interfaces.semtools.segmentation.specialized¶
BRAINSABC¶
Wraps the executable command `` BRAINSABC ``.
title: Intra-subject registration, bias Correction, and tissue classification (BRAINS)
category: Segmentation.Specialized
description: Atlas-based tissue segmentation method. This is an algorithmic extension of work done by XXXX at UNC and Utah XXXX need more description here.
Inputs:
[Optional]
inputVolumes: (a list of items which are an existing file name)
The list of input image files to be segmented.
argument: ``--inputVolumes %s...``
atlasDefinition: (an existing file name)
Contains all parameters for Atlas
argument: ``--atlasDefinition %s``
restoreState: (an existing file name)
The initial state for the registration process
argument: ``--restoreState %s``
saveState: (a boolean or a file name)
(optional) Filename to which save the final state of the
registration
argument: ``--saveState %s``
inputVolumeTypes: (a list of items which are a unicode string)
The list of input image types corresponding to the inputVolumes.
argument: ``--inputVolumeTypes %s``
outputDir: (a boolean or a directory name)
Ouput directory
argument: ``--outputDir %s``
atlasToSubjectTransformType: ('Identity' or 'Rigid' or 'Affine' or
'BSpline' or 'SyN')
What type of linear transform type do you want to use to register
the atlas to the reference subject image.
argument: ``--atlasToSubjectTransformType %s``
atlasToSubjectTransform: (a boolean or a file name)
The transform from atlas to the subject
argument: ``--atlasToSubjectTransform %s``
atlasToSubjectInitialTransform: (a boolean or a file name)
The initial transform from atlas to the subject
argument: ``--atlasToSubjectInitialTransform %s``
subjectIntermodeTransformType: ('Identity' or 'Rigid' or 'Affine' or
'BSpline')
What type of linear transform type do you want to use to register
the atlas to the reference subject image.
argument: ``--subjectIntermodeTransformType %s``
outputVolumes: (a boolean or a list of items which are a file name)
Corrected Output Images: should specify the same number of images as
inputVolume, if only one element is given, then it is used as a file
pattern where %s is replaced by the imageVolumeType, and %d by the
index list location.
argument: ``--outputVolumes %s...``
outputLabels: (a boolean or a file name)
Output Label Image
argument: ``--outputLabels %s``
outputDirtyLabels: (a boolean or a file name)
Output Dirty Label Image
argument: ``--outputDirtyLabels %s``
posteriorTemplate: (a unicode string)
filename template for Posterior output files
argument: ``--posteriorTemplate %s``
outputFormat: ('NIFTI' or 'Meta' or 'Nrrd')
Output format
argument: ``--outputFormat %s``
interpolationMode: ('BSpline' or 'NearestNeighbor' or 'WindowedSinc'
or 'Linear' or 'ResampleInPlace' or 'Hamming' or 'Cosine' or
'Welch' or 'Lanczos' or 'Blackman')
Type of interpolation to be used when applying transform to moving
volume. Options are Linear, NearestNeighbor, BSpline, WindowedSinc,
or ResampleInPlace. The ResampleInPlace option will create an image
with the same discrete voxel values and will adjust the origin and
direction of the physical space interpretation.
argument: ``--interpolationMode %s``
maxIterations: (an integer (int or long))
Filter iterations
argument: ``--maxIterations %d``
medianFilterSize: (a list of items which are an integer (int or
long))
The radius for the optional MedianImageFilter preprocessing in all 3
directions.
argument: ``--medianFilterSize %s``
filterIteration: (an integer (int or long))
Filter iterations
argument: ``--filterIteration %d``
filterTimeStep: (a float)
Filter time step should be less than (PixelSpacing/(1^(DIM+1)),
value is set to negative, then allow automatic setting of this
value.
argument: ``--filterTimeStep %f``
filterMethod: ('None' or 'CurvatureFlow' or
'GradientAnisotropicDiffusion' or 'Median')
Filter method for preprocessing of registration
argument: ``--filterMethod %s``
maxBiasDegree: (an integer (int or long))
Maximum bias degree
argument: ``--maxBiasDegree %d``
useKNN: (a boolean)
Use the KNN stage of estimating posteriors.
