SYNOPSIS
mia3dprealignnonrigid i <infile> o <outfile> [options]DESCRIPTION
mia3dprealignnonrigid This program runs the nonrigid registration of an image series by first registering an already aligned subset of the images to one reference, and then by registering the remaining images by using synthetic references. The is a 3D version of G. Wollny, MJ LedesmaCabryo, P.Kellman, and A.Santos, "Exploiting Quasiperiodicity in Motion Correction of FreeBreathing," IEEE Transactions on Medical Imaging, 29(8), 2010.OPTIONS
FileIO

 i infile=(input, required); io
 input images following the naming pattern nameXXXX.ext For supported file types see PLUGINS:3dimage/io
 o outfile=(output, required); io
 file name base for registered files given as Cformat string For supported file types see PLUGINS:3dimage/io
 savereferences
 Save synthetic references to files refXXXX.v
Preconditions & Preprocessing

 k skip=0
 Skip images at the begin of the seriesSkip images at the begin of the series
 preskip=20
 Skip images at the beginning+skip of the series when searching for high contrats imageSkip images at the beginning+skip of the series when searching for high contrats image
 postskip=2
 Skip images at the end of the series when searching for high contrats imageSkip images at the end of the series when searching for high contrats image
 maxcandidates=20
 maximum number of candidates for global reference imagemaximum number of candidates for global reference image
 S costseries=image:cost=[ngf:eval=ds]
 Const function to use for the analysis of the seriesConst function to use for the analysis of the series For supported plugins see PLUGINS:3dimage/fullcost
 refidx=
 save reference index number to this file
 R globalreference=1
 save reference index number to this filesave reference index number to this file
 D maxsubsetdelta=0
 Maximum delta between two elements of the prealigned subsetMaximum delta between two elements of the prealigned subset
Registration

 O optimizer=gsl:opt=gd,step=0.01
 Optimizer used for minimizationOptimizer used for minimization For supported plugins see PLUGINS:minimizer/singlecost
 l mrlevels=3
 multiresolution levelsmultiresolution levels
 f transForm=spline
 transformation typetransformation type For supported plugins see PLUGINS:3dimage/transform
 1 costsubset=image:cost=[ngf:eval=ds]
 Cost function for registration during the subset registrationCost function for registration during the subset registration For supported plugins see PLUGINS:3dimage/fullcost
 2 costfinal=image:cost=ssd
 Cost function for registration during the final registrationCost function for registration during the final registration For supported plugins see PLUGINS:3dimage/fullcost
Help & Info

 V verbose=warning

verbosity of output, print messages of given level and higher priorities. Supported priorities starting at lowest level are:
 info  Low level messages
 trace  Function call trace
 fail  Report test failures
 warning  Warnings
 error  Report errors
 debug  Debug output
 message  Normal messages
 fatal  Report only fatal errors
 copyright
 print copyright information
 h help
 print this help
 ? usage
 print a short help
 version
 print the version number and exit
Processing

 threads=1
 Maxiumum number of threads to use for processing,This number should be lower or equal to the number of logical processor cores in the machine. (1: automatic estimation).Maxiumum number of threads to use for processing,This number should be lower or equal to the number of logical processor cores in the machine. (1: automatic estimation).
PLUGINS: 1d/spacialkernel
 cdiff
 Central difference filter kernel, mirror boundary conditions are used.
 (no parameters)
 gauss
 spacial Gauss filter kernel, supported parameters are:

w
= 1; uint in [0, inf)

half filter width.

half filter width.
PLUGINS: 1d/splinebc
 mirror
 Spline interpolation boundary conditions that mirror on the boundary
 (no parameters)
 repeat
 Spline interpolation boundary conditions that repeats the value at the boundary
 (no parameters)
 zero
 Spline interpolation boundary conditions that assumes zero for values outside
 (no parameters)
PLUGINS: 1d/splinekernel
 bspline
 Bspline kernel creation , supported parameters are:

d
= 3; int in [0, 5]

Spline degree.

Spline degree.
 omoms
 OMomsspline kernel creation, supported parameters are:

d
= 3; int in [3, 3]

Spline degree.

Spline degree.
PLUGINS: 3dimage/combiner
 absdiff
 Image combiner 'absdiff'
 (no parameters)
 add
 Image combiner 'add'
 (no parameters)
 div
 Image combiner 'div'
 (no parameters)
 mul
 Image combiner 'mul'
 (no parameters)
 sub
 Image combiner 'sub'
 (no parameters)
PLUGINS: 3dimage/cost
 lncc
 local normalized cross correlation with masking support., supported parameters are:

w
= 5; uint in [1, 256]

half width of the window used for evaluating the localized cross correlation.

half width of the window used for evaluating the localized cross correlation.
 mi
 Spline parzen based mutual information., supported parameters are:

cut
= 0; float in [0, 40]

Percentage of pixels to cut at high and low intensities to remove outliers.

Percentage of pixels to cut at high and low intensities to remove outliers.

mbins
= 64; uint in [1, 256]

Number of histogram bins used for the moving image.

Number of histogram bins used for the moving image.

mkernel
= [bspline:d=3]; factory

Spline kernel for moving image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

Spline kernel for moving image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

rbins
= 64; uint in [1, 256]

Number of histogram bins used for the reference image.

