ENH: Wrapper for DenoiseImage

CHANGES

@@ -1,6 +1,7 @@
 Next release
 ============
 
+* ENH: Provides a Nipype wrapper for ANTs DenoiseImage (https://github.com/nipy/nipype/pull/1291)
 * FIX: Minor bugfix logging hash differences (https://github.com/nipy/nipype/pull/1298)
 * FIX: Use released Prov python library (https://github.com/nipy/nipype/pull/1279)
 * ENH: Support for Python 3 (https://github.com/nipy/nipype/pull/1221)

nipype/interfaces/ants/__init__.py

@@ -12,7 +12,7 @@
 
 # Segmentation Programs
 from .segmentation import (Atropos, LaplacianThickness, N4BiasFieldCorrection, JointFusion, CorticalThickness,
- BrainExtraction)
+ BrainExtraction, DenoiseImage)
 
 # Visualization Programs
 from .visualization import ConvertScalarImageToRGB, CreateTiledMosaic

nipype/interfaces/ants/segmentation.py

@@ -795,3 +795,107 @@ def _list_outputs(self):
  outputs['output_label_image'] = os.path.abspath(
  self.inputs.output_label_image)
  return outputs
+
+
+class DenoiseImageInputSpec(ANTSCommandInputSpec):
+ dimension = traits.Enum(2, 3, 4, argstr='-d %d', usedefault=False,
+ desc='This option forces the image to be treated '
+ 'as a specified-dimensional image. If not '
+ 'specified, the program tries to infer the '
+ 'dimensionality from the input image.')
+ input_image = File(exists=True, argstr="-i %s", mandatory=True,
+ desc='A scalar image is expected as input for noise correction.')
+ noise_model = traits.Enum('Gaussian', 'Rician', argstr='-n %s', usedefault=True,
+ desc=('Employ a Rician or Gaussian noise model.'))
+ shrink_factor = traits.Int(default_value=1, usedefault=True, argstr='-s %s',
+ desc=('Running noise correction on large images can '
+ 'be time consuming. To lessen computation time, '
+ 'the input image can be resampled. The shrink '
+ 'factor, specified as a single integer, describes '
+ 'this resampling. Shrink factor = 1 is the default.'))
+ output_image = traits.Str(argstr="-o %s", genfile=True, hash_files=False,
+ desc='The output consists of the noise corrected '
+ 'version of the input image.')
+ save_noise = traits.Bool(False, mandatory=True, usedefault=True,
+ desc=('True if the estimated noise should be saved '
+ 'to file.'), xor=['noise_image'])
+ noise_image = File(desc='Filename for the estimated noise.', hash_files=False)
+ verbose = traits.Bool(False, argstr="-v", desc=('Verbose output.'))
+
+
+class DenoiseImageOutputSpec(TraitedSpec):
+ output_image = File(exists=True)
+ noise_image = File(exists=True)
+
+
+class DenoiseImage(ANTSCommand):
+ """
+ Examples
+ --------
+ >>> import copy
+ >>> from nipype.interfaces.ants import DenoiseImage
+ >>> denoise = DenoiseImage()
+ >>> denoise.inputs.dimension = 3
+ >>> denoise.inputs.input_image = 'im1.nii'
+ >>> denoise.cmdline
+ 'DenoiseImage -d 3 -i im1.nii -n Gaussian -o im1_noise_corrected.nii -s 1'
+
+ >>> denoise_2 = copy.deepcopy(denoise)
+ >>> denoise_2.inputs.output_image = 'output_corrected_image.nii.gz'
+ >>> denoise_2.inputs.noise_model = 'Rician'
+ >>> denoise_2.inputs.shrink_factor = 2
+ >>> denoise_2.cmdline
+ 'DenoiseImage -d 3 -i im1.nii -n Rician -o output_corrected_image.nii.gz -s 2'
+
+ >>> denoise_3 = DenoiseImage()
+ >>> denoise_3.inputs.input_image = 'im1.nii'
+ >>> denoise_3.inputs.save_noise = True
+ >>> denoise_3.cmdline
+ 'DenoiseImage -i im1.nii -n Gaussian -o [ im1_noise_corrected.nii, im1_noise.nii ] -s 1'
+ """
+ input_spec = DenoiseImageInputSpec
+ output_spec = DenoiseImageOutputSpec
+ _cmd = 'DenoiseImage'
+
+ def _gen_filename(self, name):
+ if name == 'output_image':
+ output = self.inputs.output_image
+ if not isdefined(output):
+ _, name, ext = split_filename(self.inputs.input_image)
+ output = name + '_noise_corrected' + ext
+ return output
+
+ if name == 'noise_image':
+ output = self.inputs.noise_image
+ if not isdefined(output):
+ _, name, ext = split_filename(self.inputs.input_image)
+ output = name + '_noise' + ext
+ return output
+ return None
+
+ def _format_arg(self, name, trait_spec, value):
+ if ((name == 'output_image') and
+ (self.inputs.save_noise or isdefined(self.inputs.noise_image))):
+ noise_image = self._gen_filename('noise_image')
+ output = self._gen_filename('output_image')
+ newval = '[ %s, %s ]' % (output, noise_image)
+ return trait_spec.argstr % newval
+
+ return super(DenoiseImage,
+ self)._format_arg(name, trait_spec, value)
+
+ def _parse_inputs(self, skip=None):
+ if skip is None:
+ skip = []
+ skip += ['save_noise', 'noise_image']
+ return super(DenoiseImage, self)._parse_inputs(skip=skip)
+
+ def _list_outputs(self):
+ outputs = self._outputs().get()
+ outputs['output_image'] = os.path.abspath(
+ self._gen_filename('output_image'))
+
+ if self.inputs.save_noise or isdefined(self.inputs.noise_image):
+ outputs['noise_image'] = os.path.abspath(
+ self._gen_filename('noise_image'))
+ return outputs

