def load_data(data, n_echos=None):
"""
Coerces input `data` files to required 3D array output
Parameters
----------
data : (X x Y x M x T) array_like or :obj:`list` of img_like
Input multi-echo data array, where `X` and `Y` are spatial dimensions,
`M` is the Z-spatial dimensions with all the input echos concatenated,
and `T` is time. A list of image-like objects (e.g., .nii) are
accepted, as well
n_echos : :obj:`int`, optional
Number of echos in provided data array. Only necessary if `data` is
array_like. Default: None
Returns
-------
fdata : (S x E x T) :obj:`numpy.ndarray`
Output data where `S` is samples, `E` is echos, and `T` is time
ref_img : :obj:`str` or :obj:`numpy.ndarray`
Filepath to reference image for saving output files or NIFTI-like array
"""
if n_echos is None:
raise ValueError(
'Number of echos must be specified. '
'Confirm that TE times are provided with the `-e` argument.')
if isinstance(data, list):
if len(data) == 1: # a z-concatenated file was provided
data = data[0]
elif len(data) == 2: # inviable -- need more than 2 echos
raise ValueError('Cannot run `tedana` with only two echos: '
'{}'.format(data))
else: # individual echo files were provided (surface or volumetric)
fdata = np.stack([utils.load_image(f) for f in data], axis=1)
ref_img = check_niimg(data[0])
ref_img.header.extensions = []
return np.atleast_3d(fdata), ref_img
img = check_niimg(data)
(nx, ny), nz = img.shape[:2], img.shape[2] // n_echos
fdata = utils.load_image(img.get_fdata().reshape(nx,
ny,
nz,
n_echos,
-1,
order='F'))
# create reference image
ref_img = img.__class__(np.zeros((nx, ny, nz, 1)),
affine=img.affine,
header=img.header,
extra=img.extra)
ref_img.header.extensions = []
ref_img.header.set_sform(ref_img.header.get_sform(), code=1)
return fdata, ref_img
def test_load_image():
fimg = nib.load(fnames[0])
exp_shape = (64350, 5)
# load filepath to image
assert utils.load_image(fnames[0]).shape == exp_shape
# load img_like object
assert utils.load_image(fimg).shape == exp_shape
# load array
assert utils.load_image(fimg.get_data()).shape == exp_shape
def test_load_image():
fimg = nib.load(fnames[0])
exp_shape = (64350, 5)
# load filepath to image
assert utils.load_image(fnames[0]).shape == exp_shape
# load img_like object
assert utils.load_image(fimg).shape == exp_shape
# load array
assert utils.load_image(fimg.get_data()).shape == exp_shape
def test_smoke_load_image():
"""
ensure that load_image returns reasonable objects with random inputs
in the correct format
Note: load_image could take in 3D or 4D array
"""
data_3d = np.random.random((100, 5, 20))
data_4d = np.random.random((100, 5, 20, 50))
assert utils.load_image(data_3d) is not None
assert utils.load_image(data_4d) is not None
def spatclust(img, min_cluster_size, threshold=None, index=None, mask=None):
"""
Spatially clusters `img`
Parameters
----------
img : str or img_like
Image file or object to be clustered
min_cluster_size : int
Minimum cluster size (in voxels)
threshold : float, optional
Whether to threshold `img` before clustering
index : array_like, optional
Whether to extract volumes from `img` for clustering
mask : (S,) array_like, optional
Boolean array for masking resultant data array
Returns
-------
clustered : :obj:`numpy.ndarray`
Boolean array of clustered (and thresholded) `img` data
"""
# we need a 4D image for `niimg.iter_img`, below
img = niimg.copy_img(check_niimg(img, atleast_4d=True))
# temporarily set voxel sizes to 1mm isotropic so that `min_cluster_size`
# represents the minimum number of voxels we want to be in a cluster,
# rather than the minimum size of the desired clusters in mm^3
if not np.all(np.abs(np.diag(img.affine)) == 1):
img.set_sform(np.sign(img.affine))
# grab desired volumes from provided image
if index is not None:
if not isinstance(index, list):
index = [index]
img = niimg.index_img(img, index)
# threshold image
if threshold is not None:
img = niimg.threshold_img(img, float(threshold))
clout = []
for subbrick in niimg.iter_img(img):
# `min_region_size` is not inclusive (as in AFNI's `3dmerge`)
# subtract one voxel to ensure we aren't hitting this thresholding issue
try:
clsts = connected_regions(subbrick,
min_region_size=int(min_cluster_size) -
1,
smoothing_fwhm=None,
extract_type='connected_components')[0]
# if no clusters are detected we get a TypeError; create a blank 4D
# image object as a placeholder instead
except TypeError:
clsts = niimg.new_img_like(subbrick,
np.zeros(subbrick.shape + (1, )))
# if multiple clusters detected, collapse into one volume
clout += [niimg.math_img('np.sum(a, axis=-1)', a=clsts)]
# convert back to data array and make boolean
clustered = utils.load_image(niimg.concat_imgs(clout).get_data()) != 0
# if mask provided, mask output
if mask is not None:
clustered = clustered[mask]
return clustered
def combine_tedana(tes,
data,
combmodes=('t2s', 'ste'),
mask=None,
overwrite=True):
""" Function based on tedana main workflow """
from tedana import utils, model, io, decay, combine
from scipy import stats
import numpy as np
import os
# ensure tes are in appropriate format
tes = [float(te) for te in tes]
n_echos = len(tes)
# coerce data to samples x echos x time array
if isinstance(data, str):
data = [data]
catd, ref_img = io.load_data(data, n_echos=n_echos)
n_samp, n_echos, n_vols = catd.shape
mask, masksum = utils.make_adaptive_mask(catd,
mask=mask,
minimum=False,
getsum=True)
# check if the t2s-map is already created first
base_name = data[0].replace('_echo-1',
'').replace('desc-preproc-hp',
'desc-preproc-hp-%s').replace(
'.nii', '').replace('.gz', '')
if not os.path.exists(base_name % 't2sv' + '.nii.gz') or overwrite:
t2s, s0, t2ss, s0s, t2sG, s0G = decay.fit_decay(
catd, tes, mask, masksum)
# set a hard cap for the T2* map
# anything that is 10x higher than the 99.5 %ile will be reset to 99.5 %ile
cap_t2s = stats.scoreatpercentile(t2s.flatten(),
99.5,
interpolation_method='lower')
t2s[t2s > cap_t2s * 10] = cap_t2s
# save
io.filewrite(t2s, base_name % 't2sv' + '.nii', ref_img, gzip=True)
io.filewrite(s0, base_name % 's0v' + '.nii', ref_img, gzip=True)
io.filewrite(t2ss, base_name % 't2ss' + '.nii', ref_img, gzip=True)
io.filewrite(s0s, base_name % 's0vs' + '.nii', ref_img, gzip=True)
io.filewrite(t2sG, base_name % 't2svG' + '.nii', ref_img, gzip=True)
io.filewrite(s0G, base_name % 's0vG' + '.nii', ref_img, gzip=True)
else:
t2sG = utils.load_image(base_name % 't2svG' + '.nii.gz')
t2s = utils.load_image(base_name % 't2sv' + '.nii.gz')
# optimally combine data
if 't2s' in combmodes:
print('Combining echos using optcomb...', end='')
ext = 'optcomb'
data_oc = combine.make_optcom(catd,
tes,
mask,
t2s=t2sG,
combmode='t2s')
# make sure to set all nan-values/inf to 0
data_oc[np.isinf(data_oc)] = 0
data_oc[np.isnan(data_oc)] = 0
print('Done, writing results...')