Number of histogram bins used for the reference image.

rkernel
= [bspline:d=0]; factory

Spline kernel for reference image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

Spline kernel for reference image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel
 ncc
 normalized cross correlation.
 (no parameters)
 ngf
 This function evaluates the image similarity based on normalized gradient fields. Given normalized gradient fields $ _S$ of the src image and $ _R$ of the ref image various evaluators are implemented., supported parameters are:

eval
= ds; dict

plugin subtype (sq, ds,dot,cross).
Supported values are:
 ds  square of scaled difference
 dot  scalar product kernel
 cross  cross product kernel

plugin subtype (sq, ds,dot,cross).
Supported values are:
 ssd
 3D image cost: sum of squared differences, supported parameters are:

autothresh
= 0; float in [0, 1000]

Use automatic masking of the moving image by only takeing intensity values into accound that are larger than the given threshold.

Use automatic masking of the moving image by only takeing intensity values into accound that are larger than the given threshold.

norm
= 0; bool

Set whether the metric should be normalized by the number of image pixels.

Set whether the metric should be normalized by the number of image pixels.
 ssdautomask
 3D image cost: sum of squared differences, with automasking based on given thresholds, supported parameters are:

rthresh
= 0; double

Threshold intensity value for reference image.

Threshold intensity value for reference image.

sthresh
= 0; double

Threshold intensity value for source image.

Threshold intensity value for source image.
PLUGINS: 3dimage/filter
 bandpass
 intensity bandpass filter, supported parameters are:

max
= 3.40282e+38; float

maximum of the band.

maximum of the band.

min
= 0; float

minimum of the band.

minimum of the band.
 binarize
 image binarize filter, supported parameters are:

max
= 3.40282e+38; float

maximum of accepted range.

maximum of accepted range.

min
= 0; float

minimum of accepted range.

minimum of accepted range.
 close
 morphological close, supported parameters are:

hint
= black; string

a hint at the main image content (blackwhite).

a hint at the main image content (blackwhite).

shape
= [sphere:r=2]; factory

structuring element.
For supported plugins see PLUGINS:3dimage/shape

structuring element.
For supported plugins see PLUGINS:3dimage/shape
 combiner
 Combine two images with the given combiner operator. if 'reverse' is set to false, the first operator is the image passed through the filter pipeline, and the second image is loaded from the file given with the 'image' parameter the moment the filter is run., supported parameters are:

image
=(input, required, string)

second image that is needed in the combiner.

second image that is needed in the combiner.

op
=(required, factory)

Image combiner to be applied to the images.
For supported plugins see PLUGINS:3dimage/combiner

Image combiner to be applied to the images.
For supported plugins see PLUGINS:3dimage/combiner

reverse
= 0; bool

reverse the order in which the images passed to the combiner.

reverse the order in which the images passed to the combiner.
 convert
 image pixel format conversion filter, supported parameters are:

a
= 1; float

linear conversion parameter a.

linear conversion parameter a.

b
= 0; float

linear conversion parameter b.

linear conversion parameter b.

map
= opt; dict

conversion mapping.
Supported values are:
 opt  apply a linear transformation that maps the real input range to the full output range
 range  apply linear transformation that maps the input data type range to the output data type range
 copy  copy data when converting
 linear  apply linear transformation x > a*x+b
 optstat  apply a linear transform that maps based on input mean and variation to the full output range

conversion mapping.
Supported values are:

repn
= ubyte; dict

output pixel type.
Supported values are:
 none  no pixel type defined
 float  floating point 32 bit
 sbyte  signed 8 bit
 ulong  unsigned 64 bit
 double  floating point 64 bit
 sint  signed 32 bit
 ushort  unsigned 16 bit
 sshort  signed 16 bit
 uint  unsigned 32 bit
 slong  signed 64 bit
 bit  binary data
 ubyte  unsigned 8 bit

output pixel type.
Supported values are:
 crop
 Crop a region of an image, the region is always clamped to the original image size in the sense that the given range is kept., supported parameters are:

end
= [[4294967295,4294967295,4294967295]]; streamable

end of cropping range, maximum = (1,1,1).

end of cropping range, maximum = (1,1,1).

start
= [[0,0,0]]; streamable

begin of cropping range.

begin of cropping range.
 dilate
 3d image stack dilate filter, supported parameters are:

hint
= black; string

a hint at the main image content (blackwhite).

a hint at the main image content (blackwhite).

shape
= [sphere:r=2]; factory

structuring element.
For supported plugins see PLUGINS:3dimage/shape

structuring element.
For supported plugins see PLUGINS:3dimage/shape
 distance
 Evaluate the 3D distance transform of an image. If the image is a binary mask, then result of the distance transform in each point corresponds to the Euclidian distance to the mask. If the input image is of a scalar pixel value, then the this scalar is interpreted as heighfield and the per pixel value adds to the distance.
 (no parameters)
 downscale
 Downscale the input image by using a given block size to define the downscale factor. Prior to scaling the image is filtered by a smoothing filter to eliminate high frequency data and avoid aliasing artifacts., supported parameters are:

b
= [[1,1,1]]; 3dbounds

blocksize.

