ANTSSLICEREGULARIZEDREGISTRATION(1) User Commands ANTSSLICEREGULARIZEDREGISTRATION(1)
NAME
antsSliceRegularizedRegistration - part of ANTS registration suite
DESCRIPTION
COMMAND:
antsSliceRegularizedRegistration
antsSliceRegularizedRegistration This program is a user-level application for
slice-by-slice translation registration. Results are regularized in z using polyno‐
mial regression. The program is targeted at spinal cord MRI. Only one stage is sup‐
ported where a stage consists of a transform; an image metric; and iterations,
shrink factors, and smoothing sigmas for each level. Specialized for 3D data: fixed
image is 3D, moving image is 3D. Registration is performed slice-by-slice then reg‐
ularized in z. The parameter -p controls the polynomial degree. -p 0 means no regu‐
larization.Implemented by B. Avants and conceived by Julien Cohen-Adad.
Outputs:
OutputPrefixTxTy_poly.csv: polynomial fit to Tx &
Ty
OutputPrefix.nii.gz: transformed image
Example call:
antsSliceRegularizedRegistration -p 4 --output [OutputPrefix,OutputPrefix.nii.gz]
--transform Translation[0.1] --metric MI[ fixed.nii.gz, moving.nii.gz , 1 , 16 ,
Regular , 0.2 ] --iterations 20 --shrinkFactors 1 --smoothingSigmas 0
OPTIONS:
-m, --metric CC[fixedImage,movingImage,metricWeight,radius,<samplingStrategy={Regular,Ran‐
dom}>,<samplingPercentage=[0,1]>]
MI[fixedImage,movingImage,metricWeight,numberOfBins,<samplingStrategy={Regular,Ran‐
dom}>,<samplingPercentage=[0,1]>] MeanSquares[fixedImage,movingImage,met‐
ricWeight,radius,<samplingStrategy={Regular,Random}>,<samplingPercentage=[0,1]>]
GC[fixedImage,movingImage,metricWeight,radius,<samplingStrategy={Regular,Ran‐
dom}>,<samplingPercentage=[0,1]>]
Four image metrics are available--- GC : global correlation, CC: ANTS neighborhood
cross correlation, MI: Mutual information, and MeanSquares: mean-squares intensity
difference. Note that the metricWeight is currently not used. Rather, it is a tem‐
porary place holder until multivariate metrics are available for a single stage.
-x, --mask mask-in-fixed-image-space.nii.gz
Fixed image mask to limit voxels considered by the metric.
-n, --interpolation Linear
NearestNeighbor MultiLabel[<sigma=imageSpacing>,<alpha=4.0>] Gauss‐
ian[<sigma=imageSpacing>,<alpha=1.0>] BSpline[<order=3>] CosineWindowedSinc Welch‐
WindowedSinc HammingWindowedSinc LanczosWindowedSinc GenericLabel[<interpola‐
tor=Linear>]
Several interpolation options are available in ITK. These have all been made avail‐
able.
-t, --transform Translation[gradientStep]
Rigid[gradientStep] Similarity[gradientStep]
Several transform options are available. The gradientStep orlearningRate character‐
izes the gradient descent optimization and is scaled appropriately for each trans‐
form using the shift scales estimator. Subsequent parameters are transform-specific
and can be determined from the usage.
-i, --iterations MxNx0...
Specify the number of iterations at each level.
-s, --smoothingSigmas MxNx0...
Specify the amount of smoothing at each level.
-f, --shrinkFactors MxNx0...
Specify the shrink factor for the virtual domain (typically the fixed image) at
each level.
-o, --output [outputTransformPrefix,<outputWarpedImage>,<outputAverageImage>]
Specify the output transform prefix (output format is .nii.gz ).Optionally, one can
choose to warp the moving image to the fixed space and, if the inverse transform
exists, one can also output the warped fixed image.
-h, --help
Print the help menu (short version). <VALUES>: 1, 0
-v, --verbose
verbose option <VALUES>: 0
-p, --polydegree
degree of polynomial - up to zDimension-2. Controls the polynomial degree. 0 means
no regularization. This may be a vector denoted by 2x2x1 for a 3-parameter trans‐
form ( e.g. rigid ). This would regularize the translation by 2nd degree polynomial
and the rotation by a linear function.
antsSliceRegularizedRegistration 2.2.0 August 2017 ANTSSLICEREGULARIZEDREGISTRATION(1)