nipype.interfaces.niftyseg.lesions module

Nipype interface for seg_FillLesions.

The fusion module provides higher-level interfaces to some of the operations that can be performed with the seg_FillLesions command-line program.

Examples

See the docstrings of the individual classes for examples.

FillLesions

Link to code

Bases: NiftySegCommand

Wrapped executable: seg_FillLesions.

Interface for executable seg_FillLesions from NiftySeg platform.

Fill all the masked lesions with WM intensity average.

Source code | Documentation

Examples

>>> from nipype.interfaces import niftyseg
>>> node = niftyseg.FillLesions()
>>> node.inputs.in_file = 'im1.nii'
>>> node.inputs.lesion_mask = 'im2.nii'
>>> node.cmdline
'seg_FillLesions -i im1.nii -l im2.nii -o im1_lesions_filled.nii.gz'
Mandatory Inputs:

  • in_file (a pathlike object or string representing an existing file) – Input image to fill lesions. Maps to a command-line argument: -i %s (position: 1).

  • lesion_mask (a pathlike object or string representing an existing file) – Lesion mask. Maps to a command-line argument: -l %s (position: 2).

Optional Inputs:

  • args (a string) – Additional parameters to the command. Maps to a command-line argument: %s.

  • bin_mask (a pathlike object or string representing a file) – Give a binary mask with the valid search areas. Maps to a command-line argument: -mask %s.

  • cwf (a float) – Patch cardinality weighting factor (by default 2). Maps to a command-line argument: -cwf %f.

  • debug (a boolean) – Save all intermidium files (by default OFF). Maps to a command-line argument: -debug.

  • environ (a dictionary with keys which are a bytes or None or a value of class ‘str’ and with values which are a bytes or None or a value of class ‘str’) – Environment variables. (Nipype default value: {})

  • in_dilation (an integer) – Dilate the mask <int> times (in voxels, by default 0). Maps to a command-line argument: -dil %d.

  • match (a float) – Percentage of minimum number of voxels between patches <float> (by default 0.5). Maps to a command-line argument: -match %f.

  • other (a boolean) – Guizard et al. (FIN 2015) method, it doesn’t include the multiresolution/hierarchical inpainting part, this part needs to be done with some external software such as reg_tools and reg_resample from NiftyReg. By default it uses the method presented in Prados et al. (Neuroimage 2016). Maps to a command-line argument: -other.

  • out_datatype (a string) – Set output <datatype> (char, short, int, uchar, ushort, uint, float, double). Maps to a command-line argument: -odt %s.

  • out_file (a pathlike object or string representing a file) – The output filename of the fill lesions results. Maps to a command-line argument: -o %s (position: 3).

  • search (a float) – Minimum percentage of valid voxels in target patch <float> (by default 0). Maps to a command-line argument: -search %f.

  • size (an integer) – Search regions size respect biggest patch size (by default 4). Maps to a command-line argument: -size %d.

  • smooth (a float) – Smoothing by <float> (in minimal 6-neighbourhood voxels (by default 0.1)). Maps to a command-line argument: -smo %f.

  • use_2d (a boolean) – Uses 2D patches in the Z axis, by default 3D. Maps to a command-line argument: -2D.

  • verbose (a boolean) – Verbose (by default OFF). Maps to a command-line argument: -v.

Outputs:

out_file (a pathlike object or string representing a file) – Output segmentation.