argument: ``--useKNN ``
purePlugsThreshold: (a float)
If this threshold value is greater than zero, only pure samples are
used to compute the distributions in EM classification, and only
pure samples are used for KNN training. The default value is set to
0, that means not using pure plugs. However, a value of 0.2 is
suggested if you want to activate using pure plugs option.
argument: ``--purePlugsThreshold %f``
numberOfSubSamplesInEachPlugArea: (a list of items which are an
integer (int or long))
Number of continous index samples taken at each direction of lattice
space for each plug volume.
argument: ``--numberOfSubSamplesInEachPlugArea %s``
atlasWarpingOff: (a boolean)
Deformable registration of atlas to subject
argument: ``--atlasWarpingOff ``
gridSize: (a list of items which are an integer (int or long))
Grid size for atlas warping with BSplines
argument: ``--gridSize %s``
defaultSuffix: (a unicode string)
argument: ``--defaultSuffix %s``
implicitOutputs: (a boolean or a list of items which are a file name)
Outputs to be made available to NiPype. Needed because not all
BRAINSABC outputs have command line arguments.
argument: ``--implicitOutputs %s...``
debuglevel: (an integer (int or long))
Display debug messages, and produce debug intermediate results.
0=OFF, 1=Minimal, 10=Maximum debugging.
argument: ``--debuglevel %d``
writeLess: (a boolean)
Does not write posteriors and filtered, bias corrected images
argument: ``--writeLess ``
numberOfThreads: (an integer (int or long))
Explicitly specify the maximum number of threads to use.
argument: ``--numberOfThreads %d``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
saveState: (an existing file name)
(optional) Filename to which save the final state of the
registration
outputDir: (an existing directory name)
Ouput directory
atlasToSubjectTransform: (an existing file name)
The transform from atlas to the subject
atlasToSubjectInitialTransform: (an existing file name)
The initial transform from atlas to the subject
outputVolumes: (a list of items which are an existing file name)
Corrected Output Images: should specify the same number of images as
inputVolume, if only one element is given, then it is used as a file
pattern where %s is replaced by the imageVolumeType, and %d by the
index list location.
outputLabels: (an existing file name)
Output Label Image
outputDirtyLabels: (an existing file name)
Output Dirty Label Image
implicitOutputs: (a list of items which are an existing file name)
Outputs to be made available to NiPype. Needed because not all
BRAINSABC outputs have command line arguments.
BRAINSConstellationDetector¶
Wraps the executable command `` BRAINSConstellationDetector ``.
title: Brain Landmark Constellation Detector (BRAINS)
category: Segmentation.Specialized
description: This program will find the mid-sagittal plane, a constellation of landmarks in a volume, and create an AC/PC aligned data set with the AC point at the center of the voxel lattice (labeled at the origin of the image physical space.) Part of this work is an extention of the algorithms originally described by Dr. Babak A. Ardekani, Alvin H. Bachman, Model-based automatic detection of the anterior and posterior commissures on MRI scans, NeuroImage, Volume 46, Issue 3, 1 July 2009, Pages 677-682, ISSN 1053-8119, DOI: 10.1016/j.neuroimage.2009.02.030. (http://www.sciencedirect.com/science/article/B6WNP-4VRP25C-4/2/8207b962a38aa83c822c6379bc43fe4c)
version: 1.0
documentation-url: http://www.nitrc.org/projects/brainscdetector/
Inputs:
[Optional]
houghEyeDetectorMode: (an integer (int or long))
, This flag controls the mode of Hough eye detector. By default,
value of 1 is for T1W images, while the value of 0 is for T2W and PD
images.,
argument: ``--houghEyeDetectorMode %d``
inputTemplateModel: (an existing file name)
User-specified template model.,
argument: ``--inputTemplateModel %s``
LLSModel: (an existing file name)
Linear least squares model filename in HD5 format
argument: ``--LLSModel %s``
inputVolume: (an existing file name)
Input image in which to find ACPC points
argument: ``--inputVolume %s``
outputVolume: (a boolean or a file name)
ACPC-aligned output image with the same voxels, but updated origin,
and direction cosign so that the AC point would fall at the physical
location (0.0,0.0,0.0), and the mid-sagital plane is the plane where
physical L/R coordinate is 0.0.
argument: ``--outputVolume %s``
outputResampledVolume: (a boolean or a file name)
ACPC-aligned output image in a resampled unifor space. Currently
this is a 1mm, 256^3, Identity direction image.
