donor with sample closest to centroid of empty parcel
ind = np.argmin([d.get(roi) for f, d in missing])
# assign expression data from that sample and add to count
expression[ind].loc[roi] = missing[ind][0].loc[roi]
counts.loc[roi, ind] += 1
# normalize data with SRS and aggregate across donors
expression = [process.normalize_expression(e) for e in expression]
if not return_donors:
expression = process.aggregate_donors(expression, metric)
if return_counts:
return expression, counts.iloc[1:]
return expression
def plot_img_on_surf(stat_map,
surf_mesh='fsaverage5',
mask_img=None,
hemispheres=['left', 'right'],
inflate=False,
views=['lateral', 'medial'],
output_file=None,
title=None,
colorbar=True,
vmax=None,
threshold=None,
cmap='cold_hot',
aspect_ratio=1.4,
**kwargs):
"""Convenience function to plot multiple views of plot_surf_stat_map
in a single figure. It projects stat_map into meshes and plots views of
left and right hemispheres. The *views* argument defines the views
that are shown. This function returns the fig, axes elements from
matplotlib unless kwargs sets and output_file, in which case nothing
is returned.
Parameters
----------
stat_map : str or 3D Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
surf_mesh : str, dict, or None, optional
If str, either one of the two:
'fsaverage5': the low-resolution fsaverage5 mesh (10242 nodes)
'fsaverage': the high-resolution fsaverage mesh (163842 nodes)
If dict, a dictionary with keys: ['infl_left', 'infl_right',
'pial_left', 'pial_right', 'sulc_left', 'sulc_right'], where
values are surface mesh geometries as accepted by plot_surf_stat_map.
Default='fsaverage5'.
mask_img : Niimg-like object or None, optional
The mask is passed to vol_to_surf.
Samples falling out of this mask or out of the image are ignored
during projection of the volume to the surface.
If ``None``, don't apply any mask.
inflate : bool, optional
If True, display images in inflated brain.
If False, display images in pial surface.
Default=False.
views : list of strings, optional
A list containing all views to display.
The montage will contain as many rows as views specified by
display mode. Order is preserved, and left and right hemispheres
are shown on the left and right sides of the figure.
Default=['lateral', 'medial'].
hemispheres : list of strings, optional
Hemispheres to display. Default=['left', 'right'].
output_file : str, optional
The name of an image file to export plot to. Valid extensions
are: *.png*, *.pdf*, *.svg*. If output_file is not None,
the plot is saved to a file, and the display is closed. Return
value is None.
title : str, optional
Place a title on the upper center of the figure.
colorbar : bool, optional
If *True*, a symmetric colorbar of the statistical map is displayed.
Default=True.
vmax : float, optional
Upper bound for plotting of stat_map values.
threshold : float, optional
If None is given, the image is not thresholded.
If a number is given, it is used to threshold the image,
values below the threshold (in absolute value) are plotted
as transparent.
cmap : str, optional
The name of a matplotlib or nilearn colormap. Default='cold_hot'.
kwargs : dict, optional
keyword arguments passed to plot_surf_stat_map.
See Also
--------
nilearn.datasets.fetch_surf_fsaverage : For surface data object to be
used as the default background map for this plotting function.
nilearn.surface.vol_to_surf : For info on the generation of surfaces.
nilearn.plotting.plot_surf_stat_map : For info on kwargs options
accepted by plot_img_on_surf.
"""
for arg in ('figure', 'axes'):
if arg in kwargs:
raise ValueError(('plot_img_on_surf does not'
' accept %s as an argument' % arg))
stat_map = check_niimg_3d(stat_map, dtype='auto')
modes = _check_views(views)
hemis = _check_hemispheres(hemispheres)
surf_mesh = _check_mesh(surf_mesh)
mesh_prefix = "infl" if inflate else "pial"
surf = {
'left': surf_mesh[mesh_prefix + '_left'],
'right': surf_mesh[mesh_prefix + '_right'],
}
texture = {
'left': vol_to_surf(stat_map,
surf_mesh['pial_left'],
mask_img=mask_img),
'right': vol_to_surf(stat_map,
surf_mesh['pial_right'],
mask_img=mask_img)
}
figsize = plt.figaspect(len(modes) / (aspect_ratio * len(hemispheres)))
fig, axes = plt.subplots(nrows=len(modes),
ncols=len(hemis),
figsize=figsize,
subplot_kw={'projection': '3d'})
axes = np.atleast_2d(axes)
if len(hemis) == 1:
axes = axes.T
for index_mode, mode in enumerate(modes):
for index_hemi, hemi in enumerate(hemis):
bg_map = surf_mesh['sulc_%s' % hemi]
plot_surf_stat_map(
surf[hemi],
texture[hemi],
view=mode,
hemi=hemi,
bg_map=bg_map,
axes=axes[index_mode, index_hemi],
colorbar=False, # Colorbar created externally.
vmax=vmax,
threshold=threshold,
cmap=cmap,
**kwargs)
for ax in axes.flatten():
# We increase this value to better position the camera of the
# 3D projection plot. The default value makes meshes look too small.
ax.dist = 6
if colorbar:
sm = _colorbar_from_array(image.get_data(stat_map),
vmax,
threshold,
kwargs,
cmap=get_cmap(cmap))
cbar_ax = fig.add_subplot(32, 1, 32)
fig.colorbar(sm, cax=cbar_ax, orientation='horizontal')
fig.subplots_adjust(wspace=-0.02, hspace=0.0)
if title is not None:
fig.suptitle(title)
if output_file is not None:
fig.savefig(output_file)
plt.close(fig)
else:
return fig, axes
def apply_mask(self, series, mask_img):
mask_img = _utils.check_niimg_3d(mask_img)
mask, mask_affine = masking._load_mask_img(mask_img)
mask_img = image.new_img_like(mask_img, mask, mask_affine)
mask_data = _utils.as_ndarray(mask_img.get_data(), dtype=np.bool)
return series[mask_data].T
def get_clusters_table(stat_img,
stat_threshold,
cluster_threshold=None,
min_distance=8.):
"""Creates pandas dataframe with img cluster statistics.
Parameters
----------
stat_img : Niimg-like object,
Statistical image (presumably in z- or p-scale).
stat_threshold : `float`
Cluster forming threshold in same scale as `stat_img` (either a
p-value or z-scale value).
cluster_threshold : `int` or `None`, optional
Cluster size threshold, in voxels.
min_distance : `float`, optional
Minimum distance between subpeaks in mm. Default=8mm.
Returns
-------
df : `pandas.DataFrame`
Table with peaks and subpeaks from thresholded `stat_img`. For binary
clusters (clusters with >1 voxel containing only one value), the table
reports the center of mass of the cluster,
rather than any peaks/subpeaks.