blocksize.

bx
= 1; uint in [1, inf)

blocksize in x direction.

blocksize in x direction.

by
= 1; uint in [1, inf)

blocksize in y direction.

blocksize in y direction.

bz
= 1; uint in [1, inf)

blocksize in z direction.

blocksize in z direction.

kernel
= gauss; string

smoothing filter kernel to be applied, the size of the filter is estimated based on the blocksize..

smoothing filter kernel to be applied, the size of the filter is estimated based on the blocksize..
 erode
 3d image stack erode filter, supported parameters are:

hint
= black; string

a hint at the main image content (blackwhite).

a hint at the main image content (blackwhite).

shape
= [sphere:r=2]; factory

structuring element.
For supported plugins see PLUGINS:3dimage/shape

structuring element.
For supported plugins see PLUGINS:3dimage/shape
 gauss
 isotropic 3D gauss filter, supported parameters are:

w
= 1; int in [0, inf)

filter width parameter.

filter width parameter.
 gradnorm
 3D image to gradient norm filter
 (no parameters)
 growmask
 Use an input binary mask and a reference gray scale image to do region growing by adding the neighborhood pixels of an already added pixel if the have a lower intensity that is above the given threshold., supported parameters are:

min
= 1; float

lower threshold for mask growing.

lower threshold for mask growing.

ref
=(input, required, string)

reference image for mask region growing.

reference image for mask region growing.

shape
= 6n; factory

neighborhood mask.
For supported plugins see PLUGINS:3dimage/shape

neighborhood mask.
For supported plugins see PLUGINS:3dimage/shape
 invert
 intensity invert filter
 (no parameters)
 isovoxel
 This filter scales an image to make the voxel size isometric and its size to correspond to the given value, supported parameters are:

interp
= [bspline:d=3]; factory

interpolation kernel to be used .
For supported plugins see PLUGINS:1d/splinekernel

interpolation kernel to be used .
For supported plugins see PLUGINS:1d/splinekernel

size
= 1; float in (0, inf)

isometric target voxel size.

isometric target voxel size.
 kmeans
 3D image kmeans filter. In the output image the pixel value represents the class membership and the class centers are stored as attribute in the image., supported parameters are:

c
= 3; int in [2, inf)

number of classes.

number of classes.
 label
 A filter to label the connected components of a binary image., supported parameters are:

n
= 6n; factory

neighborhood mask.
For supported plugins see PLUGINS:3dimage/shape

neighborhood mask.
For supported plugins see PLUGINS:3dimage/shape
 labelmap
 Image filter to remap label id's. Only applicable to images with integer valued intensities/labels., supported parameters are:

map
=(input, required, string)

Label mapping file.

Label mapping file.
 labelscale
 A filter that only creates output voxels that are already created in the input image. Scaling is done by using a voting algorithms that selects the target pixel value based on the highest pixel count of a certain label in the corresponding source region. If the region comprises two labels with the same count, the one with the lower number wins., supported parameters are:

outsize
=(required, 3dbounds)

target size given as two coma separated values.

target size given as two coma separated values.
 load
 Load the input image from a file and use it to replace the current image in the pipeline., supported parameters are:

file
=(input, required, string)

name of the input file to load from..

name of the input file to load from..
 lvdownscale
 This is a label voting downscale filter. It adownscales a 3D image by blocks. For each block the (nonzero) label that appears most times in the block is issued as output pixel in the target image. If two labels appear the same number of times, the one with the lower absolute value wins., supported parameters are:

b
= [[1,1,1]]; 3dbounds

blocksize for the downscaling. Each block will be represented by one pixel in the target image..

blocksize for the downscaling. Each block will be represented by one pixel in the target image..
 mask
 Mask an image, one image is taken from the parameters list and the other from the normal filter input. Both images must be of the same dimensions and one must be binary. The attributes of the image coming through the filter pipeline are preserved. The output pixel type corresponds to the input image that is not binary., supported parameters are:

input
=(input, required, string)

second input image file name.

second input image file name.
 mean
 3D image mean filter, supported parameters are:

w
= 1; int in [1, inf)

half filter width.

half filter width.
 median
 median 3d filter, supported parameters are:

w
= 1; int in [1, inf)

filter width parameter.

filter width parameter.
 mlv
 Mean of Least Variance 3D image filter, supported parameters are:

w
= 1; int in [1, inf)

filter width parameter.

filter width parameter.
 msnormalizer
 3D image meansigma normalizing filter, supported parameters are:

w
= 1; int in [1, inf)

half filter width.

half filter width.
 open
 morphological open, supported parameters are:

hint
= black; string

a hint at the main image content (blackwhite).

a hint at the main image content (blackwhite).

