fMRI: FSL¶
A workflow that uses fsl to perform a first level analysis on the nipype tutorial data set:
python fmri_fsl.py
First tell python where to find the appropriate functions.
from __future__ import print_function
from __future__ import division
from builtins import str
from builtins import range
import os # system functions
import nipype.interfaces.io as nio # Data i/o
import nipype.interfaces.fsl as fsl # fsl
import nipype.interfaces.utility as util # utility
import nipype.pipeline.engine as pe # pypeline engine
import nipype.algorithms.modelgen as model # model generation
import nipype.algorithms.rapidart as ra # artifact detection
Preliminaries¶
Setup any package specific configuration. The output file format for FSL routines is being set to compressed NIFTI.
fsl.FSLCommand.set_default_output_type('NIFTI_GZ')
Setting up workflows¶
In this tutorial we will be setting up a hierarchical workflow for fsl analysis. This will demonstrate how pre-defined workflows can be setup and shared across users, projects and labs.
Setup preprocessing workflow¶
This is a generic fsl feat preprocessing workflow encompassing skull stripping, motion correction and smoothing operations.
preproc = pe.Workflow(name='preproc')
Set up a node to define all inputs required for the preprocessing workflow
inputnode = pe.Node(interface=util.IdentityInterface(fields=['func',
'struct', ]),
name='inputspec')
Convert functional images to float representation. Since there can be more than one functional run we use a MapNode to convert each run.
img2float = pe.MapNode(interface=fsl.ImageMaths(out_data_type='float',
op_string='',
suffix='_dtype'),
iterfield=['in_file'],
name='img2float')
preproc.connect(inputnode, 'func', img2float, 'in_file')
Extract the middle volume of the first run as the reference
extract_ref = pe.Node(interface=fsl.ExtractROI(t_size=1),
name='extractref')
Define a function to pick the first file from a list of files
def pickfirst(files):
if isinstance(files, list):
return files[0]
else:
return files
preproc.connect(img2float, ('out_file', pickfirst), extract_ref, 'in_file')
Define a function to return the 1 based index of the middle volume
def getmiddlevolume(func):
from nibabel import load
funcfile = func
if isinstance(func, list):
funcfile = func[0]
_, _, _, timepoints = load(funcfile).shape
return int(timepoints / 2) - 1
preproc.connect(inputnode, ('func', getmiddlevolume), extract_ref, 't_min')
Realign the functional runs to the middle volume of the first run
motion_correct = pe.MapNode(interface=fsl.MCFLIRT(save_mats=True,
save_plots=True),
name='realign',
iterfield=['in_file'])
preproc.connect(img2float, 'out_file', motion_correct, 'in_file')
preproc.connect(extract_ref, 'roi_file', motion_correct, 'ref_file')
Plot the estimated motion parameters
plot_motion = pe.MapNode(interface=fsl.PlotMotionParams(in_source='fsl'),
name='plot_motion',
iterfield=['in_file'])
plot_motion.iterables = ('plot_type', ['rotations', 'translations'])
preproc.connect(motion_correct, 'par_file', plot_motion, 'in_file')
Extract the mean volume of the first functional run
meanfunc = pe.Node(interface=fsl.ImageMaths(op_string='-Tmean',
suffix='_mean'),
name='meanfunc')
preproc.connect(motion_correct, ('out_file', pickfirst), meanfunc, 'in_file')
Strip the skull from the mean functional to generate a mask
meanfuncmask = pe.Node(interface=fsl.BET(mask=True,
no_output=True,
frac=0.3),
name='meanfuncmask')
preproc.connect(meanfunc, 'out_file', meanfuncmask, 'in_file')