"""
cols = ['Cluster ID', 'X', 'Y', 'Z', 'Peak Stat', 'Cluster Size (mm3)']
# check that stat_img is niimg-like object and 3D
stat_img = check_niimg_3d(stat_img)
# If cluster threshold is used, there is chance that stat_map will be
# modified, therefore copy is needed
if cluster_threshold is None:
stat_map = get_data(stat_img)
else:
stat_map = get_data(stat_img).copy()
conn_mat = np.zeros((3, 3, 3), int) # 6-connectivity, aka NN1 or "faces"
conn_mat[1, 1, :] = 1
conn_mat[1, :, 1] = 1
conn_mat[:, 1, 1] = 1
voxel_size = np.prod(stat_img.header.get_zooms())
# Binarize using CDT
binarized = stat_map > stat_threshold
binarized = binarized.astype(int)
# If the stat threshold is too high simply return an empty dataframe
if np.sum(binarized) == 0:
warnings.warn('Attention: No clusters with stat higher than %f' %
stat_threshold)
return pd.DataFrame(columns=cols)
# Extract connected components above cluster size threshold
label_map = ndimage.measurements.label(binarized, conn_mat)[0]
clust_ids = sorted(list(np.unique(label_map)[1:]))
for c_val in clust_ids:
if cluster_threshold is not None and np.sum(
label_map == c_val) < cluster_threshold:
stat_map[label_map == c_val] = 0
binarized[label_map == c_val] = 0
# If the cluster threshold is too high simply return an empty dataframe
# this checks for stats higher than threshold after small clusters
# were removed from stat_map
if np.sum(stat_map > stat_threshold) == 0:
warnings.warn('Attention: No clusters with more than %d voxels' %
cluster_threshold)
return pd.DataFrame(columns=cols)
# Now re-label and create table
label_map = ndimage.measurements.label(binarized, conn_mat)[0]
clust_ids = sorted(list(np.unique(label_map)[1:]))
peak_vals = np.array(
[np.max(stat_map * (label_map == c)) for c in clust_ids])
clust_ids = [clust_ids[c] for c in (-peak_vals).argsort()
] # Sort by descending max value
rows = []
for c_id, c_val in enumerate(clust_ids):
cluster_mask = label_map == c_val
masked_data = stat_map * cluster_mask
cluster_size_mm = int(np.sum(cluster_mask) * voxel_size)
# Get peaks, subpeaks and associated statistics
subpeak_ijk, subpeak_vals = _local_max(masked_data,
stat_img.affine,
min_distance=min_distance)
subpeak_xyz = np.asarray(
coord_transform(subpeak_ijk[:, 0], subpeak_ijk[:, 1],
subpeak_ijk[:, 2], stat_img.affine)).tolist()
subpeak_xyz = np.array(subpeak_xyz).T
# Only report peak and, at most, top 3 subpeaks.
n_subpeaks = np.min((len(subpeak_vals), 4))
for subpeak in range(n_subpeaks):
if subpeak == 0:
row = [
c_id + 1, subpeak_xyz[subpeak, 0], subpeak_xyz[subpeak, 1],
subpeak_xyz[subpeak,
2], subpeak_vals[subpeak], cluster_size_mm
]
else:
# Subpeak naming convention is cluster num+letter: 1a, 1b, etc
sp_id = '{0}{1}'.format(c_id + 1, ascii_lowercase[subpeak - 1])
row = [
sp_id, subpeak_xyz[subpeak, 0], subpeak_xyz[subpeak, 1],
subpeak_xyz[subpeak, 2], subpeak_vals[subpeak], ''
]
rows += [row]
df = pd.DataFrame(columns=cols, data=rows)
return df
def get_stat_map(stat_map_img,
bg_img,
cut_coords=None,
colorbar=True,
title=None,
threshold=None,
annotate=True,
draw_cross=True,
black_bg='auto',
cmap=cm.cold_hot,
symmetric_cbar='auto',
dim='auto',
vmax=None,
resampling_interpolation='continuous',
n_colors=256,
opacity=1,
**kwargs):
"""
Intarctive viewer of a statistical map, with optional background
Parameters
----------
stat_map_img : Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
The statistical map image.
bg_img : Niimg-like object (default='MNI152')
See http://nilearn.github.io/manipulating_images/input_output.html
The background image that the stat map will be plotted on top of.
If nothing is specified, the MNI152 template will be used.
To turn off background image, just pass "bg_img=False".
cut_coords : None, a tuple of floats, or an integer (default None)
The MNI coordinates of the point where the cut is performed
as a 3-tuple: (x, y, z). If None is given, the cuts is calculated
automaticaly.
This parameter is not currently supported.
colorbar : boolean, optional (default True)
If True, display a colorbar next to the plots.
title : string or None (default=None)
The title displayed on the figure (or None: no title).
This parameter is not currently supported.
threshold : str, number or None (default=None)
If None is given, the image is not thresholded.
If a number is given, it is used to threshold the image:
values below the threshold (in absolute value) are plotted
as transparent. If auto is given, the threshold is determined
magically by analysis of the image.
annotate : boolean (default=True)
If annotate is True, positions and left/right annotation
are added to the plot.
draw_cross : boolean (default=True)
If draw_cross is True, a cross is drawn on the plot to
indicate the cut plosition.
black_bg : boolean (default='auto')
If True, the background of the image is set to be black.
Otherwise, a white background is used.
If set to auto, an educated guess is made to find if the background
is white or black.
cmap : matplotlib colormap, optional
The colormap for specified image. The colormap *must* be
symmetrical.
symmetric_cbar : boolean or 'auto' (default='auto')
Specifies whether the colorbar should range from -vmax to vmax
or from vmin to vmax. Setting to 'auto' will select the latter if
the range of the whole image is either positive or negative.
Note: The colormap will always be set to range from -vmax to vmax.
dim : float, 'auto' (default='auto')
Dimming factor applied to background image. By default, automatic
heuristics are applied based upon the background image intensity.
Accepted float values, where a typical scan is between -2 and 2
(-2 = increase constrast; 2 = decrease contrast), but larger values
can be used for a more pronounced effect. 0 means no dimming.
vmax : float, or None (default=)
max value for mapping colors.
resampling_interpolation : string, optional (default nearest)
The interpolation method for resampling
See nilearn.image.resample_img
n_colors : integer (default=256)
The number of discrete colors to use in the colormap, if it is
generated.
opacity : float in [0,1] (default 1)
The level of opacity of the overlay (0: transparent, 1: opaque)
Returns
-------
StatMapView : plot of the stat map.
It can be saved as an html page or rendered (transparently) by the
Jupyter notebook.