shape
= [sphere:r=2]; factory

structuring element.
For supported plugins see PLUGINS:3dimage/shape

structuring element.
For supported plugins see PLUGINS:3dimage/shape
 reorient
 3D image reorientation filter, supported parameters are:

map
= xyz; dict

oriantation mapping to be applied.
Supported values are:
 pzxy  permutate x>y>z>x
 rx180  rotate around xaxis clockwise 180 degree
 xyz  keep orientation
 pyzx  permutate x>z>y>x
 rz180  rotate around zaxis clockwise 180 degree
 ry270  rotate around yaxis clockwise 270 degree
 fxz  flip xz
 fyz  flip yz
 rx90  rotate around xaxis clockwise 90 degree
 ry90  rotate around yaxis clockwise 90 degree
 rx270  rotate around xaxis clockwise 270 degree
 rz270  rotate around zaxis clockwise 270 degree
 rz90  rotate around zaxis clockwise 90 degree
 fxy  flip xy
 ry180  rotate around yaxis clockwise 180 degree

oriantation mapping to be applied.
Supported values are:
 resize
 Resize an image. The original data is centered within the new sized image., supported parameters are:

size
= [[0,0,0]]; streamable

new size of the image a size 0 indicates to keep the size for the corresponding dimension..

new size of the image a size 0 indicates to keep the size for the corresponding dimension..
 sandp
 salt and pepper 3d filter, supported parameters are:

thresh
= 100; float in [0, inf)

thresh value.

thresh value.

w
= 1; int in [1, inf)

filter width parameter.

filter width parameter.
 scale
 3D image filter that scales to a given target size , supported parameters are:

interp
= [bspline:d=3]; factory

interpolation kernel to be used .
For supported plugins see PLUGINS:1d/splinekernel

interpolation kernel to be used .
For supported plugins see PLUGINS:1d/splinekernel

s
= [[0,0,0]]; 3dbounds

target size to set all components at once (component 0:use input image size).

target size to set all components at once (component 0:use input image size).

sx
= 0; uint in [0, inf)

target size in x direction (0:use input image size).

target size in x direction (0:use input image size).

sy
= 0; uint in [0, inf)

target size in y direction (0:use input image size).

target size in y direction (0:use input image size).

sz
= 0; uint in [0, inf)

target size in y direction (0:use input image size).

target size in y direction (0:use input image size).
 selectbig
 A filter that creats a binary mask representing the intensity with the highest pixel count.The pixel value 0 will be ignored, and if two intensities have the same pixel count, then the result is undefined. The input pixel must have an integral pixel type.
 (no parameters)
 sepconv
 3D image intensity separaple convolution filter, supported parameters are:

kx
= [gauss:w=1]; factory

filter kernel in xdirection.
For supported plugins see PLUGINS:1d/spacialkernel

filter kernel in xdirection.
For supported plugins see PLUGINS:1d/spacialkernel

ky
= [gauss:w=1]; factory

filter kernel in ydirection.
For supported plugins see PLUGINS:1d/spacialkernel

filter kernel in ydirection.
For supported plugins see PLUGINS:1d/spacialkernel

kz
= [gauss:w=1]; factory

filter kernel in zdirection.
For supported plugins see PLUGINS:1d/spacialkernel

filter kernel in zdirection.
For supported plugins see PLUGINS:1d/spacialkernel
 sws
 seeded watershead. The algorithm extracts exactly so many reagions as initial labels are given in the seed image., supported parameters are:

grad
= 0; bool

Interpret the input image as gradient. .

Interpret the input image as gradient. .

mark
= 0; bool

Mark the segmented watersheds with a special gray scale value.

Mark the segmented watersheds with a special gray scale value.

n
= [sphere:r=1]; factory

Neighborhood for watershead region growing.
For supported plugins see PLUGINS:3dimage/shape

Neighborhood for watershead region growing.
For supported plugins see PLUGINS:3dimage/shape

seed
=(input, required, string)

seed input image containing the lables for the initial regions.

seed input image containing the lables for the initial regions.
 tee
 Save the input image to a file and also pass it through to the next filter, supported parameters are:

file
=(output, required, string)

name of the output file to save the image too..

name of the output file to save the image too..
 thinning
 3D morphological thinning, based on: Lee and Kashyap, 'Building Skeleton Models via 3D Medial Surface/Axis Thinning Algorithms', Graphical Models and Image Processing, 56(6):462478, 1994. This implementation only supports the 26 neighbourhood.
 (no parameters)
 transform
 Transform the input image with the given transformation., supported parameters are:

file
=(input, required, string)

Name of the file containing the transformation..

Name of the file containing the transformation..

imgboundary
= ; string

override image interpolation boundary conditions.

override image interpolation boundary conditions.

imgkernel
= ; string

override image interpolator kernel.

override image interpolator kernel.
 variance
 3D image variance filter, supported parameters are:

w
= 1; int in [1, inf)

half filter width.

half filter width.
 ws
 basic watershead segmentation., supported parameters are:

evalgrad
= 0; bool

Set to 1 if the input image does not represent a gradient norm image.

Set to 1 if the input image does not represent a gradient norm image.

mark
= 0; bool

Mark the segmented watersheds with a special gray scale value.

Mark the segmented watersheds with a special gray scale value.

n
= [sphere:r=1]; factory

Neighborhood for watershead region growing.
For supported plugins see PLUGINS:3dimage/shape

Neighborhood for watershead region growing.
For supported plugins see PLUGINS:3dimage/shape

thresh
= 0; float in [0, 1)

Relative gradient norm threshold. The actual value threshold value is thresh * (max_grad  min_grad) + min_grad. Bassins separated by gradients with a lower norm will be joined.

