Python input_data.NiftiMasker方法代碼示例

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def _check_dict_init(dict_init, mask_img, n_components=None):
    if dict_init is not None:
        if isinstance(dict_init, np.ndarray):
            assert (dict_init.shape[1] == mask_img.get_data().sum())
            components = dict_init
        else:
            masker = NiftiMasker(smoothing_fwhm=None,
                                 mask_img=mask_img).fit()
            components = masker.transform(dict_init)
        if n_components is not None:
            return components[:n_components]
        else:
            return components
    else:
        return None 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def extract_data(nifti_file, mask_file, out_file, zscore, detrend, smoothing_fwmw):
    if mask_file is None:
        #whole brain, get coordinate info from nifti_file itself
        mask = nib.load(nifti_file.name)
    else:
        mask = nib.load(mask_file.name)
    affine = mask.get_affine()
    if mask_file is None:
        mask_data = mask.get_data()
        if mask_data.ndim == 4:
            #get mask in 3D
            img_data_type = mask.header.get_data_dtype()
            n_tr = mask_data.shape[3]
            mask_data = mask_data[:,:,:,n_tr//2].astype(bool)
            mask = nib.Nifti1Image(mask_data.astype(img_data_type), affine)
        else:
            mask_data = mask_data.astype(bool)
    else:
        mask_data = mask.get_data().astype(bool)

    #get voxel coordinates
    R = np.float64(np.argwhere(mask_data))

    #get scanner RAS coordinates based on voxel coordinates
    if affine is not []:
        R = (np.dot(affine[:3,:3], R.T) + affine[:3,3:4]).T

    #get ROI data, and run preprocessing
    nifti_masker = NiftiMasker(mask_img=mask, standardize=zscore, detrend=detrend, smoothing_fwhm=smoothing_fwmw)
    img = nib.load(nifti_file.name)
    all_images = np.float64(nifti_masker.fit_transform(img))
    data = all_images.T.copy()

    #save data
    subj_data = {'data': data, 'R': R}
    scipy.io.savemat(out_file.name, subj_data) 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def responders(l2_dir,
	roi="dsurqec_200micron_roi-dr",
	data_root="~/ni_data/ofM.dr",
	roi_root='/usr/share/mouse-brain-atlases',
	save_inplace=True,
	save_as='',
	):

	data_regex = "(?P<subject>.+)/.*?_tstat\.nii\.gz"
	data_path = "{data_root}/l2/{l2_dir}/".format(data_root=data_root, l2_dir=l2_dir)
	data_path = path.expanduser(data_path)
	roi_path = "{roi_root}/{roi}.nii".format(roi_root=roi_root, roi=roi)
	roi_path = path.expanduser(roi_path)

	data_find = DataFinder()
	data_find.inputs.root_paths = data_path
	data_find.inputs.match_regex = path.join(data_path,data_regex)
	found_data = data_find.run().outputs
	print(found_data)

	masker = NiftiMasker(mask_img=roi_path)
	voxeldf = pd.DataFrame({})
	for subject, data_file in zip(found_data.subject, found_data.out_paths):
		subject_data = {}
		print(subject, data_file)
		img = nib.load(data_file)
		img = masker.fit_transform(img)
		img = img.flatten()
		subject_data["subject"]=subject
		for i in img:
			voxel_data = deepcopy(subject_data)
			voxel_data["t"]=i
			df_ = pd.DataFrame(voxel_data, index=[None])
			voxeldf = pd.concat([voxeldf,df_])
	if save_inplace:
		voxeldf.to_csv('{}/ctx_responders.csv'.format(data_path))
	else:
		voxeldf.to_csv(path.abspath(path.expanduser(save_as))) 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def per_session(substitutions, roi_mask,
	filename_template="~/ni_data/ofM.dr/l1/{l1_dir}/sub-{subject}/ses-{session}/sub-{subject}_ses-{session}_task-{scan}_tstat.nii.gz",
	feature=[],
	atlas='',
	mapping='',
	):

	"""
	roi_mask : str
	Path to the ROI mask for which to select the t-values.