argument: ``--outputResampledVolume %s``
outputTransform: (a boolean or a file name)
The filename for the original space to ACPC alignment to be written
(in .h5 format).,
argument: ``--outputTransform %s``
outputLandmarksInInputSpace: (a boolean or a file name)
, The filename for the new subject-specific landmark definition file
in the same format produced by Slicer3 (.fcsv) with the landmarks in
the original image space (the detected RP, AC, PC, and VN4) in it to
be written.,
argument: ``--outputLandmarksInInputSpace %s``
outputLandmarksInACPCAlignedSpace: (a boolean or a file name)
, The filename for the new subject-specific landmark definition file
in the same format produced by Slicer3 (.fcsv) with the landmarks in
the output image space (the detected RP, AC, PC, and VN4) in it to
be written.,
argument: ``--outputLandmarksInACPCAlignedSpace %s``
outputMRML: (a boolean or a file name)
, The filename for the new subject-specific scene definition file in
the same format produced by Slicer3 (in .mrml format). Only the
components that were specified by the user on command line would be
generated. Compatible components include inputVolume, outputVolume,
outputLandmarksInInputSpace, outputLandmarksInACPCAlignedSpace, and
outputTransform.,
argument: ``--outputMRML %s``
outputVerificationScript: (a boolean or a file name)
, The filename for the Slicer3 script that verifies the aligned
landmarks against the aligned image file. This will happen only in
conjunction with saveOutputLandmarks and an outputVolume.,
argument: ``--outputVerificationScript %s``
mspQualityLevel: (an integer (int or long))
, Flag cotrols how agressive the MSP is estimated. 0=quick estimate
(9 seconds), 1=normal estimate (11 seconds), 2=great estimate (22
seconds), 3=best estimate (58 seconds), NOTE: -1= Prealigned so no
estimate!.,
argument: ``--mspQualityLevel %d``
otsuPercentileThreshold: (a float)
, This is a parameter to FindLargestForegroundFilledMask, which is
employed when acLowerBound is set and an
outputUntransformedClippedVolume is requested.,
argument: ``--otsuPercentileThreshold %f``
acLowerBound: (a float)
, When generating a resampled output image, replace the image with
the BackgroundFillValue everywhere below the plane This Far in
physical units (millimeters) below (inferior to) the AC point (as
found by the model.) The oversize default was chosen to have no
effect. Based on visualizing a thousand masks in the IPIG study, we
recommend a limit no smaller than 80.0 mm.,
argument: ``--acLowerBound %f``
cutOutHeadInOutputVolume: (a boolean)
, Flag to cut out just the head tissue when producing an
(un)transformed clipped volume.,
argument: ``--cutOutHeadInOutputVolume ``
outputUntransformedClippedVolume: (a boolean or a file name)
Output image in which to store neck-clipped input image, with the
use of --acLowerBound and maybe --cutOutHeadInUntransformedVolume.
argument: ``--outputUntransformedClippedVolume %s``
rescaleIntensities: (a boolean)
, Flag to turn on rescaling image intensities on input.,
argument: ``--rescaleIntensities ``
trimRescaledIntensities: (a float)
, Turn on clipping the rescaled image one-tailed on input. Units of
standard deviations above the mean. Very large values are very
permissive. Non-positive value turns clipping off. Defaults to
removing 0.00001 of a normal tail above the mean.,
argument: ``--trimRescaledIntensities %f``
rescaleIntensitiesOutputRange: (a list of items which are an integer
(int or long))
, This pair of integers gives the lower and upper bounds on the
signal portion of the output image. Out-of-field voxels are taken
from BackgroundFillValue.,
argument: ``--rescaleIntensitiesOutputRange %s``
BackgroundFillValue: (a unicode string)
Fill the background of image with specified short int value. Enter
number or use BIGNEG for a large negative number.
