NIPY logo
Home · Quickstart · Documentation · Citation · NiPy
Loading

Table Of Contents

Versions

ReleaseDevel
0.8.0pre-0.9
Download Github

Links

interfaces.slicer.legacy.registration

AffineRegistration

Link to code

Wraps command **AffineRegistration **

title: Affine Registration

category: Legacy.Registration

description: Registers two images together using an affine transform and mutual information. This module is often used to align images of different subjects or images of the same subject from different modalities.

This module can smooth images prior to registration to mitigate noise and improve convergence. Many of the registration parameters require a working knowledge of the algorithm although the default parameters are sufficient for many registration tasks.

version: 0.1.0.$Revision: 19608 $(alpha)

documentation-url: http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/AffineRegistration

contributor: Daniel Blezek (GE)

acknowledgements: This module was developed by Daniel Blezek while at GE Research with contributions from Jim Miller.

This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
FixedImageFileName: (an existing file name)
        Fixed image to which to register
MovingImageFileName: (an existing file name)
        Moving image
args: (a string)
        Additional parameters to the command
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
fixedsmoothingfactor: (an integer)
        Amount of smoothing applied to fixed image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
histogrambins: (an integer)
        Number of histogram bins to use for Mattes Mutual Information. Reduce the number of bins
        if a registration fails. If the number of bins is too large, the estimated PDFs will be
        a field of impulses and will inhibit reliable registration estimation.
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
initialtransform: (an existing file name)
        Initial transform for aligning the fixed and moving image.  Maps positions in the fixed
        coordinate frame to positions in the moving coordinate frame. Optional.
iterations: (an integer)
        Number of iterations
movingsmoothingfactor: (an integer)
        Amount of smoothing applied to moving image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
outputtransform: (a boolean or a file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (a boolean or a file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).
spatialsamples: (an integer)
        Number of spatial samples to use in estimating Mattes Mutual Information. Larger values
        yield more accurate PDFs and improved registration quality.
translationscale: (a float)
        Relative scale of translations to rotations, i.e. a value of 100 means 10mm = 1 degree.
        (Actual scale used is 1/(TranslationScale^2)). This parameter is used to 'weight' or
        'standardized' the transform parameters and their effect on the registration objective
        function.

Outputs:

outputtransform: (an existing file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (an existing file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).

BSplineDeformableRegistration

Link to code

Wraps command **BSplineDeformableRegistration **

title: BSpline Deformable Registration

category: Legacy.Registration

description: Registers two images together using BSpline transform and mutual information.

version: 0.1.0.$Revision: 19608 $(alpha)

documentation-url: http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/BSplineDeformableRegistration

contributor: Bill Lorensen (GE)

acknowledgements: This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
FixedImageFileName: (an existing file name)
        Fixed image to which to register
MovingImageFileName: (an existing file name)
        Moving image
args: (a string)
        Additional parameters to the command
constrain: (a boolean)
        Constrain the deformation to the amount specified in Maximum Deformation
default: (an integer)
        Default pixel value used if resampling a pixel outside of the volume.
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
gridSize: (an integer)
        Number of grid points on interior of the fixed image. Larger grid sizes allow for finer
        registrations.
histogrambins: (an integer)
        Number of histogram bins to use for Mattes Mutual Information. Reduce the number of bins
        if a deformable registration fails. If the number of bins is too large, the estimated
        PDFs will be a field of impulses and will inhibit reliable registration estimation.
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
initialtransform: (an existing file name)
        Initial transform for aligning the fixed and moving image. Maps positions in the fixed
        coordinate frame to positions in the moving coordinate frame. This transform should be
        an affine or rigid transform.  It is used an a bulk transform for the BSpline. Optional.
iterations: (an integer)
        Number of iterations
maximumDeformation: (a float)
        If Constrain Deformation is checked, limit the deformation to this amount.
outputtransform: (a boolean or a file name)
        Transform calculated that aligns the fixed and moving image. Maps positions from the
        fixed coordinate frame to the moving coordinate frame. Optional (specify an output
        transform or an output volume or both).
outputwarp: (a boolean or a file name)
        Vector field that applies an equivalent warp as the BSpline. Maps positions from the
        fixed coordinate frame to the moving coordinate frame. Optional.
resampledmovingfilename: (a boolean or a file name)
        Resampled moving image to fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).
spatialsamples: (an integer)
        Number of spatial samples to use in estimating Mattes Mutual Information. Larger values
        yield more accurate PDFs and improved registration quality.