"""
# Load stat map
stat_map_img = check_niimg_3d(stat_map_img, dtype='auto')
_, _, vmin, vmax = _get_colorbar_and_data_ranges(
_safe_get_data(stat_map_img, ensure_finite=True), vmax, symmetric_cbar,
kwargs)
# load background image, and resample stat map
if bg_img is not None and bg_img is not False:
bg_img, black_bg, bg_min, bg_max = _load_anat(bg_img,
dim=dim,
black_bg=black_bg)
bg_img = _resample_to_self(bg_img,
interpolation=resampling_interpolation)
stat_map_img = image.resample_to_img(
stat_map_img, bg_img, interpolation=resampling_interpolation)
else:
stat_map_img = _resample_to_self(
stat_map_img, interpolation=resampling_interpolation)
bg_img = image.new_img_like(stat_map_img, np.zeros(stat_map_img.shape),
stat_map_img.affine)
bg_min = 0
bg_max = 0
if black_bg == 'auto':
black_bg = False
# Select coordinates for the cut
# https://github.com/nilearn/nilearn/blob/master/nilearn/plotting/displays.py#L943
if isinstance(cut_coords, numbers.Number):
raise ValueError(
"The input given for display_mode='ortho' needs to be "
"a list of 3d world coordinates in (x, y, z). "
"You provided single cut, cut_coords={0}".format(cut_coords))
if cut_coords is None:
cut_coords = find_xyz_cut_coords(stat_map_img,
activation_threshold=threshold)
print(cut_coords)
# Create a base64 sprite for the background
bg_sprite = BytesIO()
save_sprite(bg_img,
output_sprite=bg_sprite,
cmap='gray',
format='jpg',
resample=False,
vmin=bg_min,
vmax=bg_max)
bg_sprite.seek(0)
bg_base64 = encodebytes(bg_sprite.read()).decode('utf-8')
bg_sprite.close()
# Create a base64 sprite for the stat map
# Possibly, also generate a file with the colormap
stat_map_sprite = BytesIO()
stat_map_json = StringIO()
if colorbar:
stat_map_cm = BytesIO()
else:
stat_map_cm = None
cmap_c = _custom_cmap(cmap, vmin, vmax, threshold)
save_sprite(stat_map_img, stat_map_sprite, stat_map_cm, stat_map_json,
vmax, vmin, cmap_c, threshold, n_colors, 'png', False)
# Convert the sprite and colormap to base64
stat_map_sprite.seek(0)
stat_map_base64 = encodebytes(stat_map_sprite.read()).decode('utf-8')
stat_map_sprite.close()
if colorbar:
stat_map_cm.seek(0)
cm_base64 = encodebytes(stat_map_cm.read()).decode('utf-8')
stat_map_cm.close()
else:
cm_base64 = ''
# Load the sprite meta-data from the json dump
stat_map_json.seek(0)
params = json.load(stat_map_json)
stat_map_json.close()
# Convet cut coordinates into cut slices
cut_slices = np.round(
nb.affines.apply_affine(np.linalg.inv(stat_map_img.affine),
cut_coords))
# Create a json-like structure
# with all the brain sprite parameters
sprite_params = {
'canvas': '3Dviewer',
'sprite': 'spriteImg',
'nbSlice': params['nbSlice'],
'overlay': {
'sprite': 'overlayImg',
'nbSlice': params['nbSlice'],
'opacity': opacity
},
'colorBackground': '#000000',
'colorFont': '#ffffff',
'colorCrosshair': '#de101d',
'crosshair': draw_cross,
'affine': params['affine'],
'flagCoordinates': annotate,
'title': title,
'flagValue': annotate,
'numSlice': {
'X': cut_slices[0],
'Y': cut_slices[1],
'Z': cut_slices[2]
},
}
if colorbar:
sprite_params['colorMap'] = {
'img': 'colorMap',
'min': params['min'],
'max': params['max']
}
return sprite_params, bg_base64, stat_map_base64, cm_base64
def save_sprite(img,
output_sprite,
output_cmap=None,
output_json=None,
vmax=None,
vmin=None,
cmap='Greys',
threshold=None,
n_colors=256,
format='png',
resample=True,
interpolation='nearest'):
""" Generate a sprite from a 3D Niimg-like object.
Parameters
----------
img : Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
output_file : string or file-like
Path string to a filename, or a Python file-like object.
If *format* is *None* and *fname* is a string, the output
format is deduced from the extension of the filename.
output_cmap : string, file-like or None, optional (default None)
Path string to a filename, or a Python file-like object.
The color map will be saved in that file (unless it is None).
If *format* is *None* and *fname* is a string, the output format is
deduced from the extension of the filename.
output_json : string, file-like or None, optional (default None)
Path string to a filename, or a Python file-like object.
The parameters of the sprite will be saved in that file
(unless it is None): Y and Z sizes, vmin, vmax, affine transform.
vmax : float, or None, optional (default None)
max value for mapping colors.
vmin : float, or None, optional (default None)
min value for mapping color.
cmap : name of a matplotlib colormap, optional (default 'Greys')
The colormap for the sprite. A matplotlib colormap can also
be passed directly in cmap.
threshold : a number, None, or 'auto', optional (default None)
If None is given, the image is not thresholded.
If a number is given, it is used to threshold the image:
values below the threshold (in absolute value) are plotted
as transparent. If auto is given, the threshold is determined
magically by analysis of the image.
n_colors : integer, optional (default 256)
The number of discrete colors to use in the colormap, if it is
generated.
format : string, optional (default 'png')
One of the file extensions supported by the active backend. Most
backends support png, pdf, ps, eps and svg.
resample : boolean, optional (default True)
Resample to isotropic voxels, with a LR/AP/VD orientation.
This is necessary for proper rendering of arbitrary Niimg volumes,
but not necessary if the image is in an isotropic standard space.
interpolation : string, optional (default nearest)
The interpolation method for resampling
See nilearn.image.resample_img
black_bg : boolean, optional
If True, the background of the image is set to be black.
Returns
----------
sprite : numpy array with the sprite
"""
# Get cmap
if isinstance(cm, str):
cmap = plt.cm.get_cmap(cmap)
img = check_niimg_3d(img, dtype='auto')
# resample to isotropic voxel with standard orientation
if resample:
img = _resample_to_self(img, interpolation)
# Read data
data = _safe_get_data(img, ensure_finite=True)
if np.isnan(np.sum(data)):
data = np.nan_to_num(data)
# Deal with automatic settings of plot parameters
if threshold == 'auto':
# Threshold epsilon below a percentile value, to be sure that some
# voxels pass the threshold
threshold = fast_abs_percentile(data) - 1e-5
# threshold
threshold = float(threshold) if threshold is not None else None
# Get vmin vmax
show_nan_msg = False
if vmax is not None and np.isnan(vmax):
vmax = None
show_nan_msg = True
if vmin is not None and np.isnan(vmin):
vmin = None
show_nan_msg = True
if show_nan_msg:
nan_msg = ('NaN is not permitted for the vmax and vmin arguments.\n'
'Tip: Use np.nanmax() instead of np.max().')