	roi_mask_normalize : str
	Path to a ROI mask by the mean of whose t-values to normalite the t-values in roi_mask.
	"""

	if isinstance(roi_mask,str):
		roi_mask = path.abspath(path.expanduser(roi_mask))
		roi_mask = nib.load(roi_mask)

	masker = NiftiMasker(mask_img=roi_mask)

	n_jobs = mp.cpu_count()-2
	dfs = Parallel(n_jobs=n_jobs, verbose=0, backend="threading")(map(delayed(roi_df),
		[filename_template]*len(substitutions),
		[masker]*len(substitutions),
		substitutions,
		feature*len(substitutions),
		[atlas]*len(substitutions),
		[mapping]*len(substitutions),
		))
	df = pd.concat(dfs)

	return df 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def mean(img_path, mask_path):
	"""Return the mean of the masked region of an image.
	"""
	mask = path.abspath(path.expanduser(mask_path))
	if mask_path.endswith("roi"):
		mask = loadmat(mask)["ROI"]
		while mask.ndim != 3:
			mask=mask[0]
		img_path = path.abspath(path.expanduser(img_path))
		img = nib.load(img_path)
	else:
		masker = NiftiMasker(mask_img=mask)
		roi_df(img_path,masker) 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def roi_data(img_path, masker,
	substitution={},
	exclude_zero=False,
	zero_threshold=0.1,
	):
	"""
	Return the mean of a Region of Interest (ROI) score.

	Parameters
	----------

	img_path : str
		Path to NIfTI file from which the ROI is to be extracted.
	makser : nilearn.NiftiMasker
		Nilearn `nifti1.Nifti1Image` object to use for masking the desired ROI.
	exclude_zero : bool, optional
		Whether to filter out zero values.
	substitution : dict, optional
		A dictionary with keys which include 'subject' and 'session'.
	zero_threshold : float, optional
		Absolute value below which values are to be considered zero.
	"""
	if substitution:
		img_path = img_path.format(**substitution)
	img_path = path.abspath(path.expanduser(img_path))
	img = nib.load(img_path)
	try:
		masked_data = masker.fit_transform(img)
	except:
		masker = path.abspath(path.expanduser(masker))
		masker = NiftiMasker(mask_img=masker)
		masked_data = masker.fit_transform(img)
	masked_data = masked_data.flatten()
	masked_data = masked_data[~np.isnan(masked_data)]
	if exclude_zero:
		masked_data = masked_data[np.abs(masked_data)>=zero_threshold]
	masked_mean = np.mean(masked_data)
	masked_median = np.median(masked_data)
	return masked_mean, masked_median 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def pattern_df(img_path, pattern,
	substitution=False,
	):
	"""
	Return a dataframe containing the `patern` score of `img_path` (i.e. the mean of the multiplication product).

	Parameters
	----------

	img_path : str
		Path to NIfTI file from which the ROI is to be extracted.
	pattern : nilearn.NiftiMasker
		Nilearn `nifti1.Nifti1Image` object to use for masking the desired ROI.
	substitution : dict, optional
		A dictionary with keys which include 'subject' and 'session'.

	"""

	subject_data={}
	if substitution:
		img_path = img_path.format(**substitution)
	img_path = path.abspath(path.expanduser(img_path))
	try:
		img = nib.load(img_path)
	except (FileNotFoundError, nib.py3k.FileNotFoundError):
		return pd.DataFrame({}), pd.DataFrame({})
	else:
		img_data = img.get_data()
		pattern_data = pattern.get_data()
		pattern_evaluation = img_data*pattern_data
		pattern_evaluation = pattern_evaluation.flatten()
		pattern_score = np.nanmean(pattern_evaluation)
		subject_data["session"]=substitution["session"]
		subject_data["subject"]=substitution["subject"]
		subject_data["t"]=pattern_score
		subject_data['feature'] = pattern.get_filename()
		df = pd.DataFrame(subject_data, index=[None])
		return df 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def get_signal(substitutions_a, substitutions_b,
	functional_file_template="~/ni_data/ofM.dr/preprocessing/{preprocessing_dir}/sub-{subject}/ses-{session}/func/sub-{subject}_ses-{session}_task-{scan}.nii.gz",
	mask="~/ni_data/templates/DSURQEc_200micron_bin.nii.gz",
	):

	mask = path.abspath(path.expanduser(mask))