argument: ``--BackgroundFillValue %s``
interpolationMode: ('NearestNeighbor' or 'Linear' or
'ResampleInPlace' or 'BSpline' or 'WindowedSinc' or 'Hamming' or
'Cosine' or 'Welch' or 'Lanczos' or 'Blackman')
Type of interpolation to be used when applying transform to moving
volume. Options are Linear, ResampleInPlace, NearestNeighbor,
BSpline, or WindowedSinc
argument: ``--interpolationMode %s``
forceACPoint: (a list of items which are a float)
, Use this flag to manually specify the AC point from the original
image on the command line.,
argument: ``--forceACPoint %s``
forcePCPoint: (a list of items which are a float)
, Use this flag to manually specify the PC point from the original
image on the command line.,
argument: ``--forcePCPoint %s``
forceVN4Point: (a list of items which are a float)
, Use this flag to manually specify the VN4 point from the original
image on the command line.,
argument: ``--forceVN4Point %s``
forceRPPoint: (a list of items which are a float)
, Use this flag to manually specify the RP point from the original
image on the command line.,
argument: ``--forceRPPoint %s``
inputLandmarksEMSP: (an existing file name)
, The filename for the new subject-specific landmark definition file
in the same format produced by Slicer3 (in .fcsv) with the landmarks
in the estimated MSP aligned space to be loaded. The detector will
only process landmarks not enlisted on the file.,
argument: ``--inputLandmarksEMSP %s``
forceHoughEyeDetectorReportFailure: (a boolean)
, Flag indicates whether the Hough eye detector should report
failure,
argument: ``--forceHoughEyeDetectorReportFailure ``
rmpj: (a float)
, Search radius for MPJ in unit of mm,
argument: ``--rmpj %f``
rac: (a float)
, Search radius for AC in unit of mm,
argument: ``--rac %f``
rpc: (a float)
, Search radius for PC in unit of mm,
argument: ``--rpc %f``
rVN4: (a float)
, Search radius for VN4 in unit of mm,
argument: ``--rVN4 %f``
debug: (a boolean)
, Show internal debugging information.,
argument: ``--debug ``
verbose: (a boolean)
, Show more verbose output,
argument: ``--verbose ``
writeBranded2DImage: (a boolean or a file name)
, The filename for the 2D .png branded midline debugging image. This
will happen only in conjunction with requesting an outputVolume.,
argument: ``--writeBranded2DImage %s``
resultsDir: (a boolean or a directory name)
, The directory for the debuging images to be written.,
argument: ``--resultsDir %s``
writedebuggingImagesLevel: (an integer (int or long))
, This flag controls if debugging images are produced. By default
value of 0 is no images. Anything greater than zero will be
increasing level of debugging images.,
argument: ``--writedebuggingImagesLevel %d``
numberOfThreads: (an integer (int or long))
Explicitly specify the maximum number of threads to use.
argument: ``--numberOfThreads %d``
atlasVolume: (an existing file name)
Atlas volume image to be used for BRAINSFit registration
argument: ``--atlasVolume %s``
atlasLandmarks: (an existing file name)
Atlas landmarks to be used for BRAINSFit registration
initialization,
argument: ``--atlasLandmarks %s``
atlasLandmarkWeights: (an existing file name)
Weights associated with atlas landmarks to be used for BRAINSFit
registration initialization,
argument: ``--atlasLandmarkWeights %s``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
outputVolume: (an existing file name)
ACPC-aligned output image with the same voxels, but updated origin,
and direction cosign so that the AC point would fall at the physical
location (0.0,0.0,0.0), and the mid-sagital plane is the plane where
physical L/R coordinate is 0.0.
outputResampledVolume: (an existing file name)
ACPC-aligned output image in a resampled unifor space. Currently
this is a 1mm, 256^3, Identity direction image.
outputTransform: (an existing file name)
The filename for the original space to ACPC alignment to be written
(in .h5 format).,
outputLandmarksInInputSpace: (an existing file name)
, The filename for the new subject-specific landmark definition file
in the same format produced by Slicer3 (.fcsv) with the landmarks in
the original image space (the detected RP, AC, PC, and VN4) in it to
be written.,
outputLandmarksInACPCAlignedSpace: (an existing file name)
, The filename for the new subject-specific landmark definition file
in the same format produced by Slicer3 (.fcsv) with the landmarks in
the output image space (the detected RP, AC, PC, and VN4) in it to
be written.,
outputMRML: (an existing file name)
, The filename for the new subject-specific scene definition file in
the same format produced by Slicer3 (in .mrml format). Only the
components that were specified by the user on command line would be
generated. Compatible components include inputVolume, outputVolume,
outputLandmarksInInputSpace, outputLandmarksInACPCAlignedSpace, and
outputTransform.,
outputVerificationScript: (an existing file name)
, The filename for the Slicer3 script that verifies the aligned
landmarks against the aligned image file. This will happen only in
conjunction with saveOutputLandmarks and an outputVolume.,
outputUntransformedClippedVolume: (an existing file name)
Output image in which to store neck-clipped input image, with the
use of --acLowerBound and maybe --cutOutHeadInUntransformedVolume.