io.filewrite(data_oc, base_name % ext + '.nii', ref_img, gzip=True)
if 'ste' in combmodes:
print('Combining echos using optcomb...', end='')
ext = 'PAID'
data_oc = combine.make_optcom(catd,
tes,
mask,
t2s=t2sG,
combmode='ste')
# make sure to set all nan-values/inf to 0
data_oc[np.isinf(data_oc)] = 0
data_oc[np.isnan(data_oc)] = 0
io.filewrite(data_oc, base_name % ext + '.nii', ref_img, gzip=True)
print('Done, writing results...')
return 0
def tedana_workflow(data,
tes,
out_dir='.',
mask=None,
fittype='loglin',
combmode='t2s',
tedpca='mdl',
fixed_seed=42,
maxit=500,
maxrestart=10,
tedort=False,
gscontrol=None,
no_png=False,
png_cmap='coolwarm',
verbose=False,
low_mem=False,
debug=False,
quiet=False,
t2smap=None,
mixm=None,
ctab=None,
manacc=None):
"""
Run the "canonical" TE-Dependent ANAlysis workflow.
Parameters
----------
data : :obj:`str` or :obj:`list` of :obj:`str`
Either a single z-concatenated file (single-entry list or str) or a
list of echo-specific files, in ascending order.
tes : :obj:`list`
List of echo times associated with data in milliseconds.
out_dir : :obj:`str`, optional
Output directory.
mask : :obj:`str` or None, optional
Binary mask of voxels to include in TE Dependent ANAlysis. Must be
spatially aligned with `data`. If an explicit mask is not provided,
then Nilearn's compute_epi_mask function will be used to derive a mask
from the first echo's data.
fittype : {'loglin', 'curvefit'}, optional
Monoexponential fitting method. 'loglin' uses the the default linear
fit to the log of the data. 'curvefit' uses a monoexponential fit to
the raw data, which is slightly slower but may be more accurate.
Default is 'loglin'.
combmode : {'t2s'}, optional
Combination scheme for TEs: 't2s' (Posse 1999, default).
tedpca : {'kundu', 'kundu-stabilize', 'mdl', 'aic', 'kic'}, optional
Method with which to select components in TEDPCA. Default is 'mdl'.
tedort : :obj:`bool`, optional
Orthogonalize rejected components w.r.t. accepted ones prior to
denoising. Default is False.
gscontrol : {None, 't1c', 'gsr'} or :obj:`list`, optional
Perform additional denoising to remove spatially diffuse noise. Default
is None.
verbose : :obj:`bool`, optional
Generate intermediate and additional files. Default is False.
no_png : obj:'bool', optional
Do not generate .png plots and figures. Default is false.
png_cmap : obj:'str', optional
Name of a matplotlib colormap to be used when generating figures.
Cannot be used with --no-png. Default is 'coolwarm'.
t2smap : :obj:`str`, optional
Precalculated T2* map in the same space as the input data.
mixm : :obj:`str` or None, optional
File containing mixing matrix, to be used when re-running the workflow.
If not provided, ME-PCA and ME-ICA are done. Default is None.
ctab : :obj:`str` or None, optional
File containing component table from which to extract pre-computed
classifications, to be used with 'mixm' when re-running the workflow.
Default is None.
manacc : :obj:`list`, :obj:`str`, or None, optional
List of manually accepted components. Can be a list of the components,
a comma-separated string with component numbers, or None. Default is
None.
Other Parameters
----------------
fixed_seed : :obj:`int`, optional
Value passed to ``mdp.numx_rand.seed()``.
Set to a positive integer value for reproducible ICA results;
otherwise, set to -1 for varying results across calls.
maxit : :obj:`int`, optional
Maximum number of iterations for ICA. Default is 500.
maxrestart : :obj:`int`, optional
Maximum number of attempts for ICA. If ICA fails to converge, the
fixed seed will be updated and ICA will be run again. If convergence
is achieved before maxrestart attempts, ICA will finish early.
Default is 10.
low_mem : :obj:`bool`, optional
Enables low-memory processing, including the use of IncrementalPCA.
May increase workflow duration. Default is False.
debug : :obj:`bool`, optional
Whether to run in debugging mode or not. Default is False.
quiet : :obj:`bool`, optional
If True, suppresses logging/printing of messages. Default is False.