Outputs:

outputtransform: (an existing file name)
        Transform calculated that aligns the fixed and moving image. Maps positions from the
        fixed coordinate frame to the moving coordinate frame. Optional (specify an output
        transform or an output volume or both).
outputwarp: (an existing file name)
        Vector field that applies an equivalent warp as the BSpline. Maps positions from the
        fixed coordinate frame to the moving coordinate frame. Optional.
resampledmovingfilename: (an existing file name)
        Resampled moving image to fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).

ExpertAutomatedRegistration

Link to code

Wraps command **ExpertAutomatedRegistration **

title: Expert Automated Registration

category: Legacy.Registration

description: Provides rigid, affine, and BSpline registration methods via a simple GUI

version: 0.1.0.$Revision: 2104 $(alpha)

documentation-url: http://www.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/ExpertAutomatedRegistration

contributor: Stephen R Aylward (Kitware), Casey B Goodlett (Kitware)

acknowledgements: This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
affineMaxIterations: (an integer)
        Maximum number of affine optimization iterations
affineSamplingRatio: (a float)
        Portion of the image to use in computing the metric during affine registration
args: (a string)
        Additional parameters to the command
bsplineMaxIterations: (an integer)
        Maximum number of bspline optimization iterations
bsplineSamplingRatio: (a float)
        Portion of the image to use in computing the metric during BSpline registration
controlPointSpacing: (an integer)
        Number of pixels between control points
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
expectedOffset: (a float)
        Expected misalignment after initialization
expectedRotation: (a float)
        Expected misalignment after initialization
expectedScale: (a float)
        Expected misalignment after initialization
expectedSkew: (a float)
        Expected misalignment after initialization
fixedImage: (an existing file name)
        Image which defines the space into which the moving image is registered
fixedImageMask: (an existing file name)
        Image which defines a mask for the fixed image
fixedLandmarks: (a list of from 3 to 3 items which are a float)
        Ordered list of landmarks in the fixed image
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
initialization: ('None' or 'Landmarks' or 'ImageCenters' or 'CentersOfMass' or
         'SecondMoments')
        Method to prime the registration process
interpolation: ('NearestNeighbor' or 'Linear' or 'BSpline')
        Method for interpolation within the optimization process
loadTransform: (an existing file name)
        Load a transform that is immediately applied to the moving image
metric: ('MattesMI' or 'NormCorr' or 'MeanSqrd')
        Method to quantify image match
minimizeMemory: (a boolean)
        Reduce the amount of memory required at the cost of increased computation time
movingImage: (an existing file name)
        The transform goes from the fixed image's space into the moving image's space
movingLandmarks: (a list of from 3 to 3 items which are a float)
        Ordered list of landmarks in the moving image
numberOfThreads: (an integer)
        Number of CPU threads to use
randomNumberSeed: (an integer)
        Seed to generate a consistent random number sequence
registration: ('None' or 'Initial' or 'Rigid' or 'Affine' or 'BSpline' or 'PipelineRigid'
         or 'PipelineAffine' or 'PipelineBSpline')
        Method for the registration process
resampledImage: (a boolean or a file name)
        Registration results
rigidMaxIterations: (an integer)
        Maximum number of rigid optimization iterations
rigidSamplingRatio: (a float)
        Portion of the image to use in computing the metric during rigid registration
sampleFromOverlap: (a boolean)
        Limit metric evaluation to the fixed image region overlapped by the moving image
saveTransform: (a boolean or a file name)
        Save the transform that results from registration
verbosityLevel: ('Silent' or 'Standard' or 'Verbose')
        Level of detail of reporting progress