Mask the functional runs with the extracted mask
maskfunc = pe.MapNode(interface=fsl.ImageMaths(suffix='_bet',
op_string='-mas'),
iterfield=['in_file'],
name='maskfunc')
preproc.connect(motion_correct, 'out_file', maskfunc, 'in_file')
preproc.connect(meanfuncmask, 'mask_file', maskfunc, 'in_file2')
Determine the 2nd and 98th percentile intensities of each functional run
getthresh = pe.MapNode(interface=fsl.ImageStats(op_string='-p 2 -p 98'),
iterfield=['in_file'],
name='getthreshold')
preproc.connect(maskfunc, 'out_file', getthresh, 'in_file')
Threshold the first run of the functional data at 10% of the 98th percentile
threshold = pe.Node(interface=fsl.ImageMaths(out_data_type='char',
suffix='_thresh'),
name='threshold')
preproc.connect(maskfunc, ('out_file', pickfirst), threshold, 'in_file')
Define a function to get 10% of the intensity
def getthreshop(thresh):
return '-thr %.10f -Tmin -bin' % (0.1 * thresh[0][1])
preproc.connect(getthresh, ('out_stat', getthreshop), threshold, 'op_string')
Determine the median value of the functional runs using the mask
medianval = pe.MapNode(interface=fsl.ImageStats(op_string='-k %s -p 50'),
iterfield=['in_file'],
name='medianval')
preproc.connect(motion_correct, 'out_file', medianval, 'in_file')
preproc.connect(threshold, 'out_file', medianval, 'mask_file')
Dilate the mask
dilatemask = pe.Node(interface=fsl.ImageMaths(suffix='_dil',
op_string='-dilF'),
name='dilatemask')
preproc.connect(threshold, 'out_file', dilatemask, 'in_file')
Mask the motion corrected functional runs with the dilated mask
maskfunc2 = pe.MapNode(interface=fsl.ImageMaths(suffix='_mask',
op_string='-mas'),
iterfield=['in_file'],
name='maskfunc2')
preproc.connect(motion_correct, 'out_file', maskfunc2, 'in_file')
preproc.connect(dilatemask, 'out_file', maskfunc2, 'in_file2')
Determine the mean image from each functional run
meanfunc2 = pe.MapNode(interface=fsl.ImageMaths(op_string='-Tmean',
suffix='_mean'),
iterfield=['in_file'],
name='meanfunc2')
preproc.connect(maskfunc2, 'out_file', meanfunc2, 'in_file')
Merge the median values with the mean functional images into a coupled list
mergenode = pe.Node(interface=util.Merge(2, axis='hstack'),
name='merge')
preproc.connect(meanfunc2, 'out_file', mergenode, 'in1')
preproc.connect(medianval, 'out_stat', mergenode, 'in2')
Smooth each run using SUSAN with the brightness threshold set to 75% of the median value for each run and a mask constituting the mean functional
smooth = pe.MapNode(interface=fsl.SUSAN(),
iterfield=['in_file', 'brightness_threshold', 'usans'],
name='smooth')
Define a function to get the brightness threshold for SUSAN
def getbtthresh(medianvals):
return [0.75 * val for val in medianvals]
def getusans(x):
return [[tuple([val[0], 0.75 * val[1]])] for val in x]
preproc.connect(maskfunc2, 'out_file', smooth, 'in_file')
preproc.connect(medianval, ('out_stat', getbtthresh), smooth, 'brightness_threshold')
preproc.connect(mergenode, ('out', getusans), smooth, 'usans')
Mask the smoothed data with the dilated mask
maskfunc3 = pe.MapNode(interface=fsl.ImageMaths(suffix='_mask',
op_string='-mas'),
iterfield=['in_file'],
name='maskfunc3')
preproc.connect(smooth, 'smoothed_file', maskfunc3, 'in_file')
preproc.connect(dilatemask, 'out_file', maskfunc3, 'in_file2')
Scale each volume of the run so that the median value of the run is set to 10000
intnorm = pe.MapNode(interface=fsl.ImageMaths(suffix='_intnorm'),
iterfield=['in_file', 'op_string'],