Notes
-----
This workflow writes out several files. For a complete list of the files
generated by this workflow, please visit
https://tedana.readthedocs.io/en/latest/outputs.html
"""
out_dir = op.abspath(out_dir)
if not op.isdir(out_dir):
os.mkdir(out_dir)
# boilerplate
basename = 'report'
extension = 'txt'
repname = op.join(out_dir, (basename + '.' + extension))
repex = op.join(out_dir, (basename + '*'))
previousreps = glob(repex)
previousreps.sort(reverse=True)
for f in previousreps:
previousparts = op.splitext(f)
newname = previousparts[0] + '_old' + previousparts[1]
os.rename(f, newname)
refname = op.join(out_dir, '_references.txt')
# create logfile name
basename = 'tedana_'
extension = 'tsv'
start_time = datetime.datetime.now().strftime('%Y-%m-%dT%H%M%S')
logname = op.join(out_dir, (basename + start_time + '.' + extension))
# set logging format
log_formatter = logging.Formatter(
'%(asctime)s\t%(name)-12s\t%(levelname)-8s\t%(message)s',
datefmt='%Y-%m-%dT%H:%M:%S')
text_formatter = logging.Formatter('%(message)s')
# set up logging file and open it for writing
log_handler = logging.FileHandler(logname)
log_handler.setFormatter(log_formatter)
# Removing handlers after basicConfig doesn't work, so we use filters
# for the relevant handlers themselves.
log_handler.addFilter(ContextFilter())
sh = logging.StreamHandler()
sh.addFilter(ContextFilter())
if quiet:
logging.basicConfig(level=logging.WARNING, handlers=[log_handler, sh])
elif debug:
logging.basicConfig(level=logging.DEBUG, handlers=[log_handler, sh])
else:
logging.basicConfig(level=logging.INFO, handlers=[log_handler, sh])
# Loggers for report and references
rep_handler = logging.FileHandler(repname)
rep_handler.setFormatter(text_formatter)
ref_handler = logging.FileHandler(refname)
ref_handler.setFormatter(text_formatter)
RepLGR.setLevel(logging.INFO)
RepLGR.addHandler(rep_handler)
RepLGR.setLevel(logging.INFO)
RefLGR.addHandler(ref_handler)
LGR.info('Using output directory: {}'.format(out_dir))
# ensure tes are in appropriate format
tes = [float(te) for te in tes]
n_echos = len(tes)
# Coerce gscontrol to list
if not isinstance(gscontrol, list):
gscontrol = [gscontrol]
LGR.info('Loading input data: {}'.format([f for f in data]))
catd, ref_img = io.load_data(data, n_echos=n_echos)
n_samp, n_echos, n_vols = catd.shape
LGR.debug('Resulting data shape: {}'.format(catd.shape))
if no_png and (png_cmap != 'coolwarm'):
LGR.warning('Overriding --no-png since --png-cmap provided.')
no_png = False
# check if TR is 0
img_t_r = ref_img.header.get_zooms()[-1]
if img_t_r == 0 and not no_png:
raise IOError(
'Dataset has a TR of 0. This indicates incorrect'
' header information. To correct this, we recommend'
' using this snippet:'
'\n'
'https://gist.github.com/jbteves/032c87aeb080dd8de8861cb151bff5d6'
'\n'
'to correct your TR to the value it should be.')
if mixm is not None and op.isfile(mixm):
mixm = op.abspath(mixm)
# Allow users to re-run on same folder
if mixm != op.join(out_dir, 'ica_mixing.tsv'):
shutil.copyfile(mixm, op.join(out_dir, 'ica_mixing.tsv'))
shutil.copyfile(mixm, op.join(out_dir, op.basename(mixm)))
elif mixm is not None:
raise IOError('Argument "mixm" must be an existing file.')
if ctab is not None and op.isfile(ctab):
ctab = op.abspath(ctab)
# Allow users to re-run on same folder
if ctab != op.join(out_dir, 'ica_decomposition.json'):
shutil.copyfile(ctab, op.join(out_dir, 'ica_decomposition.json'))
shutil.copyfile(ctab, op.join(out_dir, op.basename(ctab)))
elif ctab is not None:
raise IOError('Argument "ctab" must be an existing file.')
if isinstance(manacc, str):
manacc = [int(comp) for comp in manacc.split(',')]
if ctab and not mixm:
LGR.warning('Argument "ctab" requires argument "mixm".')
ctab = None
elif manacc is not None and not mixm:
LGR.warning('Argument "manacc" requires argument "mixm".')
manacc = None
if t2smap is not None and op.isfile(t2smap):
t2smap = op.abspath(t2smap)
# Allow users to re-run on same folder
if t2smap != op.join(out_dir, 't2sv.nii.gz'):
shutil.copyfile(t2smap, op.join(out_dir, 't2sv.nii.gz'))
shutil.copyfile(t2smap, op.join(out_dir, op.basename(t2smap)))
elif t2smap is not None:
raise IOError('Argument "t2smap" must be an existing file.')
RepLGR.info("TE-dependence analysis was performed on input data.")
if mask and not t2smap:
# TODO: add affine check
LGR.info('Using user-defined mask')
RepLGR.info("A user-defined mask was applied to the data.")
elif t2smap and not mask:
LGR.info('Using user-defined T2* map to generate mask')
t2s_limited = utils.load_image(t2smap)
t2s_full = t2s_limited.copy()
mask = (t2s_limited != 0).astype(int)
elif t2smap and mask:
LGR.info('Combining user-defined mask and T2* map to generate mask')
t2s_limited = utils.load_image(t2smap)
t2s_full = t2s_limited.copy()
mask = utils.load_image(mask)
mask[t2s_limited == 0] = 0 # reduce mask based on T2* map
else:
LGR.info('Computing EPI mask from first echo')
first_echo_img = io.new_nii_like(ref_img, catd[:, 0, :])
mask = compute_epi_mask(first_echo_img)
RepLGR.info("An initial mask was generated from the first echo using "
"nilearn's compute_epi_mask function.")