Outputs:

resampledImage: (an existing file name)
        Registration results
saveTransform: (an existing file name)
        Save the transform that results from registration

LinearRegistration

Link to code

Wraps command **LinearRegistration **

title: Linear Registration

category: Legacy.Registration

description: Registers two images together using a rigid transform and mutual information.

version: 0.1.0.$Revision: 19608 $(alpha)

documentation-url: http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/LinearRegistration

contributor: Daniel Blezek (GE)

acknowledgements: This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
FixedImageFileName: (an existing file name)
        Fixed image to which to register
MovingImageFileName: (an existing file name)
        Moving image
args: (a string)
        Additional parameters to the command
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
fixedsmoothingfactor: (an integer)
        Amount of smoothing applied to fixed image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
histogrambins: (an integer)
        Number of histogram bins to use for Mattes Mutual Information. Reduce the number of bins
        if a registration fails. If the number of bins is too large, the estimated PDFs will be
        a field of impulses and will inhibit reliable registration estimation.
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
initialtransform: (an existing file name)
        Initial transform for aligning the fixed and moving image. Maps positions in the fixed
        coordinate frame to positions in the moving coordinate frame. Optional.
iterations: (an integer)
        Comma separated list of iterations. Must have the same number of elements as the
        learning rate.
learningrate: (a float)
        Comma separated list of learning rates. Learning rate is a scale factor on the gradient
        of the registration objective function (gradient with respect to the parameters of the
        transformation) used to update the parameters of the transformation during optimization.
        Smaller values cause the optimizer to take smaller steps through the parameter space.
        Larger values are typically used early in the registration process to take large jumps
        in parameter space followed by smaller values to home in on the optimum value of the
        registration objective function. Default is: 0.01, 0.005, 0.0005, 0.0002. Must have the
        same number of elements as iterations.
movingsmoothingfactor: (an integer)
        Amount of smoothing applied to moving image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
outputtransform: (a boolean or a file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (a boolean or a file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).
spatialsamples: (an integer)
        Number of spatial samples to use in estimating Mattes Mutual Information. Larger values
        yield more accurate PDFs and improved registration quality.
translationscale: (a float)
        Relative scale of translations to rotations, i.e. a value of 100 means 10mm = 1 degree.
        (Actual scale used 1/(TranslationScale^2)). This parameter is used to 'weight' or
        'standardized' the transform parameters and their effect on the registration objective
        function.

Outputs:

outputtransform: (an existing file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (an existing file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).

MultiResolutionAffineRegistration

Link to code

Wraps command **MultiResolutionAffineRegistration **

title: Robust Multiresolution Affine Registration

category: Legacy.Registration

description: Provides affine registration using multiple resolution levels and decomposed affine transforms.

version: 0.1.0.$Revision: 2104 $(alpha)

documentation-url: http://www.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/MultiResolutionAffineRegistration

contributor: Casey B Goodlett (Utah)

acknowledgements: This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
args: (a string)
        Additional parameters to the command
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
fixedImage: (an existing file name)
        Image which defines the space into which the moving image is registered
fixedImageMask: (an existing file name)
        Label image which defines a mask of interest for the fixed image
fixedImageROI: (a list of items which are any value)
        Label image which defines a ROI of interest for the fixed image
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
metricTolerance: (a float)
movingImage: (an existing file name)
        The transform goes from the fixed image's space into the moving image's space
numIterations: (an integer)
        Number of iterations to run at each resolution level.
numLineIterations: (an integer)
        Number of iterations to run at each resolution level.
resampledImage: (a boolean or a file name)
        Registration results
saveTransform: (a boolean or a file name)
        Save the output transform from the registration
stepSize: (a float)
        The maximum step size of the optimizer in voxels
stepTolerance: (a float)
        The maximum step size of the optimizer in voxels

Outputs:

resampledImage: (an existing file name)
        Registration results
saveTransform: (an existing file name)
        Save the output transform from the registration

RigidRegistration

Link to code

Wraps command **RigidRegistration **

title: Rigid Registration

category: Legacy.Registration

description: Registers two images together using a rigid transform and mutual information.