	out_t_names = []
	out_cope_names = []
	out_varcb_names = []
	for substitution in substitutions_a+substitutions_b:
		ts_name = path.abspath(path.expanduser("{subject}_{session}.mat".format(**substitution)))
		out_t_name = path.abspath(path.expanduser("{subject}_{session}_tstat.nii.gz".format(**substitution)))
		out_cope_name = path.abspath(path.expanduser("{subject}_{session}_cope.nii.gz".format(**substitution)))
		out_varcb_name = path.abspath(path.expanduser("{subject}_{session}_varcb.nii.gz".format(**substitution)))
		out_t_names.append(out_t_name)
		out_cope_names.append(out_cope_name)
		out_varcb_names.append(out_varcb_name)
		functional_file = path.abspath(path.expanduser(functional_file_template.format(**substitution)))
		if not path.isfile(ts_name):
			masker = NiftiMasker(mask_img=mask)
			ts = masker.fit_transform(functional_file).T
			ts = np.mean(ts, axis=0)
			header = "/NumWaves 1\n/NumPoints 1490\n/PPheights 1.308540e+01 4.579890e+00\n\n/Matrix"
			np.savetxt(ts_name, ts, delimiter="\n", header=header, comments="")
		glm = fsl.GLM(in_file=functional_file, design=ts_name, output_type='NIFTI_GZ')
		glm.inputs.contrasts = path.abspath(path.expanduser("run0.con"))
		glm.inputs.out_t_name = out_t_name
		glm.inputs.out_cope = out_cope_name
		glm.inputs.out_varcb_name = out_varcb_name
		print(glm.cmdline)
		glm_run=glm.run()

	copemerge = fsl.Merge(dimension='t')
	varcopemerge = fsl.Merge(dimension='t') 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def apply_mask(self, mask, resample_mask_to_brain=False):
        """ Mask Brain_Data instance

        Note target data will be resampled into the same space as the mask. If you would like the mask
        resampled into the Brain_Data space, then set resample_mask_to_brain=True.

        Args:
            mask: (Brain_Data or nifti object) mask to apply to Brain_Data object.
            resample_mask_to_brain: (bool) Will resample mask to brain space before applying mask (default=False).

        Returns:
            masked: (Brain_Data) masked Brain_Data object

        """

        masked = deepcopy(self)
        mask = check_brain_data(mask)
        if not check_brain_data_is_single(mask):
            raise ValueError('Mask must be a single image')

        n_vox = len(self) if check_brain_data_is_single(self) else self.shape()[1]
        if resample_mask_to_brain: 
            mask = resample_to_img(mask.to_nifti(), masked.to_nifti())
            mask = check_brain_data(mask, masked.mask)

        nifti_masker = NiftiMasker(mask_img=mask.to_nifti()).fit()

        if n_vox == len(mask):
            if check_brain_data_is_single(masked):
                masked.data = masked.data[mask.data.astype(bool)]
            else:
                masked.data = masked.data[:, mask.data.astype(bool)]
        else:
            masked.data = nifti_masker.fit_transform(masked.to_nifti())
        masked.nifti_masker = nifti_masker
        if (len(masked.shape()) > 1) & (masked.shape()[0] == 1):
            masked.data = masked.data.flatten()
        return masked 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def __init__(self, brain_mask=None, output_dir=None):  # no scoring param
        # self.resource_folder = os.path.join(os.getcwd(),'resources')
        if output_dir is None:
            self.output_dir = os.path.join(os.getcwd())
        else:
            self.output_dir = output_dir

        if isinstance(brain_mask, str):
            brain_mask = nib.load(brain_mask)
        elif brain_mask is None:
            brain_mask = nib.load(resolve_mni_path(MNI_Template)['mask'])
        elif ~isinstance(brain_mask, nib.nifti1.Nifti1Image):
            raise ValueError("brain_mask is not a string or a nibabel instance")
        self.brain_mask = brain_mask
        self.nifti_masker = NiftiMasker(mask_img=self.brain_mask) 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def get_masker(mask):
    """
    Get an initialized, fitted nilearn Masker instance from passed argument.

    Parameters
    ----------
    mask : str, :class:`nibabel.nifti1.Nifti1Image`, or any nilearn Masker

    Returns
    -------
    masker : an initialized, fitted instance of a subclass of
        `nilearn.input_data.base_masker.BaseMasker`
    """
    if isinstance(mask, str):
        mask = nib.load(mask)

    if isinstance(mask, nib.nifti1.Nifti1Image):
        mask = NiftiMasker(mask)

    if not (hasattr(mask, 'transform') and hasattr(mask, 'inverse_transform')):
        raise ValueError("mask argument must be a string, a nibabel image,"
                         " or a Nilearn Masker instance.")