mask, masksum = utils.make_adaptive_mask(catd, mask=mask, getsum=True)
LGR.debug('Retaining {}/{} samples'.format(mask.sum(), n_samp))
io.filewrite(masksum, op.join(out_dir, 'adaptive_mask.nii'), ref_img)
if t2smap is None:
LGR.info('Computing T2* map')
t2s_limited, s0_limited, t2s_full, s0_full = decay.fit_decay(
catd, tes, mask, masksum, fittype)
# set a hard cap for the T2* map
# anything that is 10x higher than the 99.5 %ile will be reset to 99.5 %ile
cap_t2s = stats.scoreatpercentile(t2s_limited.flatten(),
99.5,
interpolation_method='lower')
LGR.debug('Setting cap on T2* map at {:.5f}'.format(cap_t2s * 10))
t2s_limited[t2s_limited > cap_t2s * 10] = cap_t2s
io.filewrite(t2s_limited, op.join(out_dir, 't2sv.nii'), ref_img)
io.filewrite(s0_limited, op.join(out_dir, 's0v.nii'), ref_img)
if verbose:
io.filewrite(t2s_full, op.join(out_dir, 't2svG.nii'), ref_img)
io.filewrite(s0_full, op.join(out_dir, 's0vG.nii'), ref_img)
# optimally combine data
data_oc = combine.make_optcom(catd,
tes,
mask,
t2s=t2s_full,
combmode=combmode)
# regress out global signal unless explicitly not desired
if 'gsr' in gscontrol:
catd, data_oc = gsc.gscontrol_raw(catd,
data_oc,
n_echos,
ref_img,
out_dir=out_dir)
if mixm is None:
# Identify and remove thermal noise from data
dd, n_components = decomposition.tedpca(catd,
data_oc,
combmode,
mask,
t2s_limited,
t2s_full,
ref_img,
tes=tes,
algorithm=tedpca,
kdaw=10.,
rdaw=1.,
out_dir=out_dir,
verbose=verbose,
low_mem=low_mem)
mmix_orig = decomposition.tedica(dd, n_components, fixed_seed, maxit,
maxrestart)
if verbose:
io.filewrite(utils.unmask(dd, mask),
op.join(out_dir, 'ts_OC_whitened.nii.gz'), ref_img)
LGR.info('Making second component selection guess from ICA results')
# Estimate betas and compute selection metrics for mixing matrix
# generated from dimensionally reduced data using full data (i.e., data
# with thermal noise)
comptable, metric_maps, betas, mmix = metrics.dependence_metrics(
catd,
data_oc,
mmix_orig,
t2s_limited,
tes,
ref_img,
reindex=True,
label='meica_',
out_dir=out_dir,
algorithm='kundu_v2',
verbose=verbose)
comp_names = [
io.add_decomp_prefix(comp,
prefix='ica',
max_value=comptable.index.max())
for comp in comptable.index.values
]
mixing_df = pd.DataFrame(data=mmix, columns=comp_names)
mixing_df.to_csv(op.join(out_dir, 'ica_mixing.tsv'),
sep='\t',
index=False)
betas_oc = utils.unmask(computefeats2(data_oc, mmix, mask), mask)
io.filewrite(betas_oc, op.join(out_dir, 'ica_components.nii.gz'),
ref_img)
comptable = metrics.kundu_metrics(comptable, metric_maps)
comptable = selection.kundu_selection_v2(comptable, n_echos, n_vols)
else:
LGR.info('Using supplied mixing matrix from ICA')
mmix_orig = pd.read_table(op.join(out_dir, 'ica_mixing.tsv')).values
if ctab is None:
comptable, metric_maps, betas, mmix = metrics.dependence_metrics(
catd,
data_oc,
mmix_orig,
t2s_limited,
tes,
ref_img,
label='meica_',
out_dir=out_dir,
algorithm='kundu_v2',
verbose=verbose)
comptable = metrics.kundu_metrics(comptable, metric_maps)
comptable = selection.kundu_selection_v2(comptable, n_echos,
n_vols)
else:
mmix = mmix_orig.copy()
comptable = io.load_comptable(ctab)
if manacc is not None:
comptable = selection.manual_selection(comptable, acc=manacc)
betas_oc = utils.unmask(computefeats2(data_oc, mmix, mask), mask)
io.filewrite(betas_oc, op.join(out_dir, 'ica_components.nii.gz'),
ref_img)
# Save decomposition
comptable[
'Description'] = 'ICA fit to dimensionally-reduced optimally combined data.'
mmix_dict = {}
mmix_dict['Method'] = ('Independent components analysis with FastICA '
'algorithm implemented by sklearn. Components '
'are sorted by Kappa in descending order. '
'Component signs are flipped to best match the '
'data.')
io.save_comptable(comptable,
op.join(out_dir, 'ica_decomposition.json'),
label='ica',
metadata=mmix_dict)
if comptable[comptable.classification == 'accepted'].shape[0] == 0:
LGR.warning('No BOLD components detected! Please check data and '
'results!')
mmix_orig = mmix.copy()
if tedort:
acc_idx = comptable.loc[~comptable.classification.str.
contains('rejected')].index.values
rej_idx = comptable.loc[comptable.classification.str.contains(
'rejected')].index.values
acc_ts = mmix[:, acc_idx]
rej_ts = mmix[:, rej_idx]
betas = np.linalg.lstsq(acc_ts, rej_ts, rcond=None)[0]
pred_rej_ts = np.dot(acc_ts, betas)
resid = rej_ts - pred_rej_ts
mmix[:, rej_idx] = resid
comp_names = [
io.add_decomp_prefix(comp,
prefix='ica',
max_value=comptable.index.max())
for comp in comptable.index.values
]
mixing_df = pd.DataFrame(data=mmix, columns=comp_names)
mixing_df.to_csv(op.join(out_dir, 'ica_orth_mixing.tsv'),
sep='\t',
index=False)
RepLGR.info("Rejected components' time series were then "
"orthogonalized with respect to accepted components' time "
"series.")
io.writeresults(data_oc,
mask=mask,
comptable=comptable,
mmix=mmix,
n_vols=n_vols,
ref_img=ref_img,
out_dir=out_dir)
if 't1c' in gscontrol:
gsc.gscontrol_mmix(data_oc,
mmix,
mask,
comptable,
ref_img,
out_dir=out_dir)
if verbose:
io.writeresults_echoes(catd,
mmix,
mask,
comptable,
ref_img,
out_dir=out_dir)
if not no_png:
LGR.info('Making figures folder with static component maps and '
'timecourse plots.')
# make figure folder first
if not op.isdir(op.join(out_dir, 'figures')):
os.mkdir(op.join(out_dir, 'figures'))
viz.write_comp_figs(data_oc,
mask=mask,
comptable=comptable,
mmix=mmix_orig,
ref_img=ref_img,
out_dir=op.join(out_dir, 'figures'),
png_cmap=png_cmap)
LGR.info('Making Kappa vs Rho scatter plot')
viz.write_kappa_scatter(comptable=comptable,
out_dir=op.join(out_dir, 'figures'))
LGR.info('Making Kappa/Rho scree plot')
viz.write_kappa_scree(comptable=comptable,
out_dir=op.join(out_dir, 'figures'))
LGR.info('Making overall summary figure')
viz.write_summary_fig(comptable=comptable,
out_dir=op.join(out_dir, 'figures'))
LGR.info('Workflow completed')
RepLGR.info("This workflow used numpy (Van Der Walt, Colbert, & "
"Varoquaux, 2011), scipy (Jones et al., 2001), pandas "
"(McKinney, 2010), scikit-learn (Pedregosa et al., 2011), "
"nilearn, and nibabel (Brett et al., 2019).")