name='intnorm')
preproc.connect(maskfunc3, 'out_file', intnorm, 'in_file')
Define a function to get the scaling factor for intensity normalization
def getinormscale(medianvals):
return ['-mul %.10f' % (10000. / val) for val in medianvals]
preproc.connect(medianval, ('out_stat', getinormscale), intnorm, 'op_string')
Perform temporal highpass filtering on the data
highpass = pe.MapNode(interface=fsl.ImageMaths(suffix='_tempfilt'),
iterfield=['in_file'],
name='highpass')
preproc.connect(intnorm, 'out_file', highpass, 'in_file')
Generate a mean functional image from the first run
meanfunc3 = pe.MapNode(interface=fsl.ImageMaths(op_string='-Tmean',
suffix='_mean'),
iterfield=['in_file'],
name='meanfunc3')
preproc.connect(highpass, ('out_file', pickfirst), meanfunc3, 'in_file')
Strip the structural image and coregister the mean functional image to the structural image
nosestrip = pe.Node(interface=fsl.BET(frac=0.3),
name='nosestrip')
skullstrip = pe.Node(interface=fsl.BET(mask=True),
name='stripstruct')
coregister = pe.Node(interface=fsl.FLIRT(dof=6),
name='coregister')
Use nipype.algorithms.rapidart
to determine which of the
images in the functional series are outliers based on deviations in
intensity and/or movement.
art = pe.MapNode(interface=ra.ArtifactDetect(use_differences=[True, False],
use_norm=True,
norm_threshold=1,
zintensity_threshold=3,
parameter_source='FSL',
mask_type='file'),
iterfield=['realigned_files', 'realignment_parameters'],
name="art")
preproc.connect([(inputnode, nosestrip, [('struct', 'in_file')]),
(nosestrip, skullstrip, [('out_file', 'in_file')]),
(skullstrip, coregister, [('out_file', 'in_file')]),
(meanfunc2, coregister, [(('out_file', pickfirst), 'reference')]),
(motion_correct, art, [('par_file', 'realignment_parameters')]),
(maskfunc2, art, [('out_file', 'realigned_files')]),
(dilatemask, art, [('out_file', 'mask_file')]),
])
Set up model fitting workflow¶
modelfit = pe.Workflow(name='modelfit')
Use nipype.algorithms.modelgen.SpecifyModel
to generate design information.
modelspec = pe.Node(interface=model.SpecifyModel(), name="modelspec")
Use nipype.interfaces.fsl.Level1Design
to generate a run specific fsf
file for analysis
level1design = pe.Node(interface=fsl.Level1Design(), name="level1design")
Use nipype.interfaces.fsl.FEATModel
to generate a run specific mat
file for use by FILMGLS
modelgen = pe.MapNode(interface=fsl.FEATModel(), name='modelgen',
iterfield=['fsf_file', 'ev_files'])
Use nipype.interfaces.fsl.FILMGLS
to estimate a model specified by a
mat file and a functional run
modelestimate = pe.MapNode(interface=fsl.FILMGLS(smooth_autocorr=True,
mask_size=5,
threshold=1000),
name='modelestimate',
iterfield=['design_file', 'in_file'])
Use nipype.interfaces.fsl.ContrastMgr
to generate contrast estimates
conestimate = pe.MapNode(interface=fsl.ContrastMgr(), name='conestimate',
iterfield=['tcon_file', 'param_estimates',
'sigmasquareds', 'corrections',
'dof_file'])
modelfit.connect([
(modelspec, level1design, [('session_info', 'session_info')]),
(level1design, modelgen, [('fsf_files', 'fsf_file'),
('ev_files', 'ev_files')]),
(modelgen, modelestimate, [('design_file', 'design_file')]),
(modelgen, conestimate, [('con_file', 'tcon_file')]),
(modelestimate, conestimate, [('param_estimates', 'param_estimates'),
('sigmasquareds', 'sigmasquareds'),
('corrections', 'corrections'),
('dof_file', 'dof_file')]),
])
Set up fixed-effects workflow¶
fixed_fx = pe.Workflow(name='fixedfx')
Use nipype.interfaces.fsl.Merge