    # Fit the masker if needed
    if not hasattr(mask, 'mask_img_'):
        mask.fit()

    return mask 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def compute_fixed_effects(contrast_imgs, variance_imgs, mask=None,
                          precision_weighted=False):
    """Compute the fixed effects, given images of effects and variance

    Parameters
    ----------
    contrast_imgs: list of Nifti1Images or strings
              the input contrast images
    variance_imgs: list of Nifti1Images or strings
              the input variance images
    mask: Nifti1Image or NiftiMasker instance or None, optional,
              mask image. If None, it is recomputed from contrast_imgs
    precision_weighted: Bool, optional,
              Whether fixed effects estimates should be weighted by inverse
              variance or not. Defaults to False.

    Returns
    -------
    fixed_fx_contrast_img: Nifti1Image,
             the fixed effects contrast computed within the mask
    fixed_fx_variance_img: Nifti1Image,
             the fixed effects variance computed within the mask
    fixed_fx_t_img: Nifti1Image,
             the fixed effects t-test computed within the mask
    """
    if len(contrast_imgs) != len(variance_imgs):
        raise ValueError(
            'The number of contrast images (%d) '
            'differs from the number of variance images (%d). '
            % (len(contrast_imgs), len(variance_imgs))
        )

    if isinstance(mask, NiftiMasker):
        masker = mask.fit()
    elif mask is None:
        masker = NiftiMasker().fit(contrast_imgs)
    else:
        masker = NiftiMasker(mask_img=mask).fit()

    variances = masker.transform(variance_imgs)
    contrasts = masker.transform(contrast_imgs)

    (fixed_fx_contrast,
     fixed_fx_variance, fixed_fx_t) = _compute_fixed_effects_params(
            contrasts, variances, precision_weighted)

    fixed_fx_contrast_img = masker.inverse_transform(fixed_fx_contrast)
    fixed_fx_variance_img = masker.inverse_transform(fixed_fx_variance)
    fixed_fx_t_img = masker.inverse_transform(fixed_fx_t)
    return fixed_fx_contrast_img, fixed_fx_variance_img, fixed_fx_t_img 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def iter_threshold_volume(file_template, substitutions,
	mask_path='',
	threshold=60,
	threshold_is_percentile=True,
	invert_data=False,
	save_as='',
	):
	"""
	Return a `pandas.DataFrame` (optionally savable as `.csv`), containing the total volume of brain space exceeding a value.
	This function is an iteration wrapper of `samri.report.snr.threshold_volume()` using the SAMRI file_template/substitution model.

	Parameters
	----------

	file_template : str
		A formattable string containing as format fields keys present in the dictionaries passed to the `substitutions` variable.
	substitutions : list of dicts
		A list of dictionaries countaining formatting strings as keys and strings as values.
	masker : str or nilearn.NiftiMasker, optional
		Path to a NIfTI file containing a mask (1 and 0 values) or a `nilearn.NiftiMasker` object.
		NOT YET SUPPORTED!
	threshold : float, optional
		A float giving the voxel value threshold.
	threshold_is_percentile : bool, optional
		Whether `threshold` is to be interpreted not literally, but as a percentile of the data matrix.
		This is useful for making sure that the volume estimation is not susceptible to the absolute value range, but only the value distribution.
	save_as : str, optional
		Path to which to save the Pandas DataFrame.

	Returns
	-------

	pandas.DataFrame
		Pandas DataFrame object containing a row for each analyzed file and columns named 'Mean', 'Median', and (provided the respective key is present in the `sustitutions` variable) 'subject', 'session', 'task', and 'acquisition'.
	"""

	n_jobs = mp.cpu_count()-2
	iter_data = Parallel(n_jobs=n_jobs, verbose=0, backend="threading")(map(delayed(threshold_volume),
		[file_template]*len(substitutions),
		substitutions,
		[mask_path]*len(substitutions),
		[threshold]*len(substitutions),
		[threshold_is_percentile]*len(substitutions),
		))

	df_items = [
		('Volume', [i[1] for i in iter_data]),
		]
	df = pd.DataFrame.from_items(df_items)
	for field in ['subject','session','task','acquisition']:
		try:
			df[field] = [i[field] for i in substitutions]
		except KeyError:
			pass
	if save_as:
		save_as = path.abspath(path.expanduser(save_as))
		if save_as.lower().endswith('.csv'):
			df.to_csv(save_as)
		else:
			raise ValueError("Please specify an output path ending in any one of "+",".join((".csv",))+".")
	return df 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def significant_signal(data_path,
	substitution={},
	mask_path='',
	exclude_ones=False,
	):
	"""Return the mean and median inverse logarithm of a p-value map.