RefLGR.info(
"Van Der Walt, S., Colbert, S. C., & Varoquaux, G. (2011). The "
"NumPy array: a structure for efficient numerical computation. "
"Computing in Science & Engineering, 13(2), 22.")
RefLGR.info("Jones E, Oliphant E, Peterson P, et al. SciPy: Open Source "
"Scientific Tools for Python, 2001-, http://www.scipy.org/")
RefLGR.info("McKinney, W. (2010, June). Data structures for statistical "
"computing in python. In Proceedings of the 9th Python in "
"Science Conference (Vol. 445, pp. 51-56).")
RefLGR.info("Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., "
"Thirion, B., Grisel, O., ... & Vanderplas, J. (2011). "
"Scikit-learn: Machine learning in Python. Journal of machine "
"learning research, 12(Oct), 2825-2830.")
RefLGR.info("Brett, M., Markiewicz, C. J., Hanke, M., Côté, M.-A., "
"Cipollini, B., McCarthy, P., … freec84. (2019, May 28). "
"nipy/nibabel. Zenodo. http://doi.org/10.5281/zenodo.3233118")
RepLGR.info("This workflow also used the Dice similarity index "
"(Dice, 1945; Sørensen, 1948).")
RefLGR.info("Dice, L. R. (1945). Measures of the amount of ecologic "
"association between species. Ecology, 26(3), 297-302.")
RefLGR.info(
"Sørensen, T. J. (1948). A method of establishing groups of "
"equal amplitude in plant sociology based on similarity of "
"species content and its application to analyses of the "
"vegetation on Danish commons. I kommission hos E. Munksgaard.")
with open(repname, 'r') as fo:
report = [line.rstrip() for line in fo.readlines()]
report = ' '.join(report)
with open(refname, 'r') as fo:
reference_list = sorted(list(set(fo.readlines())))
references = '\n'.join(reference_list)
report += '\n\nReferences\n' + references
with open(repname, 'w') as fo:
fo.write(report)
os.remove(refname)
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
def tedana_workflow(data,
tes,
out_dir='.',
mask=None,
convention='bids',
prefix='',
fittype='loglin',
combmode='t2s',
tedpca='mdl',
fixed_seed=42,
maxit=500,
maxrestart=10,
tedort=False,
gscontrol=None,
no_reports=False,
png_cmap='coolwarm',
verbose=False,
low_mem=False,
debug=False,
quiet=False,
t2smap=None,
mixm=None,
ctab=None,
manacc=None):
"""
Run the "canonical" TE-Dependent ANAlysis workflow.
Parameters
----------
data : :obj:`str` or :obj:`list` of :obj:`str`
Either a single z-concatenated file (single-entry list or str) or a
list of echo-specific files, in ascending order.
tes : :obj:`list`
List of echo times associated with data in milliseconds.
out_dir : :obj:`str`, optional
Output directory.
mask : :obj:`str` or None, optional
Binary mask of voxels to include in TE Dependent ANAlysis. Must be
spatially aligned with `data`. If an explicit mask is not provided,
then Nilearn's compute_epi_mask function will be used to derive a mask
from the first echo's data.
fittype : {'loglin', 'curvefit'}, optional
Monoexponential fitting method. 'loglin' uses the the default linear
fit to the log of the data. 'curvefit' uses a monoexponential fit to
the raw data, which is slightly slower but may be more accurate.
Default is 'loglin'.
combmode : {'t2s'}, optional
Combination scheme for TEs: 't2s' (Posse 1999, default).
tedpca : {'mdl', 'aic', 'kic', 'kundu', 'kundu-stabilize', float}, optional
Method with which to select components in TEDPCA.
If a float is provided, then it is assumed to represent percentage of variance
explained (0-1) to retain from PCA.
Default is 'mdl'.
tedort : :obj:`bool`, optional
Orthogonalize rejected components w.r.t. accepted ones prior to
denoising. Default is False.
gscontrol : {None, 'mir', 'gsr'} or :obj:`list`, optional
Perform additional denoising to remove spatially diffuse noise. Default
is None.
verbose : :obj:`bool`, optional
Generate intermediate and additional files. Default is False.
no_reports : obj:'bool', optional
Do not generate .html reports and .png plots. Default is false such
that reports are generated.
png_cmap : obj:'str', optional
Name of a matplotlib colormap to be used when generating figures.
Cannot be used with --no-png. Default is 'coolwarm'.
t2smap : :obj:`str`, optional
Precalculated T2* map in the same space as the input data. Values in
the map must be in seconds.
mixm : :obj:`str` or None, optional
File containing mixing matrix, to be used when re-running the workflow.
If not provided, ME-PCA and ME-ICA are done. Default is None.
ctab : :obj:`str` or None, optional
File containing component table from which to extract pre-computed
classifications, to be used with 'mixm' when re-running the workflow.
Default is None.
manacc : :obj:`list` of :obj:`int` or None, optional
List of manually accepted components. Can be a list of the components
numbers or None.
If provided, this parameter requires ``mixm`` and ``ctab`` to be provided as well.
Default is None.
Other Parameters
----------------
fixed_seed : :obj:`int`, optional
Value passed to ``mdp.numx_rand.seed()``.
Set to a positive integer value for reproducible ICA results;
otherwise, set to -1 for varying results across calls.
maxit : :obj:`int`, optional
Maximum number of iterations for ICA. Default is 500.
maxrestart : :obj:`int`, optional
Maximum number of attempts for ICA. If ICA fails to converge, the
fixed seed will be updated and ICA will be run again. If convergence
is achieved before maxrestart attempts, ICA will finish early.
Default is 10.
low_mem : :obj:`bool`, optional
Enables low-memory processing, including the use of IncrementalPCA.
May increase workflow duration. Default is False.
debug : :obj:`bool`, optional
Whether to run in debugging mode or not. Default is False.
quiet : :obj:`bool`, optional
If True, suppresses logging/printing of messages. Default is False.