writeBranded2DImage: (an existing file name)
, The filename for the 2D .png branded midline debugging image. This
will happen only in conjunction with requesting an outputVolume.,
resultsDir: (an existing directory name)
, The directory for the debuging images to be written.,
BRAINSCreateLabelMapFromProbabilityMaps¶
Wraps the executable command `` BRAINSCreateLabelMapFromProbabilityMaps ``.
title: Create Label Map From Probability Maps (BRAINS)
category: Segmentation.Specialized
description: Given A list of Probability Maps, generate a LabelMap.
Inputs:
[Optional]
inputProbabilityVolume: (a list of items which are an existing file
name)
The list of proobabilityimages.
argument: ``--inputProbabilityVolume %s...``
priorLabelCodes: (a list of items which are an integer (int or long))
A list of PriorLabelCode values used for coding the output label
images
argument: ``--priorLabelCodes %s``
foregroundPriors: (a list of items which are an integer (int or
long))
A list: For each Prior Label, 1 if foreground, 0 if background
argument: ``--foregroundPriors %s``
nonAirRegionMask: (an existing file name)
a mask representing the 'NonAirRegion' -- Just force pixels in this
region to zero
argument: ``--nonAirRegionMask %s``
inclusionThreshold: (a float)
tolerance for inclusion
argument: ``--inclusionThreshold %f``
dirtyLabelVolume: (a boolean or a file name)
the labels prior to cleaning
argument: ``--dirtyLabelVolume %s``
cleanLabelVolume: (a boolean or a file name)
the foreground labels volume
argument: ``--cleanLabelVolume %s``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
dirtyLabelVolume: (an existing file name)
the labels prior to cleaning
cleanLabelVolume: (an existing file name)
the foreground labels volume
BRAINSCut¶
Wraps the executable command `` BRAINSCut ``.
title: BRAINSCut (BRAINS)
category: Segmentation.Specialized
description: Automatic Segmentation using neural networks
version: 1.0
license: https://www.nitrc.org/svn/brains/BuildScripts/trunk/License.txt
contributor: Vince Magnotta, Hans Johnson, Greg Harris, Kent Williams, Eunyoung Regina Kim
Inputs:
[Optional]
netConfiguration: (an existing file name)
XML File defining BRAINSCut parameters. OLD NAME. PLEASE USE
modelConfigurationFilename instead.
argument: ``--netConfiguration %s``
modelConfigurationFilename: (an existing file name)
XML File defining BRAINSCut parameters
argument: ``--modelConfigurationFilename %s``
trainModelStartIndex: (an integer (int or long))
Starting iteration for training
argument: ``--trainModelStartIndex %d``
verbose: (an integer (int or long))
print out some debugging information
argument: ``--verbose %d``
multiStructureThreshold: (a boolean)
multiStructureThreshold module to deal with overlaping area
argument: ``--multiStructureThreshold ``
histogramEqualization: (a boolean)
A Histogram Equalization process could be added to the
creating/applying process from Subject To Atlas. Default is false,
which genreate input vectors without Histogram Equalization.
argument: ``--histogramEqualization ``
computeSSEOn: (a boolean)
compute Sum of Square Error (SSE) along the trained model until the
number of iteration given in the modelConfigurationFilename file
argument: ``--computeSSEOn ``
generateProbability: (a boolean)
Generate probability map
argument: ``--generateProbability ``
createVectors: (a boolean)
create vectors for training neural net
argument: ``--createVectors ``
trainModel: (a boolean)
train the neural net
argument: ``--trainModel ``
NoTrainingVectorShuffling: (a boolean)
If this flag is on, there will be no shuffling.
argument: ``--NoTrainingVectorShuffling ``
applyModel: (a boolean)
apply the neural net
argument: ``--applyModel ``
validate: (a boolean)
validate data set.Just need for the first time run ( This is for
validation of xml file and not working yet )
argument: ``--validate ``
method: ('RandomForest' or 'ANN')
argument: ``--method %s``
numberOfTrees: (an integer (int or long))
Random tree: number of trees. This is to be used when only one
model with specified depth wish to be created.