warnings.warn(nan_msg)
if vmax is None:
vmax = np.nanmax(data)
if vmin is None:
vmin = np.nanmin(data)
# Create sprite
sprite = _data2sprite(data)
# Mask sprite
if threshold is not None:
if threshold == 0:
sprite = np.ma.masked_equal(sprite, 0, copy=False)
else:
sprite = np.ma.masked_inside(sprite,
-threshold,
threshold,
copy=False)
# Save the sprite
imsave(output_sprite,
sprite,
vmin=vmin,
vmax=vmax,
cmap=cmap,
format=format)
# Save the parameters
if type(vmin).__module__ == 'numpy':
vmin = vmin.tolist() # json does not deal with numpy array
if type(vmax).__module__ == 'numpy':
vmax = vmax.tolist() # json does not deal with numpy array
if output_json is not None:
params = {
'nbSlice': {
'X': data.shape[0],
'Y': data.shape[1],
'Z': data.shape[2]
},
'min': vmin,
'max': vmax,
'affine': img.affine.tolist()
}
if isinstance(output_json, str):
f = open(output_json, 'w')
f.write(json.dumps(params))
f.close()
else:
output_json.write(json.dumps(params))
# save the colormap
if output_cmap is not None:
data = np.arange(0, n_colors) / (n_colors - 1)
data = data.reshape([1, n_colors])
imsave(output_cmap, data, cmap=cmap, format=format)
return sprite
def fit(self, imgs=None, y=None):
"""Compute the mask corresponding to the data
Parameters
----------
imgs: list of Niimg-like objects
See http://nilearn.github.io/manipulating_visualizing/manipulating_images.html#niimg.
Data on which the mask must be calculated. If this is a list,
the affine is considered the same for all.
"""
# Load data (if filenames are given, load them)
if self.verbose > 0:
print("[%s.fit] Loading data from %s" % (
self.__class__.__name__,
_utils._repr_niimgs(imgs)[:200]))
# Compute the mask if not given by the user
if self.mask_img is None:
if self.verbose > 0:
print("[%s.fit] Computing mask" % self.__class__.__name__)
if not isinstance(imgs, collections.Iterable) \
or isinstance(imgs, _basestring):
raise ValueError("[%s.fit] For multiple processing, you should"
" provide a list of data "
"(e.g. Nifti1Image objects or filenames)."
"%r is an invalid input"
% (self.__class__.__name__, imgs))
mask_args = (self.mask_args if self.mask_args is not None
else {})
if self.mask_strategy == 'background':
compute_mask = masking.compute_multi_background_mask
elif self.mask_strategy == 'epi':
compute_mask = masking.compute_multi_epi_mask
else:
raise ValueError("Unknown value of mask_strategy '%s'. "
"Acceptable values are 'background' and 'epi'.")
self.mask_img_ = self._cache(compute_mask,
ignore=['n_jobs', 'verbose',
'memory'])(
imgs,
target_affine=self.target_affine,
target_shape=self.target_shape,
n_jobs=self.n_jobs,
memory=self.memory,
verbose=max(0, self.verbose - 1),
**mask_args)
else:
if imgs is not None:
warnings.warn('[%s.fit] Generation of a mask has been'
' requested (imgs != None) while a mask has'
' been provided at masker creation. Given mask'
' will be used.' % self.__class__.__name__)
self.mask_img_ = _utils.check_niimg_3d(self.mask_img)
# If resampling is requested, resample the mask as well.
# Resampling: allows the user to change the affine, the shape or both.
if self.verbose > 0:
print("[%s.transform] Resampling mask" % self.__class__.__name__)
self.mask_img_ = self._cache(image.resample_img)(
self.mask_img_,
target_affine=self.target_affine,
target_shape=self.target_shape,
interpolation='nearest', copy=False)
if self.target_affine is not None:
self.affine_ = self.target_affine
else:
self.affine_ = self.mask_img_.get_affine()
# Load data in memory
self.mask_img_.get_data()
return self
def jumeg_plot_stat_map(stat_map_img, t, bg_img=MNI152TEMPLATE, cut_coords=None,
output_file=None, display_mode='ortho', colorbar=True,
figure=None, axes=None, title=None, threshold=1e-6,
annotate=True, draw_cross=True, black_bg='auto',
cmap='magma', symmetric_cbar="auto", cbar_range=None,
dim='auto', vmax=None, resampling_interpolation='continuous',
**kwargs):
"""
Plot cuts of an ROI/mask image (by default 3 cuts: Frontal, Axial, and
Lateral)
This is based on nilearn.plotting.plot_stat_map
Parameters
----------
stat_map_img : Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
The statistical map image
t : int
Plot activity at time point given by time t.
bg_img : Niimg-like object
See http://nilearn.github.io/manipulating_images/input_output.html
The background image that the ROI/mask will be plotted on top of.
If nothing is specified, the MNI152 template will be used.
To turn off background image, just pass "bg_img=False".
cut_coords : None, a tuple of floats, or an integer
The MNI coordinates of the point where the cut is performed
If display_mode is 'ortho', this should be a 3-tuple: (x, y, z)
For display_mode == 'x', 'y', or 'z', then these are the
coordinates of each cut in the corresponding direction.
If None is given, the cuts is calculated automaticaly.
If display_mode is 'x', 'y' or 'z', cut_coords can be an integer,
in which case it specifies the number of cuts to perform
output_file : string, or None, optional
The name of an image file to export the plot to. Valid extensions
are .png, .pdf, .svg. If output_file is not None, the plot
is saved to a file, and the display is closed.
display_mode : {'ortho', 'x', 'y', 'z', 'yx', 'xz', 'yz'}
Choose the direction of the cuts: 'x' - sagittal, 'y' - coronal,
'z' - axial, 'ortho' - three cuts are performed in orthogonal
directions.
colorbar : boolean, optional
If True, display a colorbar on the right of the plots.
figure : integer or matplotlib figure, optional
Matplotlib figure used or its number. If None is given, a
new figure is created.
axes : matplotlib axes or 4 tuple of float: (xmin, ymin, width, height), optional
The axes, or the coordinates, in matplotlib figure space,
of the axes used to display the plot. If None, the complete
figure is used.
title : string, optional
The title displayed on the figure.
threshold : a number, None, or 'auto'
If None is given, the image is not thresholded.
If a number is given, it is used to threshold the image:
values below the threshold (in absolute value) are plotted
as transparent. If auto is given, the threshold is determined
magically by analysis of the image.
annotate : boolean, optional
If annotate is True, positions and left/right annotation
are added to the plot.
draw_cross : boolean, optional
If draw_cross is True, a cross is drawn on the plot to
indicate the cut plosition.
black_bg : boolean, optional
If True, the background of the image is set to be black. If
you wish to save figures with a black background, you
will need to pass "facecolor='k', edgecolor='k'"
to matplotlib.pyplot.savefig.
cmap : matplotlib colormap, optional
The colormap for specified image. The ccolormap *must* be
symmetrical.
symmetric_cbar : boolean or 'auto', optional, default 'auto'
Specifies whether the colorbar should range from -vmax to vmax
or from vmin to vmax. Setting to 'auto' will select the latter if
the range of the whole image is either positive or negative.