Notes
-----
This workflow writes out several files. For a complete list of the files
generated by this workflow, please visit
https://tedana.readthedocs.io/en/latest/outputs.html
"""
out_dir = op.abspath(out_dir)
if not op.isdir(out_dir):
os.mkdir(out_dir)
# boilerplate
basename = 'report'
extension = 'txt'
repname = op.join(out_dir, (basename + '.' + extension))
repex = op.join(out_dir, (basename + '*'))
previousreps = glob(repex)
previousreps.sort(reverse=True)
for f in previousreps:
previousparts = op.splitext(f)
newname = previousparts[0] + '_old' + previousparts[1]
os.rename(f, newname)
refname = op.join(out_dir, '_references.txt')
# create logfile name
basename = 'tedana_'
extension = 'tsv'
start_time = datetime.datetime.now().strftime('%Y-%m-%dT%H%M%S')
logname = op.join(out_dir, (basename + start_time + '.' + extension))
utils.setup_loggers(logname, repname, refname, quiet=quiet, debug=debug)
LGR.info('Using output directory: {}'.format(out_dir))
# ensure tes are in appropriate format
tes = [float(te) for te in tes]
n_echos = len(tes)
# Coerce gscontrol to list
if not isinstance(gscontrol, list):
gscontrol = [gscontrol]
# Check value of tedpca *if* it is a float
tedpca = check_tedpca_value(tedpca, is_parser=False)
LGR.info('Loading input data: {}'.format([f for f in data]))
catd, ref_img = io.load_data(data, n_echos=n_echos)
io_generator = io.OutputGenerator(
ref_img,
convention=convention,
out_dir=out_dir,
prefix=prefix,
config="auto",
verbose=verbose,
)
n_samp, n_echos, n_vols = catd.shape
LGR.debug('Resulting data shape: {}'.format(catd.shape))
# check if TR is 0
img_t_r = io_generator.reference_img.header.get_zooms()[-1]
if img_t_r == 0:
raise IOError(
'Dataset has a TR of 0. This indicates incorrect'
' header information. To correct this, we recommend'
' using this snippet:'
'\n'
'https://gist.github.com/jbteves/032c87aeb080dd8de8861cb151bff5d6'
'\n'
'to correct your TR to the value it should be.')
if mixm is not None and op.isfile(mixm):
mixm = op.abspath(mixm)
# Allow users to re-run on same folder
mixing_name = io_generator.get_name("ICA mixing tsv")
if mixm != mixing_name:
shutil.copyfile(mixm, mixing_name)
shutil.copyfile(mixm,
op.join(io_generator.out_dir, op.basename(mixm)))
elif mixm is not None:
raise IOError('Argument "mixm" must be an existing file.')
if ctab is not None and op.isfile(ctab):
ctab = op.abspath(ctab)
# Allow users to re-run on same folder
metrics_name = io_generator.get_name("ICA metrics tsv")
if ctab != metrics_name:
shutil.copyfile(ctab, metrics_name)
shutil.copyfile(ctab,
op.join(io_generator.out_dir, op.basename(ctab)))
elif ctab is not None:
raise IOError('Argument "ctab" must be an existing file.')
if ctab and not mixm:
LGR.warning('Argument "ctab" requires argument "mixm".')
ctab = None
elif manacc is not None and (not mixm or not ctab):
LGR.warning('Argument "manacc" requires arguments "mixm" and "ctab".')
manacc = None
elif manacc is not None:
# coerce to list of integers
manacc = [int(m) for m in manacc]
if t2smap is not None and op.isfile(t2smap):
t2smap_file = io_generator.get_name('t2star img')
t2smap = op.abspath(t2smap)
# Allow users to re-run on same folder
if t2smap != t2smap_file:
shutil.copyfile(t2smap, t2smap_file)
elif t2smap is not None:
raise IOError('Argument "t2smap" must be an existing file.')
RepLGR.info("TE-dependence analysis was performed on input data.")
if mask and not t2smap:
# TODO: add affine check
LGR.info('Using user-defined mask')
RepLGR.info("A user-defined mask was applied to the data.")
elif t2smap and not mask:
LGR.info('Using user-defined T2* map to generate mask')
t2s_limited_sec = utils.load_image(t2smap)
t2s_limited = utils.sec2millisec(t2s_limited_sec)
t2s_full = t2s_limited.copy()
mask = (t2s_limited != 0).astype(int)
elif t2smap and mask:
LGR.info('Combining user-defined mask and T2* map to generate mask')
t2s_limited_sec = utils.load_image(t2smap)
t2s_limited = utils.sec2millisec(t2s_limited_sec)
t2s_full = t2s_limited.copy()
mask = utils.load_image(mask)
mask[t2s_limited == 0] = 0 # reduce mask based on T2* map
else:
LGR.info('Computing EPI mask from first echo')
first_echo_img = io.new_nii_like(io_generator.reference_img,
catd[:, 0, :])
mask = compute_epi_mask(first_echo_img)
RepLGR.info("An initial mask was generated from the first echo using "
"nilearn's compute_epi_mask function.")
# Create an adaptive mask with at least 1 good echo, for denoising
mask_denoise, masksum_denoise = utils.make_adaptive_mask(
catd,
mask=mask,
getsum=True,
threshold=1,
)
LGR.debug('Retaining {}/{} samples for denoising'.format(
mask_denoise.sum(), n_samp))
io_generator.save_file(masksum_denoise, "adaptive mask img")
# Create an adaptive mask with at least 3 good echoes, for classification
masksum_clf = masksum_denoise.copy()
masksum_clf[masksum_clf < 3] = 0
mask_clf = masksum_clf.astype(bool)
RepLGR.info(
"A two-stage masking procedure was applied, in which a liberal mask "
"(including voxels with good data in at least the first echo) was used for "
"optimal combination, T2*/S0 estimation, and denoising, while a more conservative mask "
"(restricted to voxels with good data in at least the first three echoes) was used for "
"the component classification procedure.")