Relative gradient norm threshold. The actual value threshold value is thresh * (max_grad  min_grad) + min_grad. Bassins separated by gradients with a lower norm will be joined.
PLUGINS: 3dimage/fullcost
 image
 Generalized image similarity cost function that also handles multiresolution processing. The actual similarity measure is given es extra parameter., supported parameters are:

cost
= ssd; factory

Cost function kernel.
For supported plugins see PLUGINS:3dimage/cost

Cost function kernel.
For supported plugins see PLUGINS:3dimage/cost

debug
= 0; bool

Save intermediate resuts for debugging.

Save intermediate resuts for debugging.

ref
=(input, string)

Reference image.

Reference image.

src
=(input, string)

Study image.

Study image.

weight
= 1; float

weight of cost function.

weight of cost function.
 labelimage
 Similarity cost function that maps labels of two images and handles labelpreserving multiresolution processing., supported parameters are:

maxlabel
= 256; int in [2, 32000]

maximum number of labels to consider.

maximum number of labels to consider.

ref
=(input, string)

Reference image.

Reference image.

src
=(input, string)

Study image.

Study image.

weight
= 1; float

weight of cost function.

weight of cost function.
 maskedimage
 Generalized masked image similarity cost function that also handles multiresolution processing. The provided masks should be densly filled regions in multiresolution procesing because otherwise the mask information may get lost when downscaling the image. The mask may be prefiltered  after prefiltering the masks must be of bittype.The reference mask and the transformed mask of the study image are combined by binary AND. The actual similarity measure is given es extra parameter., supported parameters are:

cost
= ssd; factory

Cost function kernel.
For supported plugins see PLUGINS:3dimage/maskedcost

Cost function kernel.
For supported plugins see PLUGINS:3dimage/maskedcost

ref
=(input, string)

Reference image.

Reference image.

refmask
=(input, string)

Reference image mask (binary).

Reference image mask (binary).

refmaskfilter
= ; factory

Filter to prepare the reference mask image, the output must be a binary image..
For supported plugins see PLUGINS:3dimage/filter

Filter to prepare the reference mask image, the output must be a binary image..
For supported plugins see PLUGINS:3dimage/filter

src
=(input, string)

Study image.

Study image.

srcmask
=(input, string)

Study image mask (binary).

Study image mask (binary).

srcmaskfilter
= ; factory

Filter to prepare the study mask image, the output must be a binary image..
For supported plugins see PLUGINS:3dimage/filter

Filter to prepare the study mask image, the output must be a binary image..
For supported plugins see PLUGINS:3dimage/filter

weight
= 1; float

weight of cost function.

weight of cost function.
 taggedssd
 Evaluates the Sum of Squared Differences similarity measure by using three tagged image pairs. The cost function value is evaluated based on all image pairs, but the gradient is composed by composing its component based on the tag direction., supported parameters are:

refx
=(input, string)

Reference image Xtag.

Reference image Xtag.

refy
=(input, string)

Reference image Ytag.

Reference image Ytag.

refz
=(input, string)

Reference image Ztag.

Reference image Ztag.

srcx
=(input, string)

Study image Xtag.

Study image Xtag.

srcy
=(input, string)

Study image Ytag.

Study image Ytag.

srcz
=(input, string)

Study image Ztag.

Study image Ztag.

weight
= 1; float

weight of cost function.

weight of cost function.
PLUGINS: 3dimage/io
 analyze
 Analyze 7.5 image
 Recognized file extensions: .HDR, .hdr

Supported element types:
 unsigned 8 bit, signed 16 bit, signed 32 bit, floating point 32 bit, floating point 64 bit
 datapool
 Virtual IO to and from the internal data pool
 Recognized file extensions: [email protected]
 dicom
 Dicom image series as 3D
 Recognized file extensions: .DCM, .dcm

Supported element types:
 signed 16 bit, unsigned 16 bit
 hdf5
 HDF5 3D image IO
 Recognized file extensions: .H5, .h5

Supported element types:
 binary data, signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, signed 64 bit, unsigned 64 bit, floating point 32 bit, floating point 64 bit
 inria
 INRIA image
 Recognized file extensions: .INR, .inr

Supported element types:
 signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, floating point 32 bit, floating point 64 bit
 mhd
 MetaIO 3D image IO using the VTK implementation (experimental).
 Recognized file extensions: .MHA, .MHD, .mha, .mhd

Supported element types:
 signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, floating point 32 bit, floating point 64 bit
 nifti
 NIFTI1 3D image IO
 Recognized file extensions: .NII, .nii

Supported element types:
 signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, signed 64 bit, unsigned 64 bit, floating point 32 bit, floating point 64 bit
 vff
 VFF Sun raster format
 Recognized file extensions: .VFF, .vff

Supported element types:
 unsigned 8 bit, signed 16 bit
 vista
 Vista 3D
 Recognized file extensions: .V, .VISTA, .v, .vista

Supported element types:
 binary data, signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, floating point 32 bit, floating point 64 bit
 vti
 3D image VTKXML in and output (experimental).
 Recognized file extensions: .VTI, .vti

Supported element types:
 signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, floating point 32 bit, floating point 64 bit
 vtk
 3D VTK image legacy in and output (experimental).
 Recognized file extensions: .VTK, .VTKIMAGE, .vtk, .vtkimage

Supported element types:
 binary data, signed 8 bit, unsigned 8 bit, signed 16 bit, unsigned 16 bit, signed 32 bit, unsigned 32 bit, floating point 32 bit, floating point 64 bit
PLUGINS: 3dimage/maskedcost
 lncc
 local normalized cross correlation with masking support., supported parameters are:

w
= 5; uint in [1, 256]

half width of the window used for evaluating the localized cross correlation.

half width of the window used for evaluating the localized cross correlation.
 mi
 Spline parzen based mutual information with masking., supported parameters are:

cut
= 0; float in [0, 40]

Percentage of pixels to cut at high and low intensities to remove outliers.