	Parameters
	----------

	data_path : str
		Path to a p-value map in NIfTI format.
	mask_path : str
		Path to a region of interest map in NIfTI format.
		THIS IS ALMOST ALWAYS REQUIRED, as NIfTI statistic images populate the whole 3D circumscribed space around your structure of interest,
		and commonly assign null values to the background.
		In an inverse logarithm computation, null corresponds to infinity, which can considerably bias the evaluation.
	substitution : dict
		Dictionary whose keys are format identifiers present in `data_path` and whose values are strings.

	Returns
	-------

	mean : float
	median : float
	"""

	if substitution:
		data_path = data_path.format(**substitution)
	data_path = path.abspath(path.expanduser(data_path))
	try:
		img = nib.load(data_path)
	except FileNotFoundError:
		return float('NaN'), float('NaN')
	if mask_path:
		if isinstance(mask_path, str):
			mask_path = path.abspath(path.expanduser(mask_path))
		masker = NiftiMasker(mask_img=mask_path)
		masked_data = masker.fit_transform(img).T
		data = masked_data[~np.isnan(masked_data)]
	else:
		data = img.get_data()
		data = data[~np.isnan(data)]
	# We interpret zero as the lowest p-value, and conservatively estimate it to be equal to just under half of the smallest value in the defined range
	if 0 in data:
		full_data = img.get_data()
		nonzero = full_data[np.nonzero(full_data)]
		data_min = np.min(nonzero)
		data_min = data_min*0.49
		if data_min <= 6.8663624751916035e-46:
			data_min *=2
		data[data == 0] = data_min
	if exclude_ones:
		data = data[data!=1]
	data = -np.log10(data)
	# We use np.ma.median() because life is complicated:
	# https://github.com/numpy/numpy/issues/7330
	median = np.ma.median(data, axis=None)
	mean = np.mean(data)

	return mean, median 

# 需要導入模塊: from nilearn import input_data [as 別名]
# 或者: from nilearn.input_data import NiftiMasker [as 別名]
def seed_based(substitutions, seed, roi,
	ts_file_template="~/ni_data/ofM.dr/preprocessing/{preprocessing_dir}/sub-{subject}/ses-{session}/func/sub-{subject}_ses-{session}_task-{task}.nii.gz",
	smoothing_fwhm=.3,
	detrend=True,
	standardize=True,
	low_pass=0.25,
	high_pass=0.004,
	tr=1.,
	save_results="",
	n_procs=2,
	cachedir='',
	):
	"""Plot a ROI t-values over the session timecourse

	roi_mask : str
	Path to the ROI mask for which to select the t-values.

	figure : {"per-participant", "per-voxel", "both"}
	At what level to resolve the t-values. Per-participant compares participant means, per-voxel compares all voxel values, both creates two plots covering the aforementioned cases.

	roi_mask_normalize : str
	Path to a ROI mask by the mean of whose t-values to normalite the t-values in roi_mask.
	"""

	if isinstance(roi,str):
		roi_mask = path.abspath(path.expanduser(roi))
	if isinstance(seed,str):
		seed_mask = path.abspath(path.expanduser(seed))

	seed_masker = NiftiMasker(
			mask_img=seed_mask,
			smoothing_fwhm=smoothing_fwhm,
			detrend=detrend,
			standardize=standardize,
			low_pass=low_pass,
			high_pass=high_pass,
			t_r=tr,
			memory=cachedir, memory_level=1, verbose=0
			)
	brain_masker = NiftiMasker(
			mask_img=roi_mask,
			smoothing_fwhm=smoothing_fwhm,
			detrend=detrend,
			standardize=standardize,
			low_pass=low_pass,
			high_pass=high_pass,
			t_r=tr,
			memory=cachedir, memory_level=1, verbose=0
			)


	fc_maps = Parallel(n_jobs=n_procs, verbose=0, backend="threading")(map(delayed(add_fc_roi_data),
		[ts_file_template]*len(substitutions),
		[seed_masker]*len(substitutions),
		[brain_masker]*len(substitutions),
		[True]*len(substitutions),
		[save_results]*len(substitutions),
		substitutions,
		))

	return fc_maps