def fix_training_pipeline(self, **name_maps):
pipeline = self.new_pipeline(
name='training_fix',
desc=("Pipeline to create the training set for FIX given a group "
"of subjects with the hand_label_noise.txt file within "
"their fix_dir."),
citations=[fsl_cite],
name_maps=name_maps)
num_fix_dirs = len(self.bold_substudies())
merge_fix_dirs = pipeline.add('merge_fix_dirs',
NiPypeMerge(num_fix_dirs))
merge_label_files = pipeline.add('merge_label_files',
NiPypeMerge(num_fix_dirs))
for i, substudy_name in enumerate(self.bold_substudies(), start=1):
spec = self.substudy_spec(substudy_name)
pipeline.connect_input(spec.inverse_map('fix_dir'), merge_fix_dirs,
'in{}'.format(i), directory_format)
pipeline.connect_input(spec.inverse_map('hand_label_noise'),
merge_label_files, 'in{}'.format(i),
text_format)
merge_visits = pipeline.add(
IdentityInterface(['list_dir', 'list_label_files']),
inputs={
'list_dir': (merge_fix_dirs, 'out'),
'list_label_files': (merge_label_files, 'out')
},
joinsource=self.SUBJECT_ID,
joinfield=['list_dir', 'list_label_files'],
name='merge_visits')
merge_subjects = pipeline.add('merge_subjects',
NiPypeMerge(2, ravel_inputs=True),
inputs={
'in1': (merge_visits, 'list_dir'),
'in2':
(merge_visits, 'list_label_files')
},
joinsource=self.SUBJECT_ID,
joinfield=['in1', 'in2'])
prepare_training = pipeline.add(
'prepare_training',
PrepareFIXTraining(epi_number=num_fix_dirs),
inputs={'inputs_list': (merge_subjects, 'out')})
pipeline.add('fix_training',
FSLFixTraining(outname='FIX_training_set', training=True),
inputs={'list_dir': (prepare_training, 'prepared_dirs')},
outputs={'train_data': ('training_set', rfile_format)},
wall_time=240,
requirements=[fix_req.v('1.0')])
return pipeline
def gather_fmri_result_pipeline(self, **name_maps):
pipeline = self.new_pipeline(
name='gather_fmri',
desc=("Pipeline to gather together all the pre-processed "
"fMRI images"),
version=1,
citations=[fsl_cite],
name_maps=name_maps)
merge_inputs = pipeline.add('merge_inputs',
NiPypeMerge(len(self.bold_substudies())))
for i, substudy_name in enumerate(self.bold_substudies(), start=1):
spec = self.substudy_spec(substudy_name)
pipeline.connect_input(spec.inverse_map('smoothed_ts'),
merge_inputs, 'in{}'.format(i),
nifti_gz_format)
pipeline.add('copy2dir',
CopyToDir(),
inputs={'in_files': (merge_inputs, 'out')},
outputs={
'fmri_pre-processeing_results':
('out_dir', directory_format)
})
return pipeline
def timeseries_normalization_to_atlas_pipeline(self, **name_maps):
pipeline = self.new_pipeline(
name='timeseries_normalization_to_atlas_pipeline',
desc=("Apply ANTs transformation to the fmri filtered file to "
"normalize it to MNI 2mm."),
citations=[fsl_cite],
name_maps=name_maps)
merge_trans = pipeline.add('merge_transforms',
NiPypeMerge(3),
inputs={
'in1': ('coreg_to_tmpl_ants_warp',
nifti_gz_format),
'in2': ('coreg_to_tmpl_ants_mat',
text_matrix_format),
'in3':
('coreg_matrix', text_matrix_format)
},
wall_time=1)
pipeline.add(
'ApplyTransform',
ApplyTransforms(interpolation='Linear', input_image_type=3),
inputs={
'reference_image': ('template_brain', nifti_gz_format),
'input_image': ('cleaned_file', nifti_gz_format),
'transforms': (merge_trans, 'out')
},
outputs={'normalized_ts': ('output_image', nifti_gz_format)},
wall_time=7,
mem_gb=24,
requirements=[ants_req.v('2')])
return pipeline
def timeseries_normalization_to_atlas_pipeline(self, **kwargs):
pipeline = self.create_pipeline(
name='timeseries_normalization_to_atlas_pipeline',
inputs=[
DatasetSpec('cleaned_file', nifti_gz_format),