Percentage of pixels to cut at high and low intensities to remove outliers.

mbins
= 64; uint in [1, 256]

Number of histogram bins used for the moving image.

Number of histogram bins used for the moving image.

mkernel
= [bspline:d=3]; factory

Spline kernel for moving image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

Spline kernel for moving image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

rbins
= 64; uint in [1, 256]

Number of histogram bins used for the reference image.

Number of histogram bins used for the reference image.

rkernel
= [bspline:d=0]; factory

Spline kernel for reference image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel

Spline kernel for reference image parzen hinstogram.
For supported plugins see PLUGINS:1d/splinekernel
 ncc
 normalized cross correlation with masking support.
 (no parameters)
 ssd
 Sum of squared differences with masking.
 (no parameters)
PLUGINS: 3dimage/shape
 18n
 18n neighborhood 3D shape creator
 (no parameters)
 26n
 26n neighborhood 3D shape creator
 (no parameters)
 6n
 6n neighborhood 3D shape creator
 (no parameters)
 sphere
 Closed spherical shape neighborhood including the pixels within a given radius r., supported parameters are:

r
= 2; float in (0, inf)

sphere radius.

sphere radius.
PLUGINS: 3dimage/transform
 affine
 Affine transformation (12 degrees of freedom), supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel
 axisrot
 Restricted rotation transformation (1 degrees of freedom). The transformation is restricted to the rotation around the given axis about the given rotation center, supported parameters are:

axis
=(required, 3dfvector)

rotation axis.

rotation axis.

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

origin
=(required, 3dfvector)

center of the transformation.

center of the transformation.
 raffine
 Restricted affine transformation (3 degrees of freedom). The transformation is restricted to the rotation around the given axis and shearing along the two axis perpendicular to the given one, supported parameters are:

axis
=(required, 3dfvector)

rotation axis.

rotation axis.

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

origin
=(required, 3dfvector)

center of the transformation.

center of the transformation.
 rigid
 Rigid transformation, i.e. rotation and translation (six degrees of freedom)., supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

origin
= [[0,0,0]]; 3dfvector

Relative rotation center, i.e. <0.5,0.5,0.5> corresponds to the center of the volume.

Relative rotation center, i.e. <0.5,0.5,0.5> corresponds to the center of the volume.
 rotation
 Rotation transformation (three degrees of freedom)., supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

origin
= [[0,0,0]]; 3dfvector

Relative rotation center, i.e. <0.5,0.5,0.5> corresponds to the center of the volume.

Relative rotation center, i.e. <0.5,0.5,0.5> corresponds to the center of the volume.
 rotbend
 Restricted transformation (4 degrees of freedom). The transformation is restricted to the rotation around the x and y axis and a bending along the x axis, independedn in each direction, with the bending increasing with the squared distance from the rotation axis., supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

norot
= 0; bool

Don't optimize the rotation.

Don't optimize the rotation.

origin
=(required, 3dfvector)

center of the transformation.

center of the transformation.
 spline
 Freeform transformation that can be described by a set of Bspline coefficients and an underlying Bspline kernel., supported parameters are:

anisorate
= [[0,0,0]]; 3dfvector

anisotropic coefficient rate in pixels, nonpositive values will be overwritten by the 'rate' value..

anisotropic coefficient rate in pixels, nonpositive values will be overwritten by the 'rate' value..

debug
= 0; bool

enable additional debuging output.

enable additional debuging output.

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

kernel
= [bspline:d=3]; factory

transformation spline kernel.
For supported plugins see PLUGINS:1d/splinekernel

transformation spline kernel.
For supported plugins see PLUGINS:1d/splinekernel

penalty
= ; factory

transformation penalty energy term.
For supported plugins see PLUGINS:3dtransform/splinepenalty

transformation penalty energy term.
For supported plugins see PLUGINS:3dtransform/splinepenalty

rate
= 10; float in [1, inf)

isotropic coefficient rate in pixels.

