def test_NewSegment_inputs():
input_map = dict(
affine_regularization=dict(field='warp.affreg', ),
channel_files=dict(
copyfile=False,
field='channel',
mandatory=True,
),
channel_info=dict(field='channel', ),
ignore_exception=dict(
nohash=True,
usedefault=True,
),
matlab_cmd=dict(),
mfile=dict(usedefault=True, ),
paths=dict(),
sampling_distance=dict(field='warp.samp', ),
tissues=dict(field='tissue', ),
use_mcr=dict(),
use_v8struct=dict(
min_ver='8',
usedefault=True,
),
warping_regularization=dict(field='warp.reg', ),
write_deformation_fields=dict(field='warp.write', ),
)
inputs = NewSegment.input_spec()
for key, metadata in input_map.items():
for metakey, value in metadata.items():
yield assert_equal, getattr(inputs.traits()[key], metakey), value
def test_NewSegment_inputs():
input_map = dict(affine_regularization=dict(field='warp.affreg',
),
channel_files=dict(copyfile=False,
field='channel',
mandatory=True,
),
channel_info=dict(field='channel',
),
ignore_exception=dict(nohash=True,
usedefault=True,
),
matlab_cmd=dict(),
mfile=dict(usedefault=True,
),
paths=dict(),
sampling_distance=dict(field='warp.samp',
),
tissues=dict(field='tissue',
),
use_mcr=dict(),
use_v8struct=dict(min_ver='8',
usedefault=True,
),
warping_regularization=dict(field='warp.reg',
),
write_deformation_fields=dict(field='warp.write',
),
)
inputs = NewSegment.input_spec()
for key, metadata in input_map.items():
for metakey, value in metadata.items():
yield assert_equal, getattr(inputs.traits()[key], metakey), value
def test_NewSegment_outputs():
output_map = dict(bias_corrected_images=dict(),
bias_field_images=dict(),
dartel_input_images=dict(),
forward_deformation_field=dict(),
inverse_deformation_field=dict(),
modulated_class_images=dict(),
native_class_images=dict(),
normalized_class_images=dict(),
transformation_mat=dict(),
)
outputs = NewSegment.output_spec()
for key, metadata in output_map.items():
for metakey, value in metadata.items():
yield assert_equal, getattr(outputs.traits()[key], metakey), value
def test_NewSegment_outputs():
output_map = dict(
bias_corrected_images=dict(),
bias_field_images=dict(),
dartel_input_images=dict(),
forward_deformation_field=dict(),
inverse_deformation_field=dict(),
modulated_class_images=dict(),
native_class_images=dict(),
normalized_class_images=dict(),
transformation_mat=dict(),
)
outputs = NewSegment.output_spec()
for key, metadata in output_map.items():
for metakey, value in metadata.items():
yield assert_equal, getattr(outputs.traits()[key], metakey), value
def segmentation_pipeline(self, **kwargs): # @UnusedVariable @IgnorePep8
pipeline = self.create_pipeline(
name='ute1_segmentation',
inputs=[DatasetSpec('ute1_registered', nifti_format)],
outputs=[
DatasetSpec('air_mask', nifti_gz_format),
DatasetSpec('bones_mask', nifti_gz_format)
],
desc="Segmentation of the first echo UTE image",
version=1,
citations=(spm_cite, matlab_cite),
**kwargs)
segmentation = pipeline.create_node(
NewSegment(),
name='ute1_registered_segmentation',
requirements=[matlab2015_req, spm12_req],
wall_time=480)
pipeline.connect_input('ute1_registered', segmentation,
'channel_files')
segmentation.inputs.affine_regularization = 'none'
tissue1 = ((self.tpm_path, 1), 1, (True, False), (False, False))
tissue2 = ((self.tpm_path, 2), 1, (True, False), (False, False))
tissue3 = ((self.tpm_path, 3), 2, (True, False), (False, False))
tissue4 = ((self.tpm_path, 4), 3, (True, False), (False, False))
tissue5 = ((self.tpm_path, 5), 4, (True, False), (False, False))
tissue6 = ((self.tpm_path, 6), 3, (True, False), (False, False))
segmentation.inputs.tissues = [
tissue1, tissue2, tissue3, tissue4, tissue5, tissue6
]
select_bones_pm = pipeline.create_node(
Select(),
name='select_bones_pm_from_SPM_new_segmentation',
requirements=[],
wall_time=5)
pipeline.connect(segmentation, 'native_class_images', select_bones_pm,
'inlist')
select_bones_pm.inputs.index = 3
select_air_pm = pipeline.create_node(
Select(),
name='select_air_pm_from_SPM_new_segmentation',
requirements=[],
wall_time=5)
pipeline.connect(segmentation, 'native_class_images', select_air_pm,
'inlist')
select_air_pm.inputs.index = 5
threshold_bones = pipeline.create_node(
Threshold(),
name='bones_probabilistic_map_thresholding',
requirements=[fsl5_req],
wall_time=5)
pipeline.connect(select_bones_pm, 'out', threshold_bones, 'in_file')
threshold_bones.inputs.output_type = "NIFTI_GZ"
threshold_bones.inputs.direction = 'below'
threshold_bones.inputs.thresh = 0.2
binarize_bones = pipeline.create_node(
UnaryMaths(),
name='bones_probabilistic_map_binarization',
requirements=[fsl5_req],
wall_time=5)
pipeline.connect(threshold_bones, 'out_file', binarize_bones,
'in_file')
binarize_bones.inputs.output_type = "NIFTI_GZ"
binarize_bones.inputs.operation = 'bin'
threshold_air = pipeline.create_node(
Threshold(),
name='air_probabilistic_maps_thresholding',
requirements=[fsl5_req],
wall_time=5)
pipeline.connect(select_air_pm, 'out', threshold_air, 'in_file')
threshold_air.inputs.output_type = "NIFTI_GZ"
threshold_air.inputs.direction = 'below'
threshold_air.inputs.thresh = 0.1
binarize_air = pipeline.create_node(
UnaryMaths(),
name='air_probabilistic_map_binarization',
requirements=[fsl5_req],
wall_time=5)
pipeline.connect(threshold_air, 'out_file', binarize_air, 'in_file')
binarize_air.inputs.output_type = "NIFTI_GZ"
binarize_air.inputs.operation = 'bin'
pipeline.connect_output('bones_mask', binarize_bones, 'out_file')
pipeline.connect_output('air_mask', binarize_air, 'out_file')
pipeline.assert_connected()
return pipeline