This module was originally distributed as “Linear registration” but has been renamed to eliminate confusion with the “Affine registration” module.

This module is often used to align images of different subjects or images of the same subject from different modalities.

This module can smooth images prior to registration to mitigate noise and improve convergence. Many of the registration parameters require a working knowledge of the algorithm although the default parameters are sufficient for many registration tasks.

version: 0.1.0.$Revision: 19608 $(alpha)

documentation-url: http://wiki.slicer.org/slicerWiki/index.php/Documentation/4.1/Modules/RigidRegistration

contributor: Daniel Blezek (GE)

acknowledgements: This module was developed by Daniel Blezek while at GE Research with contributions from Jim Miller.

This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

Inputs:

[Mandatory]
terminal_output: ('stream' or 'allatonce' or 'file' or 'none')
        Control terminal output

[Optional]
FixedImageFileName: (an existing file name)
        Fixed image to which to register
MovingImageFileName: (an existing file name)
        Moving image
args: (a string)
        Additional parameters to the command
environ: (a dictionary with keys which are a value of type 'str' and with values which
         are a value of type 'str', nipype default value: {})
        Environment variables
fixedsmoothingfactor: (an integer)
        Amount of smoothing applied to fixed image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
histogrambins: (an integer)
        Number of histogram bins to use for Mattes Mutual Information. Reduce the number of bins
        if a registration fails. If the number of bins is too large, the estimated PDFs will be
        a field of impulses and will inhibit reliable registration estimation.
ignore_exception: (a boolean, nipype default value: False)
        Print an error message instead of throwing an exception in case the interface fails to
        run
initialtransform: (an existing file name)
        Initial transform for aligning the fixed and moving image. Maps positions in the fixed
        coordinate frame to positions in the moving coordinate frame. Optional.
iterations: (an integer)
        Comma separated list of iterations. Must have the same number of elements as the
        learning rate.
learningrate: (a float)
        Comma separated list of learning rates. Learning rate is a scale factor on the gradient
        of the registration objective function (gradient with respect to the parameters of the
        transformation) used to update the parameters of the transformation during optimization.
        Smaller values cause the optimizer to take smaller steps through the parameter space.
        Larger values are typically used early in the registration process to take large jumps
        in parameter space followed by smaller values to home in on the optimum value of the
        registration objective function. Default is: 0.01, 0.005, 0.0005, 0.0002. Must have the
        same number of elements as iterations.
movingsmoothingfactor: (an integer)
        Amount of smoothing applied to moving image prior to registration. Default is 0 (none).
        Range is 0-5 (unitless). Consider smoothing the input data if there is considerable
        amounts of noise or the noise pattern in the fixed and moving images is very different.
outputtransform: (a boolean or a file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (a boolean or a file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).
spatialsamples: (an integer)
        Number of spatial samples to use in estimating Mattes Mutual Information. Larger values
        yield more accurate PDFs and improved registration quality.
testingmode: (a boolean)
        Enable testing mode. Input transform will be used to construct floating image. The
        floating image will be ignored if passed.
translationscale: (a float)
        Relative scale of translations to rotations, i.e. a value of 100 means 10mm = 1 degree.
        (Actual scale used 1/(TranslationScale^2)). This parameter is used to 'weight' or
        'standardized' the transform parameters and their effect on the registration objective
        function.

Outputs:

outputtransform: (an existing file name)
        Transform calculated that aligns the fixed and moving image. Maps positions in the fixed
        coordinate frame to the moving coordinate frame. Optional (specify an output transform
        or an output volume or both).
resampledmovingfilename: (an existing file name)
        Resampled moving image to the fixed image coordinate frame. Optional (specify an output
        transform or an output volume or both).