isotropic coefficient rate in pixels.
 translate
 Translation (three degrees of freedom), supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel
 vf
 This plugin implements a transformation that defines a translation for each point of the grid defining the domain of the transformation., supported parameters are:

imgboundary
= mirror; factory

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

image interpolation boundary conditions.
For supported plugins see PLUGINS:1d/splinebc

imgkernel
= [bspline:d=3]; factory

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel

image interpolator kernel.
For supported plugins see PLUGINS:1d/splinekernel
PLUGINS: 3dtransform/io
 bbs
 Binary (nonportable) serialized IO of 3D transformations
 Recognized file extensions: .bbs
 datapool
 Virtual IO to and from the internal data pool
 Recognized file extensions: [email protected]
 vista
 Vista storage of 3D transformations
 Recognized file extensions: .v, .v3dt
 xml
 XML serialized IO of 3D transformations
 Recognized file extensions: .x3dt
PLUGINS: 3dtransform/splinepenalty
 divcurl
 divcurl penalty on the transformation, supported parameters are:

curl
= 1; float in [0, inf)

penalty weight on curl.

penalty weight on curl.

div
= 1; float in [0, inf)

penalty weight on divergence.

penalty weight on divergence.

norm
= 0; bool

Set to 1 if the penalty should be normalized with respect to the image size.

Set to 1 if the penalty should be normalized with respect to the image size.

weight
= 1; float in (0, inf)

weight of penalty energy.

weight of penalty energy.
PLUGINS: minimizer/singlecost
 gdas
 Gradient descent with automatic step size correction., supported parameters are:

ftolr
= 0; double in [0, inf)

Stop if the relative change of the criterion is below..

Stop if the relative change of the criterion is below..

maxstep
= 2; double in (0, inf)

Maximal absolute step size.

Maximal absolute step size.

maxiter
= 200; uint in [1, inf)

Stopping criterion: the maximum number of iterations.

Stopping criterion: the maximum number of iterations.

minstep
= 0.1; double in (0, inf)

Minimal absolute step size.

Minimal absolute step size.

xtola
= 0.01; double in [0, inf)

Stop if the infnorm of the change applied to x is below this value..

Stop if the infnorm of the change applied to x is below this value..
 gdsq
 Gradient descent with quadratic step estimation, supported parameters are:

ftolr
= 0; double in [0, inf)

Stop if the relative change of the criterion is below..

Stop if the relative change of the criterion is below..

gtola
= 0; double in [0, inf)

Stop if the infnorm of the gradient is below this value..

Stop if the infnorm of the gradient is below this value..

maxiter
= 100; uint in [1, inf)

Stopping criterion: the maximum number of iterations.

Stopping criterion: the maximum number of iterations.

scale
= 2; double in (1, inf)

Fallback fixed step size scaling.

Fallback fixed step size scaling.

step
= 0.1; double in (0, inf)

Initial step size.

Initial step size.

xtola
= 0; double in [0, inf)

Stop if the infnorm of xupdate is below this value..

Stop if the infnorm of xupdate is below this value..
 gsl
 optimizer plugin based on the multimin optimizers ofthe GNU Scientific Library (GSL) https://www.gnu.org/software/gsl/, supported parameters are:

eps
= 0.01; double in (0, inf)

gradient based optimizers: stop when grad < eps, simplex: stop when simplex size < eps..

gradient based optimizers: stop when grad < eps, simplex: stop when simplex size < eps..

iter
= 100; uint in [1, inf)

maximum number of iterations.

maximum number of iterations.

opt
= gd; dict

Specific optimizer to be used..
Supported values are:
 bfgs  BroydenFletcherGoldfarbShann
 bfgs2  BroydenFletcherGoldfarbShann (most efficient version)
 cgfr  FlecherReeves conjugate gradient algorithm
 gd  Gradient descent.
 simplex  Simplex algorithm of Nelder and Mead
 cgpr  PolakRibiere conjugate gradient algorithm

Specific optimizer to be used..
Supported values are:

step
= 0.001; double in (0, inf)

initial step size.

initial step size.

tol
= 0.1; double in (0, inf)

some tolerance parameter.

some tolerance parameter.
 nlopt
 Minimizer algorithms using the NLOPT library, for a description of the optimizers please see 'http://abinitio.mit.edu/wiki/index.php/NLopt_Algorithms', supported parameters are:

ftola
= 0; double in [0, inf)

Stopping criterion: the absolute change of the objective value is below this value.

Stopping criterion: the absolute change of the objective value is below this value.

ftolr
= 0; double in [0, inf)

Stopping criterion: the relative change of the objective value is below this value.

Stopping criterion: the relative change of the objective value is below this value.

higher
= inf; double

Higher boundary (equal for all parameters).

Higher boundary (equal for all parameters).