DatasetSpec('coreg_to_atlas_warp', nifti_gz_format),
DatasetSpec('coreg_to_atlas_mat', text_matrix_format),
DatasetSpec('coreg_matrix', text_matrix_format)
],
outputs=[DatasetSpec('normalized_ts', nifti_gz_format)],
desc=("Apply ANTs transformation to the fmri filtered file to "
"normalize it to MNI 2mm."),
version=1,
citations=[fsl_cite],
**kwargs)
merge_trans = pipeline.create_node(NiPypeMerge(3),
name='merge_transforms',
wall_time=1)
pipeline.connect_input('coreg_to_atlas_warp', merge_trans, 'in1')
pipeline.connect_input('coreg_to_atlas_mat', merge_trans, 'in2')
pipeline.connect_input('coreg_matrix', merge_trans, 'in3')
apply_trans = pipeline.create_node(ApplyTransforms(),
name='ApplyTransform',
wall_time=7,
memory=24000,
requirements=[ants2_req])
ref_brain = self.parameter('MNI_template')
apply_trans.inputs.reference_image = ref_brain
apply_trans.inputs.interpolation = 'Linear'
apply_trans.inputs.input_image_type = 3
pipeline.connect(merge_trans, 'out', apply_trans, 'transforms')
pipeline.connect_input('cleaned_file', apply_trans, 'input_image')
pipeline.connect_output('normalized_ts', apply_trans, 'output_image')
return pipeline
def fix_training_pipeline(self, **kwargs):
inputs = []
sub_study_names = []
for sub_study_spec in self.sub_study_specs():
try:
spec = self.data_spec(sub_study_spec.inverse_map('fix_dir'))
spec._format = directory_format
inputs.append(spec)
inputs.append(
self.data_spec(
sub_study_spec.inverse_map('hand_label_noise')))
sub_study_names.append(sub_study_spec.name)
except ArcanaNameError:
continue # Sub study doesn't have fix dir
pipeline = self.create_pipeline(
name='training_fix',
inputs=inputs,
outputs=[DatasetSpec('train_data', rfile_format)],
desc=("Pipeline to create the training set for FIX given a group "
"of subjects with the hand_label_noise.txt file within "
"their fix_dir."),
version=1,
citations=[fsl_cite],
**kwargs)
num_fix_dirs = len(sub_study_names)
merge_fix_dirs = pipeline.create_node(NiPypeMerge(num_fix_dirs),
name='merge_fix_dirs')
merge_label_files = pipeline.create_node(NiPypeMerge(num_fix_dirs),
name='merge_label_files')
for i, sub_study_name in enumerate(sub_study_names, start=1):
spec = self.sub_study_spec(sub_study_name)
pipeline.connect_input(spec.inverse_map('fix_dir'), merge_fix_dirs,
'in{}'.format(i))
pipeline.connect_input(spec.inverse_map('hand_label_noise'),
merge_label_files, 'in{}'.format(i))
merge_visits = pipeline.create_join_visits_node(
IdentityInterface(['list_dir', 'list_label_files']),
joinfield=['list_dir', 'list_label_files'],
name='merge_visits')
merge_subjects = pipeline.create_join_subjects_node(
NiPypeMerge(2), joinfield=['in1', 'in2'], name='merge_subjects')
merge_subjects.inputs.ravel_inputs = True
prepare_training = pipeline.create_node(PrepareFIXTraining(),
name='prepare_training')
prepare_training.inputs.epi_number = num_fix_dirs
pipeline.connect(merge_fix_dirs, 'out', merge_visits, 'list_dir')
pipeline.connect(merge_visits, 'list_dir', merge_subjects, 'in1')
pipeline.connect(merge_label_files, 'out', merge_visits,
'list_label_files')
pipeline.connect(merge_visits, 'list_label_files', merge_subjects,
'in2')
pipeline.connect(merge_subjects, 'out', prepare_training,
'inputs_list')
fix_training = pipeline.create_node(FSLFixTraining(),
name='fix_training',
wall_time=240,
requirements=[fix_req])
fix_training.inputs.outname = 'FIX_training_set'
fix_training.inputs.training = True
pipeline.connect(prepare_training, 'prepared_dirs', fix_training,
'list_dir')
pipeline.connect_output('train_data', fix_training, 'training_set')
return pipeline