LGR.debug('Retaining {}/{} samples for classification'.format(
mask_clf.sum(), n_samp))
if t2smap is None:
LGR.info('Computing T2* map')
t2s_limited, s0_limited, t2s_full, s0_full = decay.fit_decay(
catd, tes, mask_denoise, masksum_denoise, fittype)
# set a hard cap for the T2* map
# anything that is 10x higher than the 99.5 %ile will be reset to 99.5 %ile
cap_t2s = stats.scoreatpercentile(t2s_full.flatten(),
99.5,
interpolation_method='lower')
LGR.debug('Setting cap on T2* map at {:.5f}s'.format(
utils.millisec2sec(cap_t2s)))
t2s_full[t2s_full > cap_t2s * 10] = cap_t2s
io_generator.save_file(utils.millisec2sec(t2s_full), 't2star img')
io_generator.save_file(s0_full, 's0 img')
if verbose:
io_generator.save_file(utils.millisec2sec(t2s_limited),
'limited t2star img')
io_generator.save_file(s0_limited, 'limited s0 img')
# optimally combine data
data_oc = combine.make_optcom(catd,
tes,
masksum_denoise,
t2s=t2s_full,
combmode=combmode)
# regress out global signal unless explicitly not desired
if 'gsr' in gscontrol:
catd, data_oc = gsc.gscontrol_raw(catd, data_oc, n_echos, io_generator)
fout = io_generator.save_file(data_oc, 'combined img')
LGR.info('Writing optimally combined data set: {}'.format(fout))
if mixm is None:
# Identify and remove thermal noise from data
dd, n_components = decomposition.tedpca(catd,
data_oc,
combmode,
mask_clf,
masksum_clf,
t2s_full,
io_generator,
tes=tes,
algorithm=tedpca,
kdaw=10.,
rdaw=1.,
verbose=verbose,
low_mem=low_mem)
if verbose:
io_generator.save_file(utils.unmask(dd, mask_clf), 'whitened img')
# Perform ICA, calculate metrics, and apply decision tree
# Restart when ICA fails to converge or too few BOLD components found
keep_restarting = True
n_restarts = 0
seed = fixed_seed
while keep_restarting:
mmix, seed = decomposition.tedica(dd,
n_components,
seed,
maxit,
maxrestart=(maxrestart -
n_restarts))
seed += 1
n_restarts = seed - fixed_seed
# Estimate betas and compute selection metrics for mixing matrix
# generated from dimensionally reduced data using full data (i.e., data
# with thermal noise)
LGR.info(
'Making second component selection guess from ICA results')
required_metrics = [
'kappa', 'rho', 'countnoise', 'countsigFT2', 'countsigFS0',
'dice_FT2', 'dice_FS0', 'signal-noise_t', 'variance explained',
'normalized variance explained', 'd_table_score'
]
comptable = metrics.collect.generate_metrics(
catd,
data_oc,
mmix,
masksum_clf,
tes,
io_generator,
'ICA',
metrics=required_metrics,
)
comptable, metric_metadata = selection.kundu_selection_v2(
comptable, n_echos, n_vols)
n_bold_comps = comptable[comptable.classification ==
'accepted'].shape[0]
if (n_restarts < maxrestart) and (n_bold_comps == 0):
LGR.warning("No BOLD components found. Re-attempting ICA.")
elif (n_bold_comps == 0):
LGR.warning(
"No BOLD components found, but maximum number of restarts reached."
)
keep_restarting = False
else:
keep_restarting = False
RepLGR.disabled = True # Disable the report to avoid duplicate text
RepLGR.disabled = False # Re-enable the report after the while loop is escaped
else:
LGR.info('Using supplied mixing matrix from ICA')
mixing_file = io_generator.get_name("ICA mixing tsv")
mmix = pd.read_table(mixing_file).values
if ctab is None:
required_metrics = [
'kappa', 'rho', 'countnoise', 'countsigFT2', 'countsigFS0',
'dice_FT2', 'dice_FS0', 'signal-noise_t', 'variance explained',
'normalized variance explained', 'd_table_score'
]
comptable = metrics.collect.generate_metrics(
catd,
data_oc,
mmix,
masksum_clf,
tes,
io_generator,
'ICA',
metrics=required_metrics,
)
comptable, metric_metadata = selection.kundu_selection_v2(
comptable, n_echos, n_vols)
else:
comptable = pd.read_table(ctab)
if manacc is not None:
comptable, metric_metadata = selection.manual_selection(
comptable, acc=manacc)
# Write out ICA files.
comp_names = comptable["Component"].values
mixing_df = pd.DataFrame(data=mmix, columns=comp_names)
io_generator.save_file(mixing_df, "ICA mixing tsv")
betas_oc = utils.unmask(computefeats2(data_oc, mmix, mask_denoise),
mask_denoise)
io_generator.save_file(betas_oc, 'z-scored ICA components img')
# Save component table and associated json
io_generator.save_file(comptable, "ICA metrics tsv")
metric_metadata = metrics.collect.get_metadata(comptable)
io_generator.save_file(metric_metadata, "ICA metrics json")
decomp_metadata = {
"Method": ("Independent components analysis with FastICA "
"algorithm implemented by sklearn. "),
}
for comp_name in comp_names:
decomp_metadata[comp_name] = {
"Description":
"ICA fit to dimensionally-reduced optimally combined data.",
"Method": "tedana",
}
with open(io_generator.get_name("ICA decomposition json"), "w") as fo:
json.dump(decomp_metadata, fo, sort_keys=True, indent=4)
if comptable[comptable.classification == 'accepted'].shape[0] == 0:
LGR.warning('No BOLD components detected! Please check data and '
'results!')
mmix_orig = mmix.copy()
if tedort:
acc_idx = comptable.loc[~comptable.classification.str.
contains('rejected')].index.values
rej_idx = comptable.loc[comptable.classification.str.contains(
'rejected')].index.values
acc_ts = mmix[:, acc_idx]
rej_ts = mmix[:, rej_idx]
betas = np.linalg.lstsq(acc_ts, rej_ts, rcond=None)[0]
pred_rej_ts = np.dot(acc_ts, betas)
resid = rej_ts - pred_rej_ts
mmix[:, rej_idx] = resid
comp_names = [
io.add_decomp_prefix(comp,
prefix='ica',
max_value=comptable.index.max())
for comp in comptable.index.values
]
mixing_df = pd.DataFrame(data=mmix, columns=comp_names)
io_generator.save_file(mixing_df, "ICA orthogonalized mixing tsv")
RepLGR.info("Rejected components' time series were then "
"orthogonalized with respect to accepted components' time "
"series.")