Note: The colormap will always be set to range from -vmax to vmax.
cbar_range : None, 2-tuple
Color range of the plot.
dim : float, 'auto' (by default), optional
Dimming factor applied to background image. By default, automatic
heuristics are applied based upon the background image intensity.
Accepted float values, where a typical scan is between -2 and 2
(-2 = increase constrast; 2 = decrease contrast), but larger values
can be used for a more pronounced effect. 0 means no dimming.
vmax : float
Upper bound for plotting, passed to matplotlib.pyplot.imshow
resampling_interpolation : str
Interpolation to use when resampling the image to the destination
space. Can be "continuous" (default) to use 3rd-order spline
interpolation, or "nearest" to use nearest-neighbor mapping.
"nearest" is faster but can be noisier in some cases.
Notes
-----
Arrays should be passed in numpy convention: (x, y, z)
ordered.
For visualization, non-finite values found in passed 'stat_map_img' or
'bg_img' are set to zero.
See Also
--------
nilearn.plotting.plot_anat : To simply plot anatomical images
nilearn.plotting.plot_epi : To simply plot raw EPI images
nilearn.plotting.plot_glass_brain : To plot maps in a glass brain
"""
# noqa: E501
# dim the background
from nilearn.plotting.img_plotting import _load_anat, _plot_img_with_bg, _get_colorbar_and_data_ranges
from nilearn._utils import check_niimg_3d, check_niimg_4d
from nilearn._utils.niimg_conversions import _safe_get_data
bg_img, black_bg, bg_vmin, bg_vmax = _load_anat(bg_img, dim=dim,
black_bg=black_bg)
stat_map_img = check_niimg_4d(stat_map_img, dtype='auto')
cbar_vmin, cbar_vmax, vmin, vmax = _get_colorbar_and_data_ranges(_safe_get_data(stat_map_img, ensure_finite=True),
vmax, symmetric_cbar, kwargs)
if cbar_range is not None:
cbar_vmin = cbar_range[0]
cbar_vmax = cbar_range[1]
vmin = cbar_range[0]
vmax = cbar_range[1]
stat_map_img_at_time_t = index_img(stat_map_img, t)
stat_map_img_at_time_t = check_niimg_3d(stat_map_img_at_time_t, dtype='auto')
display = _plot_img_with_bg(
img=stat_map_img_at_time_t, bg_img=bg_img, cut_coords=cut_coords,
output_file=output_file, display_mode=display_mode,
figure=figure, axes=axes, title=title, annotate=annotate,
draw_cross=draw_cross, black_bg=black_bg, threshold=threshold,
bg_vmin=bg_vmin, bg_vmax=bg_vmax, cmap=cmap, vmin=vmin, vmax=vmax,
colorbar=colorbar, cbar_vmin=cbar_vmin, cbar_vmax=cbar_vmax,
resampling_interpolation=resampling_interpolation, **kwargs)
return display
def compute_spheres_values(self, imgs):
start_t = time.time()
# Force to get a list of imgs even if only one is given
imgs_to_check = [imgs] if not isinstance(imgs, list) else imgs
# Load Nifti images
ref_shape = imgs_to_check[0].dataobj.shape
ref_affine = imgs_to_check[0].affine
imgs = []
for img in imgs_to_check:
# check if image is 4D
imgs.append(check_niimg_4d(img))
# Check that all images have same number of volumes
if ref_shape != img.dataobj.shape:
raise ValueError("All fMRI image must have same shape")
if np.array_equal(ref_affine, img.affine):
warnings.warn("fMRI images do not have same affine")
self.ref_img = imgs[0]
# Compute world coordinates of the seeds
process_mask_img = check_niimg_3d(self.process_mask_img)
process_mask_img = image.resample_to_img(
process_mask_img, imgs[0], interpolation='nearest'
)
self.process_mask_img = process_mask_img
process_mask, process_mask_affine = masking._load_mask_img(
process_mask_img
)
process_mask_coords = np.where(process_mask != 0)
self.vx_mask_coords = process_mask_coords
process_mask_coords = coord_transform(
process_mask_coords[0], process_mask_coords[1],
process_mask_coords[2], process_mask_affine)
process_mask_coords = np.asarray(process_mask_coords).T
if self.verbose:
print("{} seeds found in the mask".format(len(process_mask_coords)))
# Compute spheres
_, A = _apply_mask_and_get_affinity(
process_mask_coords, imgs[0], self.radius, True,
mask_img=self.mask_img
)
# Number of runs: 1 4D fMRI image / run
n_runs = len(imgs)
# Number of spheres (or seed voxels)
n_spheres = A.shape[0]
# Number of volumes in each 4D fMRI image
n_conditions = imgs[0].dataobj.shape[3]
mask_img = check_niimg_3d(self.mask_img)
mask_img = image.resample_img(
mask_img, target_affine=imgs[0].affine,
target_shape=imgs[0].shape[:3], interpolation='nearest'
)
masked_imgs_data = []
for i_run, img in enumerate(imgs):
masked_imgs_data.append(masking._apply_mask_fmri(img, mask_img))
# Extract data of each sphere
# X will be #spheres x #run x #conditions x #values
X = []
for i_sph in range(n_spheres):
# Indexes of all voxels included in the current sphere
sph_indexes = A.rows[i_sph]
if len(sph_indexes) == 0:
# Append when no data are available around the process voxel
X.append(np.full((n_runs, n_conditions, 1), 0))
print("Empty sphere")
else:
# Number of voxel in the current sphere
n_values = len(sph_indexes)
sub_X = np.empty((n_runs, n_conditions, n_values), dtype=object)
for i_run, img in enumerate(imgs):
for i_cond in range(n_conditions):
sub_X[i_run, i_cond] = masked_imgs_data[i_run][i_cond][
sph_indexes]
X.append(sub_X)
if self.verbose:
dt = time.time() - start_t
print("Elapsed time to extract spheres values: {:.01f}s".format(dt))
self.spheres_values = X
def fit(self):
self.mask_img_ = [_utils.check_niimg_3d(img) for img in self.mask_img]
return self
def fit(self):
self.mask_img_ = [_utils.check_niimg_3d(img) for img in self.mask_img]
return self
def connected_label_regions(labels_img, min_size=None, connect_diag=True,
labels=None):
""" Extract connected regions from a brain atlas image defined by labels
(integers)
For each label in an parcellations, separates out connected
components and assigns to each separated region a unique label.
Parameters
----------
labels_img : Nifti-like image
A 3D image which contains regions denoted as labels. Each region
is assigned with integers.
min_size : float, in mm^3 optional (default None)
Minimum region size in volume required to keep after extraction.