argument: ``--numberOfTrees %d``
randomTreeDepth: (an integer (int or long))
Random tree depth. This is to be used when only one model with
specified depth wish to be created.
argument: ``--randomTreeDepth %d``
modelFilename: (a unicode string)
model file name given from user (not by xml configuration file)
argument: ``--modelFilename %s``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
None
BRAINSMultiSTAPLE¶
Wraps the executable command `` BRAINSMultiSTAPLE ``.
title: Create best representative label map)
category: Segmentation.Specialized
description: given a list of label map images, create a representative/average label map.
Inputs:
[Optional]
inputCompositeT1Volume: (an existing file name)
Composite T1, all label maps transofrmed into the space for this
image.
argument: ``--inputCompositeT1Volume %s``
inputLabelVolume: (a list of items which are an existing file name)
The list of proobabilityimages.
argument: ``--inputLabelVolume %s...``
inputTransform: (a list of items which are an existing file name)
transforms to apply to label volumes
argument: ``--inputTransform %s...``
labelForUndecidedPixels: (an integer (int or long))
Label for undecided pixels
argument: ``--labelForUndecidedPixels %d``
resampledVolumePrefix: (a unicode string)
if given, write out resampled volumes with this prefix
argument: ``--resampledVolumePrefix %s``
skipResampling: (a boolean)
Omit resampling images into reference space
argument: ``--skipResampling ``
outputMultiSTAPLE: (a boolean or a file name)
the MultiSTAPLE average of input label volumes
argument: ``--outputMultiSTAPLE %s``
outputConfusionMatrix: (a boolean or a file name)
Confusion Matrix
argument: ``--outputConfusionMatrix %s``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
outputMultiSTAPLE: (an existing file name)
the MultiSTAPLE average of input label volumes
outputConfusionMatrix: (an existing file name)
Confusion Matrix
BRAINSROIAuto¶
Wraps the executable command `` BRAINSROIAuto ``.
title: Foreground masking (BRAINS)
category: Segmentation.Specialized
description: This program is used to create a mask over the most prominant forground region in an image. This is accomplished via a combination of otsu thresholding and a closing operation. More documentation is available here: http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/ForegroundMasking.
version: 2.4.1
license: https://www.nitrc.org/svn/brains/BuildScripts/trunk/License.txt
contributor: Hans J. Johnson, hans-johnson -at- uiowa.edu, http://www.psychiatry.uiowa.edu
acknowledgements: Hans Johnson(1,3,4); Kent Williams(1); Gregory Harris(1), Vincent Magnotta(1,2,3); Andriy Fedorov(5), fedorov -at- bwh.harvard.edu (Slicer integration); (1=University of Iowa Department of Psychiatry, 2=University of Iowa Department of Radiology, 3=University of Iowa Department of Biomedical Engineering, 4=University of Iowa Department of Electrical and Computer Engineering, 5=Surgical Planning Lab, Harvard)
Inputs:
[Optional]
inputVolume: (an existing file name)
The input image for finding the largest region filled mask.
argument: ``--inputVolume %s``
outputROIMaskVolume: (a boolean or a file name)
The ROI automatically found from the input image.
argument: ``--outputROIMaskVolume %s``
outputVolume: (a boolean or a file name)
The inputVolume with optional [maskOutput|cropOutput] to the region
of the brain mask.
argument: ``--outputVolume %s``
maskOutput: (a boolean)
The inputVolume multiplied by the ROI mask.
argument: ``--maskOutput ``
cropOutput: (a boolean)
The inputVolume cropped to the region of the ROI mask.
argument: ``--cropOutput ``
otsuPercentileThreshold: (a float)
Parameter to the Otsu threshold algorithm.
argument: ``--otsuPercentileThreshold %f``
thresholdCorrectionFactor: (a float)
A factor to scale the Otsu algorithm's result threshold, in case
clipping mangles the image.
argument: ``--thresholdCorrectionFactor %f``
closingSize: (a float)
The Closing Size (in millimeters) for largest connected filled mask.
