This is the command mia-2dgroundtruthreg that can be run in the OnWorks free hosting provider using one of our multiple free online workstations such as Ubuntu Online, Fedora Online, Windows online emulator or MAC OS online emulator

**PROGRAM:**

**NAME**

mia-2dgroundtruthreg - Registration of a series of 2D images

**SYNOPSIS**

**mia-2dgroundtruthreg**

**-i**

**<in-file>**

**-o**

**<out-file>**

**-A**

**<alpha>**

**-B**

**<beta>**

**-R**

**<rho_thresh>**

**[options]**

**DESCRIPTION**

**mia-2dgroundtruthreg**This program implements the non-linear registration based on Pseudo

Ground Thruth for motion compensation of series of myocardial perfusion images as decribed

in Chao Li and Ying Sun, 'Nonrigid Registration of Myocardial Perfusion MRI Using Pseudo

Ground Truth' , In Proc. Medical Image Computing and Computer-Assisted Intervention MICCAI

2009, 165-172, 2009. Note that for this nonlinear motion correction a preceding linear

registration step is usually required.

**OPTIONS**

**File-IO**

-i --in-file=(input, required); string

input perfusion data set

-o --out-file=(output, required); string

output perfusion data set

-r --registered=reg

file name base for registered files

**Preconditions**

-s --skip=2

skip images at beginning of seriesskip images at beginning of series

-P --passes=4

number of registration passesnumber of registration passes

**Pseudo-Ground-Thruth**

-A --alpha=(required); double

spacial neighborhood penalty weightspacial neighborhood penalty weight

-B --beta=(required); double

temporal second derivative penalty weighttemporal second derivative penalty

weight

-R --rho_thresh=(required); double

correlation threshold for neighborhood analysiscorrelation threshold for

neighborhood analysis

**Registration**

-O --optimizer=gsl:opt=gd,step=0.1

Optimizer used for minimizationOptimizer used for minimization For

supported plugins see PLUGINS:minimizer/singlecost

-p --interpolator=bspline:d=3

image interpolator kernelimage interpolator kernel For supported plugins

see PLUGINS:1d/splinekernel

-l --mr-levels=3

multi-resolution levelsmulti-resolution levels

-d --divcurl=20

divcurl regularization weightdivcurl regularization weight

--divcurl-divider=4

divcurl weight scaling with each new passdivcurl weight scaling with each

new pass

-a --start-c-rate=32

start coefficinet rate in spines, gets divided by --c-rate-divider with

every passstart coefficinet rate in spines, gets divided by --c-rate-divider

with every pass

--c-rate-divider=4

cofficient rate divider for each passcofficient rate divider for each pass

-w --imageweight=1

image cost weightimage cost weight

**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**B-spline kernel creation , supported parameters are:

__d__= 3; int in [0, 5]

Spline degree.

**omoms**OMoms-spline kernel creation, supported parameters are:

__d__= 3; int in [3, 3]

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..

__max-step__= 2; double in (0, inf)

Maximal absolute step size.

__maxiter__= 200; uint in [1, inf)

Stopping criterion: the maximum number of iterations.

__min-step__= 0.1; double in (0, inf)

Minimal absolute step size.

__xtola__= 0.01; double in [0, inf)

Stop if the inf-norm 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..

__gtola__= 0; double in [0, inf)

Stop if the inf-norm of the gradient is below this value..

__maxiter__= 100; uint in [1, inf)

Stopping criterion: the maximum number of iterations.

__scale__= 2; double in (1, inf)

Fallback fixed step size scaling.

__step__= 0.1; double in (0, inf)

Initial step size.

__xtola__= 0; double in [0, inf)

Stop if the inf-norm of x-update 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..

__iter__= 100; uint in [1, inf)

maximum number of iterations.

__opt__= gd; dict

Specific optimizer to be used.. Supported values are:

__bfgs__‐ Broyden-Fletcher-Goldfarb-Shann

__bfgs2__‐ Broyden-Fletcher-Goldfarb-Shann (most efficient version)

__cg-fr__‐ Flecher-Reeves conjugate gradient algorithm

__gd__‐ Gradient descent.

__simplex__‐ Simplex algorithm of Nelder and Mead

__cg-pr__‐ Polak-Ribiere conjugate gradient algorithm

__step__= 0.001; double in (0, inf)

initial step size.

__tol__= 0.1; double in (0, inf)

some tolerance parameter.

**nlopt**Minimizer algorithms using the NLOPT library, for a description of the

optimizers please see 'http://ab-

initio.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.

__ftolr__= 0; double in [0, inf)

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

this value.

__higher__= inf; double

Higher boundary (equal for all parameters).