to merge the copes and
varcopes for each condition
copemerge = pe.MapNode(interface=fsl.Merge(dimension='t'),
iterfield=['in_files'],
name="copemerge")
varcopemerge = pe.MapNode(interface=fsl.Merge(dimension='t'),
iterfield=['in_files'],
name="varcopemerge")
Use nipype.interfaces.fsl.L2Model
to generate subject and condition
specific level 2 model design files
level2model = pe.Node(interface=fsl.L2Model(),
name='l2model')
Use nipype.interfaces.fsl.FLAMEO
to estimate a second level model
flameo = pe.MapNode(interface=fsl.FLAMEO(run_mode='fe'), name="flameo",
iterfield=['cope_file', 'var_cope_file'])
fixed_fx.connect([(copemerge, flameo, [('merged_file', 'cope_file')]),
(varcopemerge, flameo, [('merged_file', 'var_cope_file')]),
(level2model, flameo, [('design_mat', 'design_file'),
('design_con', 't_con_file'),
('design_grp', 'cov_split_file')]),
])
Set up first-level workflow¶
def sort_copes(files):
numelements = len(files[0])
outfiles = []
for i in range(numelements):
outfiles.insert(i, [])
for j, elements in enumerate(files):
outfiles[i].append(elements[i])
return outfiles
def num_copes(files):
return len(files)
firstlevel = pe.Workflow(name='firstlevel')
firstlevel.connect([(preproc, modelfit, [('highpass.out_file', 'modelspec.functional_runs'),
('art.outlier_files', 'modelspec.outlier_files'),
('highpass.out_file', 'modelestimate.in_file')]),
(preproc, fixed_fx, [('coregister.out_file', 'flameo.mask_file')]),
(modelfit, fixed_fx, [(('conestimate.copes', sort_copes), 'copemerge.in_files'),
(('conestimate.varcopes', sort_copes), 'varcopemerge.in_files'),
(('conestimate.copes', num_copes), 'l2model.num_copes'),
])
])
Experiment specific components¶
The nipype tutorial contains data for two subjects. Subject data
is in two subdirectories, s1
and s2
. Each subject directory
contains four functional volumes: f3.nii, f5.nii, f7.nii, f10.nii. And
one anatomical volume named struct.nii.
Below we set some variables to inform the datasource
about the
layout of our data. We specify the location of the data, the subject
sub-directories and a dictionary that maps each run to a mnemonic (or
field) for the run type (struct
or func
). These fields become
the output fields of the datasource
node in the pipeline.
In the example below, run ‘f3’ is of type ‘func’ and gets mapped to a nifti filename through a template ‘%s.nii’. So ‘f3’ would become ‘f3.nii’.
# Specify the location of the data.
data_dir = os.path.abspath('data')
# Specify the subject directories
subject_list = ['s1'] # , 's3']
# Map field names to individual subject runs.
info = dict(func=[['subject_id', ['f3', 'f5', 'f7', 'f10']]],
struct=[['subject_id', 'struct']])
infosource = pe.Node(interface=util.IdentityInterface(fields=['subject_id']),
name="infosource")
Here we set up iteration over all the subjects. The following line
is a particular example of the flexibility of the system. The
datasource
attribute iterables
tells the pipeline engine that
it should repeat the analysis on each of the items in the
subject_list
. In the current example, the entire first level
preprocessing and estimation will be repeated for each subject
contained in subject_list.
infosource.iterables = ('subject_id', subject_list)
Now we create a nipype.interfaces.io.DataSource
object and
fill in the information from above about the layout of our data. The
nipype.pipeline.NodeWrapper
module wraps the interface object
and provides additional housekeeping and pipeline specific
functionality.