localopt
= none; dict

local minimization algorithm that may be required for the main minimization algorithm..
Supported values are:
 gnorigdirectl  Dividing Rectangles (original implementation, locally biased)
 gndirectlnoscal  Dividing Rectangles (unscaled, locally biased)
 gnisres  Improved Stochastic Ranking Evolution Strategy
 ldtnewton  Truncated Newton
 gndirectlrand  Dividing Rectangles (locally biased, randomized)
 lnnewuoa  Derivativefree Unconstrained Optimization by Iteratively Constructed Quadratic Approximation
 gndirectlrandnoscale  Dividing Rectangles (unscaled, locally biased, randomized)
 gnorigdirect  Dividing Rectangles (original implementation)
 ldtnewtonprecond  Preconditioned Truncated Newton
 ldtnewtonrestart  Truncated Newton with steepestdescent restarting
 gndirect  Dividing Rectangles
 lnneldermead  NelderMead simplex algorithm
 lncobyla  Constrained Optimization BY Linear Approximation
 gncrs2lm  Controlled Random Search with Local Mutation
 ldvar2  Shifted LimitedMemory VariableMetric, Rank 2
 ldvar1  Shifted LimitedMemory VariableMetric, Rank 1
 ldmma  Method of Moving Asymptotes
 ldlbfgsnocedal  None
 ldlbfgs  Lowstorage BFGS
 gndirectl  Dividing Rectangles (locally biased)
 none  don't specify algorithm
 lnbobyqa  Derivativefree Boundconstrained Optimization
 lnsbplx  Subplex variant of NelderMead
 lnnewuoabound  Derivativefree Boundconstrained Optimization by Iteratively Constructed Quadratic Approximation
 lnpraxis  Gradientfree Local Optimization via the PrincipalAxis Method
 gndirectnoscal  Dividing Rectangles (unscaled)
 ldtnewtonprecondrestart  Preconditioned Truncated Newton with steepestdescent restarting

local minimization algorithm that may be required for the main minimization algorithm..
Supported values are:

lower
= inf; double

Lower boundary (equal for all parameters).

Lower boundary (equal for all parameters).

maxiter
= 100; int in [1, inf)

Stopping criterion: the maximum number of iterations.

Stopping criterion: the maximum number of iterations.

opt
= ldlbfgs; dict

main minimization algorithm.
Supported values are:
 gnorigdirectl  Dividing Rectangles (original implementation, locally biased)
 gmlsllds  MultiLevel SingleLinkage (lowdiscrepancysequence, require local gradient based optimization and bounds)
 gndirectlnoscal  Dividing Rectangles (unscaled, locally biased)
 gnisres  Improved Stochastic Ranking Evolution Strategy
 ldtnewton  Truncated Newton
 gndirectlrand  Dividing Rectangles (locally biased, randomized)
 lnnewuoa  Derivativefree Unconstrained Optimization by Iteratively Constructed Quadratic Approximation
 gndirectlrandnoscale  Dividing Rectangles (unscaled, locally biased, randomized)
 gnorigdirect  Dividing Rectangles (original implementation)
 ldtnewtonprecond  Preconditioned Truncated Newton
 ldtnewtonrestart  Truncated Newton with steepestdescent restarting
 gndirect  Dividing Rectangles
 auglageq  Augmented Lagrangian algorithm with equality constraints only
 lnneldermead  NelderMead simplex algorithm
 lncobyla  Constrained Optimization BY Linear Approximation
 gncrs2lm  Controlled Random Search with Local Mutation
 ldvar2  Shifted LimitedMemory VariableMetric, Rank 2
 ldvar1  Shifted LimitedMemory VariableMetric, Rank 1
 ldmma  Method of Moving Asymptotes
 ldlbfgsnocedal  None
 gmlsl  MultiLevel SingleLinkage (require local optimization and bounds)
 ldlbfgs  Lowstorage BFGS
 gndirectl  Dividing Rectangles (locally biased)
 lnbobyqa  Derivativefree Boundconstrained Optimization
 lnsbplx  Subplex variant of NelderMead
 lnnewuoabound  Derivativefree Boundconstrained Optimization by Iteratively Constructed Quadratic Approximation
 auglag  Augmented Lagrangian algorithm
 lnpraxis  Gradientfree Local Optimization via the PrincipalAxis Method
 gndirectnoscal  Dividing Rectangles (unscaled)
 ldtnewtonprecondrestart  Preconditioned Truncated Newton with steepestdescent restarting
 ldslsqp  Sequential LeastSquares Quadratic Programming

main minimization algorithm.
Supported values are:

step
= 0; double in [0, inf)

Initial step size for gradient free methods.

Initial step size for gradient free methods.

stop
= inf; double

Stopping criterion: function value falls below this value.

Stopping criterion: function value falls below this value.

xtola
= 0; double in [0, inf)

Stopping criterion: the absolute change of all xvalues is below this value.

Stopping criterion: the absolute change of all xvalues is below this value.

xtolr
= 0; double in [0, inf)

Stopping criterion: the relative change of all xvalues is below this value.

Stopping criterion: the relative change of all xvalues is below this value.
EXAMPLE
Register the image series given by images imageXXXX.v by optimizing a spline based transformation with a coefficient rate of 16 pixel, skipping two images at the beginning and using normalized gradient fields as initial cost measure and SSD as final measure. Penalize the transformation by using divcurl with aweight of 2.0. As optimizer an nlopt based newton method is used. mia3dprealignnonrigid mia3dprealignnonrigid i imageXXXX.v o registered t vista k 2F spline:rate=16,penalty=[divcurl:weight=2] 1 image:cost=[ngf:eval=ds] 2 image:cost=ssd O nlopt:opt=ldvar1,xtola=0.001,ftolr=0.001,maxiter=300
AUTHOR(s)
Gert WollnyCOPYRIGHT
This software is Copyright (c) 19992015 Leipzig, Germany and Madrid, Spain. It comes with ABSOLUTELY NO WARRANTY and you may redistribute it under the terms of the GNU GENERAL PUBLIC LICENSE Version 3 (or later). For more information run the program with the option 'copyright'.