SYNOPSIS
mia2dmyoicanonrigid2 i <infile> o <outfile> [options]DESCRIPTION
mia2dmyoicanonrigid2 This program runs the nonrigid registration of an perfusion image series.In each pass, first an ICA analysis is run to estimate and eliminate the periodic movement and create reference images with intensities similar to the corresponding original image. Then nonrigid registration is run using the an "ssd + divcurl" cost model. The Bspline crate and the divcurl cost weight are changed in each pass according to given parameters.In the first pass a bounding box around the LV myocardium may be extractedto speed up computation Special note to this implemnentation: the registration is always run from the original images to avoid the accumulation of interpolation errors.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 segmentation feature images and initial ICA mixing matrix
ICA

 C components=0
 ICA components 0 = automatic estimationICA components 0 = automatic estimation
 normalize
 don't 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
Registration

 O optimizer=gsl:opt=gd,step=0.1
 Optimizer used for minimizationOptimizer used for minimization For supported plugins see PLUGINS:minimizer/singlecost
 a startcrate=32
 start coefficinet rate in spines, gets divided by cratedivider with every passstart coefficinet rate in spines, gets divided by cratedivider with every pass
 cratedivider=4
 cofficient rate divider for each passcofficient rate divider for each pass
 d startdivcurl=20
 start divcurl weight, gets divided by divcurldivider with every passstart divcurl weight, gets divided by divcurldivider with every pass
 divcurldivider=4
 divcurl weight scaling with each new passdivcurl weight scaling with each new pass
 w imageweight=1
 image cost weightimage cost weight
 p interpolator=bspline:d=3
 image interpolator kernelimage interpolator kernel For supported plugins see PLUGINS:1d/splinekernel
 l mglevels=3
 multiresolution levelsmultiresolution levels
 P passes=3
 registration passesregistration passes
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/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: 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'. mia2dmyoicanonrigid2 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'.