io.writeresults(data_oc,
mask=mask_denoise,
comptable=comptable,
mmix=mmix,
n_vols=n_vols,
io_generator=io_generator)
if 'mir' in gscontrol:
gsc.minimum_image_regression(data_oc, mmix, mask_denoise, comptable,
io_generator)
if verbose:
io.writeresults_echoes(catd, mmix, mask_denoise, comptable,
io_generator)
# Write out BIDS-compatible description file
derivative_metadata = {
"Name":
"tedana Outputs",
"BIDSVersion":
"1.5.0",
"DatasetType":
"derivative",
"GeneratedBy": [{
"Name":
"tedana",
"Version":
__version__,
"Description":
("A denoising pipeline for the identification and removal "
"of non-BOLD noise from multi-echo fMRI data."),
"CodeURL":
"https://github.com/ME-ICA/tedana"
}]
}
with open(io_generator.get_name("data description json"), "w") as fo:
json.dump(derivative_metadata, fo, sort_keys=True, indent=4)
RepLGR.info("This workflow used numpy (Van Der Walt, Colbert, & "
"Varoquaux, 2011), scipy (Jones et al., 2001), pandas "
"(McKinney, 2010), scikit-learn (Pedregosa et al., 2011), "
"nilearn, and nibabel (Brett et al., 2019).")
RefLGR.info(
"Van Der Walt, S., Colbert, S. C., & Varoquaux, G. (2011). The "
"NumPy array: a structure for efficient numerical computation. "
"Computing in Science & Engineering, 13(2), 22.")
RefLGR.info("Jones E, Oliphant E, Peterson P, et al. SciPy: Open Source "
"Scientific Tools for Python, 2001-, http://www.scipy.org/")
RefLGR.info("McKinney, W. (2010, June). Data structures for statistical "
"computing in python. In Proceedings of the 9th Python in "
"Science Conference (Vol. 445, pp. 51-56).")
RefLGR.info("Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., "
"Thirion, B., Grisel, O., ... & Vanderplas, J. (2011). "
"Scikit-learn: Machine learning in Python. Journal of machine "
"learning research, 12(Oct), 2825-2830.")
RefLGR.info("Brett, M., Markiewicz, C. J., Hanke, M., Côté, M.-A., "
"Cipollini, B., McCarthy, P., … freec84. (2019, May 28). "
"nipy/nibabel. Zenodo. http://doi.org/10.5281/zenodo.3233118")
RepLGR.info("This workflow also used the Dice similarity index "
"(Dice, 1945; Sørensen, 1948).")
RefLGR.info("Dice, L. R. (1945). Measures of the amount of ecologic "
"association between species. Ecology, 26(3), 297-302.")
RefLGR.info(
"Sørensen, T. J. (1948). A method of establishing groups of "
"equal amplitude in plant sociology based on similarity of "
"species content and its application to analyses of the "
"vegetation on Danish commons. I kommission hos E. Munksgaard.")
with open(repname, 'r') as fo:
report = [line.rstrip() for line in fo.readlines()]
report = ' '.join(report)
with open(refname, 'r') as fo:
reference_list = sorted(list(set(fo.readlines())))
references = '\n'.join(reference_list)
report += '\n\nReferences:\n\n' + references
with open(repname, 'w') as fo:
fo.write(report)
if not no_reports:
LGR.info(
'Making figures folder with static component maps and timecourse plots.'
)
dn_ts, hikts, lowkts = io.denoise_ts(data_oc, mmix, mask_denoise,
comptable)
reporting.static_figures.carpet_plot(
optcom_ts=data_oc,
denoised_ts=dn_ts,
hikts=hikts,
lowkts=lowkts,
mask=mask_denoise,
io_generator=io_generator,
gscontrol=gscontrol,
)
reporting.static_figures.comp_figures(
data_oc,
mask=mask_denoise,
comptable=comptable,
mmix=mmix_orig,
io_generator=io_generator,
png_cmap=png_cmap,
)
if sys.version_info.major == 3 and sys.version_info.minor < 6:
warn_msg = ("Reports requested but Python version is less than "
"3.6.0. Dynamic reports will not be generated.")
LGR.warn(warn_msg)
else:
LGR.info('Generating dynamic report')
reporting.generate_report(io_generator, tr=img_t_r)
LGR.info('Workflow completed')
utils.teardown_loggers()
os.remove(refname)
def spatclust(img, min_cluster_size, threshold=None, index=None, mask=None):
"""
Spatially clusters `img`
Parameters
----------
img : str or img_like
Image file or object to be clustered
min_cluster_size : int
Minimum cluster size (in voxels)
threshold : float, optional
Whether to threshold `img` before clustering
index : array_like, optional
Whether to extract volumes from `img` for clustering
mask : (S,) array_like, optional
Boolean array for masking resultant data array
Returns
-------
clustered : :obj:`numpy.ndarray`
Boolean array of clustered (and thresholded) `img` data
"""
# we need a 4D image for `niimg.iter_img`, below
img = niimg.copy_img(check_niimg(img, atleast_4d=True))
# temporarily set voxel sizes to 1mm isotropic so that `min_cluster_size`
# represents the minimum number of voxels we want to be in a cluster,
# rather than the minimum size of the desired clusters in mm^3
if not np.all(np.abs(np.diag(img.affine)) == 1):
img.set_sform(np.sign(img.affine))
# grab desired volumes from provided image
if index is not None:
if not isinstance(index, list):
index = [index]
img = niimg.index_img(img, index)
# threshold image
if threshold is not None:
img = niimg.threshold_img(img, float(threshold))
clout = []
for subbrick in niimg.iter_img(img):
# `min_region_size` is not inclusive (as in AFNI's `3dmerge`)
# subtract one voxel to ensure we aren't hitting this thresholding issue
try:
clsts = connected_regions(subbrick,
min_region_size=int(min_cluster_size) - 1,
smoothing_fwhm=None,
extract_type='connected_components')[0]
# if no clusters are detected we get a TypeError; create a blank 4D
# image object as a placeholder instead
except TypeError:
clsts = niimg.new_img_like(subbrick,
np.zeros(subbrick.shape + (1,)))
# if multiple clusters detected, collapse into one volume
clout += [niimg.math_img('np.sum(a, axis=-1)', a=clsts)]
# convert back to data array and make boolean
clustered = utils.load_image(niimg.concat_imgs(clout).get_data()) != 0
# if mask provided, mask output
if mask is not None:
clustered = clustered[mask]
return clustered