Removes small or spurious regions.
connect_diag : bool (default True)
If 'connect_diag' is True, two voxels are considered in the same region
if they are connected along the diagonal (26-connectivity). If it is
False, two voxels are considered connected only if they are within the
same x, y, or z direction.
labels : 1D numpy array or list of str, (default None), optional
Each string in a list or array denote the name of the brain atlas
regions given in labels_img input. If provided, same names will be
re-assigned corresponding to each connected component based extraction
of regions relabelling. The total number of names should match with the
number of labels assigned in the image.
NOTE: The order of the names given in labels should be appropriately
matched with the unique labels (integers) assigned to each region
given in labels_img.
Returns
-------
new_labels_img : Nifti-like image
A new image comprising of regions extracted on an input labels_img.
new_labels : list, optional
If labels are provided, new labels assigned to region extracted will
be returned. Otherwise, only new labels image will be returned.
"""
labels_img = check_niimg_3d(labels_img)
labels_data = _safe_get_data(labels_img)
affine = labels_img.get_affine()
check_unique_labels = np.unique(labels_data)
if min_size is not None and not isinstance(min_size, numbers.Number):
raise ValueError("Expected 'min_size' to be specified as integer. "
"You provided {0}".format(min_size))
if not isinstance(connect_diag, bool):
raise ValueError("'connect_diag' must be specified as True or False. "
"You provided {0}".format(connect_diag))
if np.any(check_unique_labels < 0):
raise ValueError("The 'labels_img' you provided has unknown/negative "
"integers as labels {0} assigned to regions. "
"All regions in an image should have positive "
"integers assigned as labels."
.format(check_unique_labels))
unique_labels = set(check_unique_labels)
# check for background label indicated as 0
if np.any(check_unique_labels == 0):
unique_labels.remove(0)
if labels is not None:
if (not isinstance(labels, collections.Iterable) or
isinstance(labels, _basestring)):
labels = [labels, ]
if len(unique_labels) != len(labels):
raise ValueError("The number of labels: {0} provided as input "
"in labels={1} does not match with the number "
"of unique labels in labels_img: {2}. "
"Please provide appropriate match with unique "
"number of labels in labels_img."
.format(len(labels), labels, len(unique_labels)))
new_names = []
if labels is None:
this_labels = [None] * len(unique_labels)
else:
this_labels = labels
new_labels_data = np.zeros(labels_data.shape, dtype=np.int)
current_max_label = 0
for label_id, name in zip(unique_labels, this_labels):
this_label_mask = (labels_data == label_id)
# Extract regions assigned to each label id
if connect_diag:
structure = np.ones((3, 3, 3), dtype=np.int)
regions, this_n_labels = ndimage.label(
this_label_mask.astype(np.int), structure=structure)
else:
regions, this_n_labels = ndimage.label(this_label_mask.astype(np.int))
if min_size is not None:
index = np.arange(this_n_labels + 1)
this_label_mask = this_label_mask.astype(np.int)
regions = _remove_small_regions(regions, this_label_mask,
index, affine, min_size=min_size)
this_n_labels = regions.max()
cur_regions = regions[regions != 0] + current_max_label
new_labels_data[regions != 0] = cur_regions
current_max_label += this_n_labels
if name is not None:
new_names.extend([name] * this_n_labels)
new_labels_img = new_img_like(labels_img, new_labels_data, affine=affine)
if labels is not None:
new_labels = new_names
return new_labels_img, new_labels
return new_labels_img
def plot_vstc_grid_slice(vstc, params_plot_img_with_bg, time=None, cut_coords=6, display_mode='z',
figure=None, axes=None, colorbar=False, cmap='magma', threshold='min',
**kwargs):
"""
Plot a volume source space estimation for one slice in the grid in
plot_vstc_sliced_grid.
Parameters:
-----------
vstc : VolSourceEstimate
The volume source estimate.
time : int, float | None
None is default for finding the time sample with the voxel with global
maximal amplitude. If int, float the given time point is selected and
plotted.
cut_coords : list of a single float
The MNI coordinates of the point where the cut is performed
For display_mode == 'x', 'y', or 'z' this is the
coordinate of the cut in the corresponding direction.
display_mode : 'x', 'y', 'z'
Direction in which the brain is sliced.
figure : matplotlib.figure | None
Specify the figure container to plot in. If None, a new
matplotlib.figure is created
axes : matplotlib.figure.axes | None
Specify the axes of the given figure to plot in. Only necessary if
a figure is passed.
colorbar : bool
Show the colorbar.
cmap : matplotlib colormap, optional
The colormap for specified image. The colormap *must* be
symmetrical.
threshold : a number, None, 'auto', or 'min'
If None is given, the image is not thresholded.
If a number is given, it is used to threshold the image:
values below the threshold (in absolute value) are plotted
as transparent. If auto is given, the threshold is determined
magically by analysis of the image.
Returns:
--------
Figure : matplotlib.figure
VolSourceEstimation plotted for given or 'auto' coordinates at given
or 'auto' timepoint.
"""
vstcdata = vstc.data
if time is None:
# global maximum amp in time
t = int(np.where(np.sum(vstcdata, axis=0) == np.max(np.sum(vstcdata, axis=0)))[0])
t_in_ms = vstc.times[t] * 1e3
else:
t = np.argmin(np.fabs(vstc.times - time))
t_in_ms = vstc.times[t] * 1e3
print(' Found time slice: ', t_in_ms, 'ms')
if threshold == 'min':
threshold = vstcdata.min()
# jumeg_plot_stat_map starts here
output_file = None
title = None
annotate = True
draw_cross = True
resampling_interpolation = 'continuous'
bg_img = params_plot_img_with_bg['bg_img']
black_bg = params_plot_img_with_bg['black_bg']
bg_vmin = params_plot_img_with_bg['bg_vmin']
bg_vmax = params_plot_img_with_bg['bg_vmax']
stat_map_img = params_plot_img_with_bg['stat_map_img']
cbar_vmin = params_plot_img_with_bg['cbar_vmin']
cbar_vmax = params_plot_img_with_bg['cbar_vmax']
vmin = params_plot_img_with_bg['vmin']
vmax = params_plot_img_with_bg['vmax']
# noqa: E501
# dim the background
from nilearn.plotting.img_plotting import _plot_img_with_bg
from nilearn._utils import check_niimg_3d
stat_map_img_at_time_t = index_img(stat_map_img, t)
stat_map_img_at_time_t = check_niimg_3d(stat_map_img_at_time_t, dtype='auto')
display = _plot_img_with_bg(
img=stat_map_img_at_time_t, bg_img=bg_img, cut_coords=cut_coords,
output_file=output_file, display_mode=display_mode,
figure=figure, axes=axes, title=title, annotate=annotate,
draw_cross=draw_cross, black_bg=black_bg, threshold=threshold,
bg_vmin=bg_vmin, bg_vmax=bg_vmax, cmap=cmap, vmin=vmin, vmax=vmax,
colorbar=colorbar, cbar_vmin=cbar_vmin, cbar_vmax=cbar_vmax,
resampling_interpolation=resampling_interpolation, **kwargs)
vstc_plt = display
return vstc_plt
def remove_distance(coexpression, atlas, atlas_info=None, labels=None):
"""
Corrects for distance-dependent correlation effects in `coexpression`
Regresses Euclidean distance between regions in `atlas` from correlated
gene expression array `coexpression`. If `atlas_info` is provided different
connection types (e.g., cortex-cortex, cortex-subcortex, subcortex-
subcortex) will be residualized independently.