This value is divided by image spacing and rounded to the next
largest voxel number.
argument: ``--closingSize %f``
ROIAutoDilateSize: (a float)
This flag is only relavent when using ROIAUTO mode for initializing
masks. It defines the final dilation size to capture a bit of
background outside the tissue region. At setting of 10mm has been
shown to help regularize a BSpline registration type so that there
is some background constraints to match the edges of the head
better.
argument: ``--ROIAutoDilateSize %f``
outputVolumePixelType: ('float' or 'short' or 'ushort' or 'int' or
'uint' or 'uchar')
The output image Pixel Type is the scalar datatype for
representation of the Output Volume.
argument: ``--outputVolumePixelType %s``
numberOfThreads: (an integer (int or long))
Explicitly specify the maximum number of threads to use.
argument: ``--numberOfThreads %d``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
outputROIMaskVolume: (an existing file name)
The ROI automatically found from the input image.
outputVolume: (an existing file name)
The inputVolume with optional [maskOutput|cropOutput] to the region
of the brain mask.
BinaryMaskEditorBasedOnLandmarks¶
Wraps the executable command `` BinaryMaskEditorBasedOnLandmarks ``.
title: BRAINS Binary Mask Editor Based On Landmarks(BRAINS)
category: Segmentation.Specialized
version: 1.0
documentation-url: http://www.nitrc.org/projects/brainscdetector/
Inputs:
[Optional]
inputBinaryVolume: (an existing file name)
Input binary image in which to be edited
argument: ``--inputBinaryVolume %s``
outputBinaryVolume: (a boolean or a file name)
Output binary image in which to be edited
argument: ``--outputBinaryVolume %s``
inputLandmarksFilename: (an existing file name)
The filename for the landmark definition file in the same format
produced by Slicer3 (.fcsv).
argument: ``--inputLandmarksFilename %s``
inputLandmarkNames: (a list of items which are a unicode string)
A target input landmark name to be edited. This should be listed in
the inputLandmakrFilename Given.
argument: ``--inputLandmarkNames %s``
setCutDirectionForLandmark: (a list of items which are a unicode
string)
Setting the cutting out direction of the input binary image to the
one of anterior, posterior, left, right, superior or posterior.
(ENUMERATION: ANTERIOR, POSTERIOR, LEFT, RIGHT, SUPERIOR, POSTERIOR)
argument: ``--setCutDirectionForLandmark %s``
setCutDirectionForObliquePlane: (a list of items which are a unicode
string)
If this is true, the mask will be thresholded out to the direction
of inferior, posterior, and/or left. Default behavrior is that
cutting out to the direction of superior, anterior and/or right.
argument: ``--setCutDirectionForObliquePlane %s``
inputLandmarkNamesForObliquePlane: (a list of items which are a
unicode string)
Three subset landmark names of inputLandmarksFilename for a oblique
plane computation. The plane computed for binary volume editing.
argument: ``--inputLandmarkNamesForObliquePlane %s``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
outputBinaryVolume: (an existing file name)
Output binary image in which to be edited
ESLR¶
Wraps the executable command `` ESLR ``.
title: Clean Contiguous Label Map (BRAINS)
category: Segmentation.Specialized
description: From a range of label map values, extract the largest contiguous region of those labels
Inputs:
[Optional]
inputVolume: (an existing file name)
Input Label Volume
argument: ``--inputVolume %s``
outputVolume: (a boolean or a file name)
Output Label Volume
argument: ``--outputVolume %s``
low: (an integer (int or long))
The lower bound of the labels to be used.
argument: ``--low %d``
high: (an integer (int or long))
The higher bound of the labels to be used.
argument: ``--high %d``
closingSize: (an integer (int or long))
The closing size for hole filling.
argument: ``--closingSize %d``
openingSize: (an integer (int or long))
The opening size for hole filling.
argument: ``--openingSize %d``
safetySize: (an integer (int or long))
The safetySize size for the clipping region.
argument: ``--safetySize %d``
preserveOutside: (a boolean)
For values outside the specified range, preserve those values.
argument: ``--preserveOutside ``
numberOfThreads: (an integer (int or long))
Explicitly specify the maximum number of threads to use.
argument: ``--numberOfThreads %d``
args: (a unicode string)
Additional parameters to the command
argument: ``%s``
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', nipype default value: {})
Environment variables
Outputs:
outputVolume: (an existing file name)
Output Label Volume