nipype/interfaces/ants/tests/test_auto_DenoiseImage.py

@@ -0,0 +1,60 @@
+# AUTO-GENERATED by tools/checkspecs.py - DO NOT EDIT
+from ....testing import assert_equal
+from ..segmentation import DenoiseImage
+
+
+def test_DenoiseImage_inputs():
+ input_map = dict(args=dict(argstr='%s',
+ ),
+ dimension=dict(argstr='-d %d',
+ usedefault=False,
+ ),
+ environ=dict(nohash=True,
+ usedefault=True,
+ ),
+ ignore_exception=dict(nohash=True,
+ usedefault=True,
+ ),
+ input_image=dict(argstr='-i %s',
+ mandatory=True,
+ ),
+ noise_image=dict(hash_files=False,
+ ),
+ noise_model=dict(argstr='-n %s',
+ usedefault=True,
+ ),
+ num_threads=dict(nohash=True,
+ usedefault=True,
+ ),
+ output_image=dict(argstr='-o %s',
+ genfile=True,
+ hash_files=False,
+ ),
+ save_noise=dict(mandatory=True,
+ usedefault=True,
+ xor=['noise_image'],
+ ),
+ shrink_factor=dict(argstr='-s %s',
+ usedefault=True,
+ ),
+ terminal_output=dict(nohash=True,
+ ),
+ verbose=dict(argstr='-v',
+ ),
+ )
+ inputs = DenoiseImage.input_spec()
+
+ for key, metadata in list(input_map.items()):
+ for metakey, value in list(metadata.items()):
+ yield assert_equal, getattr(inputs.traits()[key], metakey), value
+
+
+def test_DenoiseImage_outputs():
+ output_map = dict(noise_image=dict(),
+ output_image=dict(),
+ )
+ outputs = DenoiseImage.output_spec()
+
+ for key, metadata in list(output_map.items()):
+ for metakey, value in list(metadata.items()):
+ yield assert_equal, getattr(outputs.traits()[key], metakey), value