Parameters
----------
coexpression : (R x R) array_like
Correlated gene expression array, where `R` is the number of regions,
as generated with e.g., `numpy.corrcoef(expression)`.
atlas : niimg-like object
A parcellation image in MNI space, where each parcel is identified by a
unique integer ID
atlas_info : str or pandas.DataFrame, optional
Filepath to or pre-loaded dataframe containing information about
`atlas`. Must have at least columns 'id', 'hemisphere', and 'structure'
containing information mapping atlas IDs to hemisphere (i.e, "L", "R")
and broad structural class (i.e., "cortex", "subcortex", "cerebellum").
Default: None
labels : (N,) array_like, optional
If only a subset `N` of the ROIs in `atlas` were used to generate the
`coexpression` array this array should specify which to consider. Not
specifying this may cause a ValueError if `atlas` and `atlas_info` do
not match. Default: None
Returns
-------
residualized : (R, R) numpy.ndarray
Provided `coexpression` data residualized against spatial distance
between region pairs
"""
# load atlas_info, if provided
atlas = check_niimg_3d(atlas)
if atlas_info is not None:
atlas_info = utils.check_atlas_info(atlas, atlas_info, labels=labels)
if labels is not None and len(labels) != len(coexpression):
raise ValueError('Provided labels {} are a different length than '
'provided coexpression matrix of size {}. Please '
'confirm inputs and try again.'.format(
labels, coexpression.shape))
# check that provided coexpression array is symmetric
check_symmetric(coexpression, raise_exception=True)
# we'll do basic Euclidean distance correction for now
# TODO: implement gray matter volume / cortical surface path distance
centroids = utils.get_centroids(atlas, labels=labels)
dist = cdist(centroids, centroids, metric='euclidean')
corr_resid = np.zeros_like(coexpression)
triu_inds = np.triu_indices_from(coexpression, k=1)
# if no atlas_info, just residualize all correlations against distance
if atlas_info is None:
corr_resid[triu_inds] = _resid_dist(coexpression[triu_inds],
dist[triu_inds])
# otherwise, we can residualize the different connection types separately
else:
triu_inds = np.ravel_multi_index(triu_inds, corr_resid.shape)
coexpression, dist = coexpression.ravel(), dist.ravel()
types = ['cortex', 'subcortex']
for src, tar in itertools.combinations_with_replacement(types, 2):
# get indices of sources and targets
sources = np.where(atlas_info.structure == src)[0]
targets = np.where(atlas_info.structure == tar)[0]
inds = np.ravel_multi_index(np.ix_(sources, targets),
corr_resid.shape)
if src != tar: # e.g., cortex + subcortex
rev = np.ravel_multi_index(np.ix_(targets, sources),
corr_resid.shape)
inds = np.append(inds.ravel(), rev.ravel())
# find intersection of source / target indices + upper triangle
inds = np.intersect1d(triu_inds, inds)
back = np.unravel_index(inds, corr_resid.shape)
# residualize
corr_resid[back] = _resid_dist(coexpression[inds], dist[inds])
corr_resid = (corr_resid + corr_resid.T + np.eye(len(corr_resid)))
return corr_resid
def _fit(self, img, mask):
LGR.info(
"Performing dimensionality reduction based on GIFT "
"(https://trendscenter.org/software/gift/) and Li, Y. O., Adali, T., "
"& Calhoun, V. D. (2007). Estimating the number of independent components "
"for functional magnetic resonance imaging data. Human Brain Mapping, 28(11), "
"1251–1266. https://doi.org/10.1002/hbm.20359")
img = check_niimg_4d(img)
mask = check_niimg_3d(mask)
data = img.get_fdata()
mask = mask.get_fdata()
[n_x, n_y, n_z, n_timepoints] = data.shape
data_nib_V = np.reshape(data, (n_x * n_y * n_z, n_timepoints),
order="F")
mask_vec = np.reshape(mask, n_x * n_y * n_z, order="F")
X = data_nib_V[mask_vec == 1, :]
n_samples = np.sum(mask_vec)
self.scaler_ = StandardScaler(with_mean=True, with_std=True)
if self.normalize:
# TODO: determine if tedana is already normalizing before this
X = self.scaler_.fit_transform(X.T).T # This was X_sc
# X = ((X.T - X.T.mean(axis=0)) / X.T.std(axis=0)).T
LGR.info("Performing SVD on original data...")
V, eigenvalues = utils._icatb_svd(X, n_timepoints)
LGR.info("SVD done on original data")
# Reordering of values
eigenvalues = eigenvalues[::-1]
dataN = np.dot(X, V[:, ::-1])
# Potentially the small differences come from the different signs on V
# Using 12 gaussian components from middle, top and bottom gaussian
# components to determine the subsampling depth.
# Final subsampling depth is determined using median
kurt = kurtosis(dataN, axis=0, fisher=True)
kurt[kurt < 0] = 0
kurt = np.expand_dims(kurt, 1)
kurt[eigenvalues > np.mean(eigenvalues)] = 1000
idx_gauss = np.where(
((kurt[:, 0] < 0.3) & (kurt[:, 0] > 0)
& (eigenvalues > np.finfo(float).eps)
) == 1)[0] # NOTE: make sure np.where is giving us just one tuple
idx = np.array(idx_gauss[:]).T
dfs = np.sum(eigenvalues > np.finfo(float).eps) # degrees of freedom
minTp = 12
if len(idx) >= minTp:
middle = int(np.round(len(idx) / 2))
idx = np.hstack([idx[0:4], idx[middle - 1:middle + 3], idx[-4:]])
else:
minTp = np.min([minTp, dfs])
idx = np.arange(dfs - minTp, dfs)
idx = np.unique(idx)
# Estimate the subsampling depth for effectively i.i.d. samples
LGR.info(
"Estimating the subsampling depth for effective i.i.d samples...")
