SYNOPSIS
mia2dmyoicanonrigid i <infile> o <outfile> [options]DESCRIPTION
mia2dmyoicanonrigid This program implements the motion compensation algorithm described in Wollny G, Kellman P, Santos A, LedesmaCarbayo MJ, "Automatic Motion Compensation of Free Breathing acquired Myocardial Perfusion Data by using Independent Component Analysis" Medical Image Analysis, 2012, DOI:10.1016/j.media.2012.02.004.OPTIONS
FileIO

 i infile=(input, required); string
 input perfusion data set
 o outfile=(output, required); string
 output perfusion data set
 r registered=reg
 file name base for registered fiels
 savecropped=
 save cropped set to this file
 savefeature=
 save the features images resulting from the ICA and some intermediate images used for the RVLV segmentation with the given file name base to PNG files. Also save the coefficients of the initial best and the final IC mixing matrix.
 saverefs=
 save synthetic reference images
 saveregs=
 save intermediate registered images
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
ICA

 C components=0
 ICA components 0 = automatic estimationICA components 0 = automatic estimation
 normalize
 normalized ICs
 nomeanstrip
 don't strip the mean from the mixing curves
 s segscale=0
 segment and scale the crop box around the LV (0=no segmentation)segment and scale the crop box around the LV (0=no segmentation)
 k skip=0
 skip images at the beginning of the series e.g. because as they are of other modalitiesskip images at the beginning of the series e.g. because as they are of other modalities
 m maxicaiter=400
 maximum number of iterations in ICAmaximum number of iterations in ICA
 E segmethod=features

Segmentation method
 deltapeak  difference of the peak enhancement images
 features  feature images
 deltafeature  difference of the feature images
 b minbreathingfrequency=1
 minimal mean frequency a mixing curve can have to be considered to stem from brething. A healthy rest breating rate is 12 per minute. A negative value disables the test.minimal mean frequency a mixing curve can have to be considered to stem from brething. A healthy rest breating rate is 12 per minute. A negative value disables the test.
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).
Registration

 O optimizer=gsl:opt=gd,step=0.1
 Optimizer used for minimizationOptimizer used for minimization For supported plugins see PLUGINS:minimizer/singlecost
 R refiner=
 optimizer used for refinement after the main optimizer was calledoptimizer used for refinement after the main optimizer was called For supported plugins see PLUGINS:minimizer/singlecost
 a startcrate=16
 start coefficinet rate in spines, gets divided by cratedivider with every passstart coefficinet rate in spines, gets divided by cratedivider with every pass
 cratedivider=2
 cofficient rate divider for each passcofficient rate divider for each pass
 d startdivcurl=10
 start divcurl weight, gets divided by divcurldivider with every passstart divcurl weight, gets divided by divcurldivider with every pass
 divcurldivider=2
 divcurl weight scaling with each new passdivcurl weight scaling with each new pass
 w imagecost=image:weight=1,cost=ssd
 image costimage cost For supported plugins see PLUGINS:2dimage/fullcost
 l mglevels=3
 multiresolution levelsmultiresolution levels
 P passes=5
 registration passesregistration passes
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: 2dimage/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.
 lsd
 LeastSquares Distance measure
 (no parameters)
 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. Various evaluation kernels are availabe., supported parameters are:

eval
= ds; dict

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

plugin subtype.
Supported values are:
 ssd
 2D imaga 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
 2D 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: 2dimage/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:2dimage/cost

Cost function kernel.
For supported plugins see PLUGINS:2dimage/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:

debug
= 0; int in [0, 1]

write the distance transforms to a 3D image.

write the distance transforms to a 3D image.

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 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:2dimage/maskedcost

Cost function kernel.
For supported plugins see PLUGINS:2dimage/maskedcost

ref
=(input, string)

Reference image.

Reference image.

refmask
=(input, string)

Reference image mask (binary).

Reference image mask (binary).

src
=(input, string)

Study image.

Study image.

srcmask
=(input, string)

Study image mask (binary).

Study image mask (binary).

weight
= 1; float

weight of cost function.

weight of cost function.
PLUGINS: 2dimage/io
 bmp
 BMP 2Dimage input/output support
 Recognized file extensions: .BMP, .bmp

Supported element types:
 binary data, unsigned 8 bit, unsigned 16 bit
 datapool
 Virtual IO to and from the internal data pool
 Recognized file extensions: [email protected]
 dicom
 2D image io for DICOM
 Recognized file extensions: .DCM, .dcm

Supported element types:
 signed 16 bit, unsigned 16 bit
 exr
 a 2dimage io plugin for OpenEXR images
 Recognized file extensions: .EXR, .exr

Supported element types:
 unsigned 32 bit, floating point 32 bit
 jpg
 a 2dimage io plugin for jpeg gray scale images
 Recognized file extensions: .JPEG, .JPG, .jpeg, .jpg

Supported element types:
 unsigned 8 bit
 png
 a 2dimage io plugin for png images
 Recognized file extensions: .PNG, .png

Supported element types:
 binary data, unsigned 8 bit, unsigned 16 bit
 raw
 RAW 2Dimage output support
 Recognized file extensions: .RAW, .raw

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
 tif
 TIFF 2Dimage input/output support
 Recognized file extensions: .TIF, .TIFF, .tif, .tiff

Supported element types:
 binary data, unsigned 8 bit, unsigned 16 bit, unsigned 32 bit
 vista
 a 2dimage io plugin for vista images
 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
PLUGINS: 2dimage/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: 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 perfusion series given in 'segment.set' by using automatic ICA estimation. Skip two images at the beginning and otherwiese use the default parameters. Store the result in 'registered.set'. mia2dmyoicanonrigid i segment.set o registered.set k 2
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'.