datasource = pe.Node(interface=nio.DataGrabber(infields=['subject_id'],
outfields=['func', 'struct']),
name='datasource')
datasource.inputs.base_directory = data_dir
datasource.inputs.template = '%s/%s.nii'
datasource.inputs.template_args = info
datasource.inputs.sort_filelist = True
Use the get_node function to retrieve an internal node by name. Then set the iterables on this node to perform two different extents of smoothing.
smoothnode = firstlevel.get_node('preproc.smooth')
assert(str(smoothnode) == 'preproc.smooth')
smoothnode.iterables = ('fwhm', [5., 10.])
hpcutoff = 120
TR = 3. # ensure float
firstlevel.inputs.preproc.highpass.suffix = '_hpf'
firstlevel.inputs.preproc.highpass.op_string = '-bptf %d -1' % (hpcutoff / TR)
Setup a function that returns subject-specific information about the
experimental paradigm. This is used by the
nipype.interfaces.spm.SpecifyModel
to create the information necessary
to generate an SPM design matrix. In this tutorial, the same paradigm was used
for every participant. Other examples of this function are available in the
doc/examples folder. Note: Python knowledge required here.
def subjectinfo(subject_id):
from nipype.interfaces.base import Bunch
from copy import deepcopy
print("Subject ID: %s\n" % str(subject_id))
output = []
names = ['Task-Odd', 'Task-Even']
for r in range(4):
onsets = [list(range(15, 240, 60)), list(range(45, 240, 60))]
output.insert(r,
Bunch(conditions=names,
onsets=deepcopy(onsets),
durations=[[15] for s in names],
amplitudes=None,
tmod=None,
pmod=None,
regressor_names=None,
regressors=None))
return output
Setup the contrast structure that needs to be evaluated. This is a list of lists. The inner list specifies the contrasts and has the following format - [Name,Stat,[list of condition names],[weights on those conditions]. The condition names must match the names listed in the subjectinfo function described above.
cont1 = ['Task>Baseline', 'T', ['Task-Odd', 'Task-Even'], [0.5, 0.5]]
cont2 = ['Task-Odd>Task-Even', 'T', ['Task-Odd', 'Task-Even'], [1, -1]]
cont3 = ['Task', 'F', [cont1, cont2]]
contrasts = [cont1, cont2]
firstlevel.inputs.modelfit.modelspec.input_units = 'secs'
firstlevel.inputs.modelfit.modelspec.time_repetition = TR
firstlevel.inputs.modelfit.modelspec.high_pass_filter_cutoff = hpcutoff
firstlevel.inputs.modelfit.level1design.interscan_interval = TR
firstlevel.inputs.modelfit.level1design.bases = {'dgamma': {'derivs': False}}
firstlevel.inputs.modelfit.level1design.contrasts = contrasts
firstlevel.inputs.modelfit.level1design.model_serial_correlations = True
Set up complete workflow¶
l1pipeline = pe.Workflow(name="level1")
l1pipeline.base_dir = os.path.abspath('./fsl/workingdir')
l1pipeline.config = {"execution": {"crashdump_dir": os.path.abspath('./fsl/crashdumps')}}
l1pipeline.connect([(infosource, datasource, [('subject_id', 'subject_id')]),
(infosource, firstlevel, [(('subject_id', subjectinfo), 'modelfit.modelspec.subject_info')]),
(datasource, firstlevel, [('struct', 'preproc.inputspec.struct'),
('func', 'preproc.inputspec.func'),
]),
])
Execute the pipeline¶
The code discussed above sets up all the necessary data structures with
appropriate parameters and the connectivity between the processes, but does not
generate any output. To actually run the analysis on the data the
nipype.pipeline.engine.Pipeline.Run
function needs to be called.
if __name__ == '__main__':
l1pipeline.write_graph()
outgraph = l1pipeline.run()
# l1pipeline.run(plugin='MultiProc', plugin_args={'n_procs':2})
Example source code
You can download the full source code of this example
.
This same script is also included in the Nipype source distribution under the
examples
directory.