__local-opt__= none; dict

local minimization algorithm that may be required for the main

minimization algorithm.. Supported values are:

__gn-orig-direct-l__‐ Dividing Rectangles (original implementation,

locally biased)

__gn-direct-l-noscal__‐ Dividing Rectangles (unscaled, locally biased)

__gn-isres__‐ Improved Stochastic Ranking Evolution Strategy

__ld-tnewton__‐ Truncated Newton

__gn-direct-l-rand__‐ Dividing Rectangles (locally biased, randomized)

__ln-newuoa__‐ Derivative-free Unconstrained Optimization by Iteratively

Constructed Quadratic Approximation

__gn-direct-l-rand-noscale__‐ Dividing Rectangles (unscaled, locally

biased, randomized)

__gn-orig-direct__‐ Dividing Rectangles (original implementation)

__ld-tnewton-precond__‐ Preconditioned Truncated Newton

__ld-tnewton-restart__‐ Truncated Newton with steepest-descent restarting

__gn-direct__‐ Dividing Rectangles

__ln-neldermead__‐ Nelder-Mead simplex algorithm

__ln-cobyla__‐ Constrained Optimization BY Linear Approximation

__gn-crs2-lm__‐ Controlled Random Search with Local Mutation

__ld-var2__‐ Shifted Limited-Memory Variable-Metric, Rank 2

__ld-var1__‐ Shifted Limited-Memory Variable-Metric, Rank 1

__ld-mma__‐ Method of Moving Asymptotes

__ld-lbfgs-nocedal__‐ None

__ld-lbfgs__‐ Low-storage BFGS

__gn-direct-l__‐ Dividing Rectangles (locally biased)

__none__‐ don't specify algorithm

__ln-bobyqa__‐ Derivative-free Bound-constrained Optimization

__ln-sbplx__‐ Subplex variant of Nelder-Mead

__ln-newuoa-bound__‐ Derivative-free Bound-constrained Optimization by

Iteratively Constructed Quadratic Approximation

__ln-praxis__‐ Gradient-free Local Optimization via the Principal-Axis

Method

__gn-direct-noscal__‐ Dividing Rectangles (unscaled)

__ld-tnewton-precond-restart__‐ Preconditioned Truncated Newton with

steepest-descent restarting

__lower__= -inf; double

Lower boundary (equal for all parameters).

__maxiter__= 100; int in [1, inf)

Stopping criterion: the maximum number of iterations.

__opt__= ld-lbfgs; dict

main minimization algorithm. Supported values are:

__gn-orig-direct-l__‐ Dividing Rectangles (original implementation,

locally biased)

__g-mlsl-lds__‐ Multi-Level Single-Linkage (low-discrepancy-sequence,

require local gradient based optimization and bounds)

__gn-direct-l-noscal__‐ Dividing Rectangles (unscaled, locally biased)

__gn-isres__‐ Improved Stochastic Ranking Evolution Strategy

__ld-tnewton__‐ Truncated Newton

__gn-direct-l-rand__‐ Dividing Rectangles (locally biased, randomized)

__ln-newuoa__‐ Derivative-free Unconstrained Optimization by Iteratively

Constructed Quadratic Approximation

__gn-direct-l-rand-noscale__‐ Dividing Rectangles (unscaled, locally

biased, randomized)

__gn-orig-direct__‐ Dividing Rectangles (original implementation)

__ld-tnewton-precond__‐ Preconditioned Truncated Newton

__ld-tnewton-restart__‐ Truncated Newton with steepest-descent restarting

__gn-direct__‐ Dividing Rectangles

__auglag-eq__‐ Augmented Lagrangian algorithm with equality constraints

only

__ln-neldermead__‐ Nelder-Mead simplex algorithm

__ln-cobyla__‐ Constrained Optimization BY Linear Approximation

__gn-crs2-lm__‐ Controlled Random Search with Local Mutation

__ld-var2__‐ Shifted Limited-Memory Variable-Metric, Rank 2

__ld-var1__‐ Shifted Limited-Memory Variable-Metric, Rank 1

__ld-mma__‐ Method of Moving Asymptotes

__ld-lbfgs-nocedal__‐ None

__g-mlsl__‐ Multi-Level Single-Linkage (require local optimization and

bounds)

__ld-lbfgs__‐ Low-storage BFGS

__gn-direct-l__‐ Dividing Rectangles (locally biased)

__ln-bobyqa__‐ Derivative-free Bound-constrained Optimization

__ln-sbplx__‐ Subplex variant of Nelder-Mead

__ln-newuoa-bound__‐ Derivative-free Bound-constrained Optimization by

Iteratively Constructed Quadratic Approximation

__auglag__‐ Augmented Lagrangian algorithm

__ln-praxis__‐ Gradient-free Local Optimization via the Principal-Axis

Method

__gn-direct-noscal__‐ Dividing Rectangles (unscaled)

__ld-tnewton-precond-restart__‐ Preconditioned Truncated Newton with

steepest-descent restarting

__ld-slsqp__‐ Sequential Least-Squares Quadratic Programming

__step__= 0; double in [0, inf)

Initial step size for gradient free methods.

__stop__= -inf; double

Stopping criterion: function value falls below this value.

__xtola__= 0; double in [0, inf)

Stopping criterion: the absolute change of all x-values is below this

value.

__xtolr__= 0; double in [0, inf)

Stopping criterion: the relative change of all x-values is below this

value.

**EXAMPLE**

Register the perfusion series given by images imageXXXX.exr by using Pseudo Ground Truth

estimation. Skip two images at the beginning and otherwiese use the default parameters.

Store the result images to 'regXXXX.exr'.

mia-2dgroundtruthreg -i imageXXXX.exr -o regXXXX.exr -k 2

**AUTHOR(s)**

Gert Wollny

**COPYRIGHT**

This software is Copyright (c) 1999‐2015 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'.

Use mia-2dgroundtruthreg online using onworks.net services