mask_ND = np.reshape(mask_vec, (n_x, n_y, n_z), order="F")
sub_depth = len(idx)
sub_iid_sp = np.zeros((sub_depth, ))
for i in range(sub_depth):
x_single = np.zeros(n_x * n_y * n_z)
x_single[mask_vec == 1] = dataN[:, idx[i]]
x_single = np.reshape(x_single, (n_x, n_y, n_z), order="F")
sub_iid_sp[i] = utils._est_indp_sp(x_single)[0] + 1
if i > 6:
tmp_sub_sp = sub_iid_sp[0:i]
tmp_sub_median = np.round(np.median(tmp_sub_sp))
if np.sum(tmp_sub_sp == tmp_sub_median) > 6:
sub_iid_sp = tmp_sub_sp
break
dim_n = x_single.ndim
sub_iid_sp_median = int(np.round(np.median(sub_iid_sp)))
if np.floor(np.power(n_samples / n_timepoints,
1 / dim_n)) < sub_iid_sp_median:
sub_iid_sp_median = int(
np.floor(np.power(n_samples / n_timepoints, 1 / dim_n)))
N = np.round(n_samples / np.power(sub_iid_sp_median, dim_n))
if sub_iid_sp_median != 1:
mask_s = utils._subsampling(mask_ND, sub_iid_sp_median)
mask_s_1d = np.reshape(mask_s, np.prod(mask_s.shape), order="F")
dat = np.zeros((int(np.sum(mask_s_1d)), n_timepoints))
LGR.info("Generating subsampled i.i.d. data...")
for i_vol in range(n_timepoints):
x_single = np.zeros(n_x * n_y * n_z)
x_single[mask_vec == 1] = X[:, i_vol]
x_single = np.reshape(x_single, (n_x, n_y, n_z), order="F")
dat0 = utils._subsampling(x_single, sub_iid_sp_median)
dat0 = np.reshape(dat0, np.prod(dat0.shape), order="F")
dat[:, i_vol] = dat0[mask_s_1d == 1]
# Perform Variance Normalization
temp_scaler = StandardScaler(with_mean=True, with_std=True)
dat = temp_scaler.fit_transform(dat.T).T
# (completed)
LGR.info("Performing SVD on subsampled i.i.d. data...")
V, eigenvalues = utils._icatb_svd(dat, n_timepoints)
LGR.info("SVD done on subsampled i.i.d. data")
eigenvalues = eigenvalues[::-1]
LGR.info("Effective number of i.i.d. samples %d" % N)
# Make eigen spectrum adjustment
LGR.info("Perform eigen spectrum adjustment ...")
eigenvalues = utils._eigensp_adj(eigenvalues, N, eigenvalues.shape[0])
# (completed)
if np.sum(np.imag(eigenvalues)):
raise ValueError(
"Invalid eigenvalue found for the subsampled data.")
# Correction on the ill-conditioned results (when tdim is large,
# some least significant eigenvalues become small negative numbers)
if eigenvalues[
np.real(eigenvalues) <= np.finfo(float).eps].shape[0] > 0:
eigenvalues[np.real(eigenvalues) <= np.finfo(float).eps] = np.min(
eigenvalues[np.real(eigenvalues) >= np.finfo(float).eps])
LGR.info("Estimating the dimensionality ...")
p = n_timepoints
aic = np.zeros(p - 1)
kic = np.zeros(p - 1)
mdl = np.zeros(p - 1)
for k_idx, k in enumerate(np.arange(1, p)):
LH = np.log(
np.prod(np.power(eigenvalues[k:], 1 / (p - k))) /
np.mean(eigenvalues[k:]))
mlh = 0.5 * N * (p - k) * LH
df = 1 + 0.5 * k * (2 * p - k + 1)
aic[k_idx] = (-2 * mlh) + (2 * df)
kic[k_idx] = (-2 * mlh) + (3 * df)
mdl[k_idx] = -mlh + (0.5 * df * np.log(N))
itc = np.row_stack([aic, kic, mdl])
dlap = np.diff(itc, axis=1)
# Calculate optimal number of components with each criterion
# AIC
a_aic = np.where(dlap[0, :] > 0)[0] + 1
if a_aic.size == 0:
n_aic = itc[0, :].shape[0]
else:
n_aic = a_aic[0]
# KIC
a_kic = np.where(dlap[1, :] > 0)[0] + 1
if a_kic.size == 0:
n_kic = itc[1, :].shape[0]
else:
n_kic = a_kic[0]
# MDL
a_mdl = np.where(dlap[2, :] > 0)[0] + 1
if a_mdl.size == 0:
n_mdl = itc[2, :].shape[0]
else:
n_mdl = a_mdl[0]
if self.criterion == "aic":
n_components = n_aic
elif self.criterion == "kic":
n_components = n_kic
elif self.criterion == "mdl":
n_components = n_mdl
LGR.info("Performing PCA")
# PCA with all possible components (the estimated selection is made after)
ppca = PCA(n_components=None,
svd_solver="full",
copy=False,
whiten=False)
ppca.fit(X)
# Get cumulative explained variance as components are added
cumsum_varexp = np.cumsum(ppca.explained_variance_ratio_)
# Calculate number of components for 90% varexp
n_comp_varexp_90 = np.where(cumsum_varexp >= 0.9)[0][0] + 1
# Calculate number of components for 95% varexp
n_comp_varexp_95 = np.where(cumsum_varexp >= 0.95)[0][0] + 1
LGR.info("Estimated number of components is %d" % n_components)
# Save results of each criterion into dictionaries
self.aic_ = {
"n_components": n_aic,
"value": aic,
"explained_variance_total": cumsum_varexp[n_aic - 1],
}
self.kic_ = {
"n_components": n_kic,
"value": kic,
"explained_variance_total": cumsum_varexp[n_kic - 1],
}
self.mdl_ = {
"n_components": n_mdl,
"value": mdl,
"explained_variance_total": cumsum_varexp[n_mdl - 1],
}
self.varexp_90_ = {
"n_components": n_comp_varexp_90,
"explained_variance_total": cumsum_varexp[n_comp_varexp_90 - 1],
}
self.varexp_95_ = {
"n_components": n_comp_varexp_95,
"explained_variance_total": cumsum_varexp[n_comp_varexp_95 - 1],
}
# Assign attributes from model
self.components_ = ppca.components_[:n_components, :]
self.explained_variance_ = ppca.explained_variance_[:n_components]
self.explained_variance_ratio_ = ppca.explained_variance_ratio_[:
n_components]
self.singular_values_ = ppca.singular_values_[:n_components]
self.mean_ = ppca.mean_
self.n_components_ = n_components
self.n_features_ = ppca.n_features_
self.n_samples_ = ppca.n_samples_
# Commenting out noise variance as it depends on the covariance of the estimation
# self.noise_variance_ = ppca.noise_variance_
component_maps = np.dot(np.dot(X, self.components_.T),
np.diag(1.0 / self.explained_variance_))
component_maps_3d = np.zeros((n_x * n_y * n_z, n_components))
component_maps_3d[mask_vec == 1, :] = component_maps
component_maps_3d = np.reshape(component_maps_3d,
(n_x, n_y, n_z, n_components),
order="F")
self.u_ = component_maps
self.u_nii_ = nib.Nifti1Image(component_maps_3d, img.affine,
img.header)