SYNOPSIS

mia-2dmyoicapgt -i <in-file> -o <out-file> [options]

DESCRIPTION

mia-2dmyoicapgt This program implements a two passs motion compensation algorithm. First a linear registration is run based on a variation of Gupta et~al. "Fully automatic registration and segmentation of first-pass myocardial perfusion MR image sequences", Academic Radiology 17, 1375-1385 as described in in Wollny G, Kellman P, Santos A, Ledesma-Carbayo M-J, "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, followed by a non-linear registration based 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. This version of the program may run all registrations in parallel.

OPTIONS

Pseudo Ground Thruth estimation

-A --alpha=0.1

spacial neighborhood penalty weightspacial neighborhood penalty weight

-B --beta=4

temporal second derivative penalty weighttemporal second derivative penalty weight

-T --rho-thresh=0.85

correlation threshold for neighborhood analysiscorrelation threshold for neighborhood analysis

File-IO

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

input perfusion data set

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

output perfusion data set

-r --registered=

File name base for the registered images. Image type and numbering scheme are taken from the input images as given in the input data set.

--save-cropped=(output); string

save cropped set to this file, the image files will use the stem of the name as file name base

--save-feature=(output); string

save segmentation feature images and initial ICA mixing matrix

--save-refs=(output); string

for each registration pass save the reference images to files with the given name base

--save-regs=(output); string

for each registration pass 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

--no-meanstrip

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 --max-ica-iter=400

maximum number of iterations in ICAmaximum number of iterations in ICA

-E --segmethod=features

Segmentation method

delta-peak - difference of the peak enhancement images

features - feature images

delta-feature - difference of the feature images

-b --min-breathing-frequency=-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. A value 0.0 forces the series to be indentified as acquired with initial breath hold.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. A value 0.0 forces the series to be indentified as acquired with initial breath hold.

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

-L --linear-optimizer=gsl:opt=simplex,step=1.0

Optimizer used for minimization of the linear registration The string value will be used to construct a plug-in. For supported plugins see PLUGINS:minimizer/singlecost

--linear-transform=affine

linear transform to be used The string value will be used to construct a plug-in. For supported plugins see PLUGINS:2dimage/transform

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

Optimizer used for minimization in the non-linear registration. The string value will be used to construct a plug-in. For supported plugins see PLUGINS:minimizer/singlecost

-a --start-c-rate=16

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

--c-rate-divider=2

Cofficient rate divider for each pass.Cofficient rate divider for each pass.

-d --start-divcurl=10000

Start divcurl weight, gets divided by --divcurl-divider with every pass.Start divcurl weight, gets divided by --divcurl-divider with every pass.

--divcurl-divider=2

Divcurl weight scaling with each new pass.Divcurl weight scaling with each new pass.

-R --reference=-1

Global reference all image should be aligned to. If set to a non-negative value, the images will be aligned to this references, and the cropped output image date will be injected into the original images. Leave at -1 if you don't care. In this case all images with be registered to a mean position of the movementGlobal reference all image should be aligned to. If set to a non-negative value, the images will be aligned to this references, and the cropped output image date will be injected into the original images. Leave at -1 if you don't care. In this case all images with be registered to a mean position of the movement

-w --imagecost=image:weight=1,cost=ssd

image cost, do not specify the src and ref parameters, these will be set by the program. The string value will be used to construct a plug-in. For supported plugins see PLUGINS:2dimage/fullcost

-l --mg-levels=3

multi-resolution levelsmulti-resolution levels

-p --linear-passes=3

linear registration passes (0 to disable)linear registration passes (0 to disable)

-P --nonlinear-passes=3

non-linear registration passes (0 to disable)non-linear registration passes (0 to disable)

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

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: 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.

lsd

Least-Squares 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.

mbins = 64; uint in [1, 256]

Number of histogram bins used for the moving image.

mkernel = [bspline:d=3]; factory

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

rbins = 64; uint in [1, 256]

Number of histogram bins used for the reference image.

rkernel = [bspline:d=0]; factory

Spline kernel for reference image parzen hinstogram. For supported plug-ins 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

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.

norm = 0; bool

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

ssd-automask

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.

sthresh = 0; double

Threshold intensity value for source image.

PLUGINS: 2dimage/fullcost

image

Generalized image similarity cost function that also handles multi-resolution processing. The actual similarity measure is given es extra parameter., supported parameters are:

cost = ssd; factory

Cost function kernel. For supported plug-ins see PLUGINS:2dimage/cost

debug = 0; bool

Save intermediate resuts for debugging.

ref =(input, string)

Reference image.

src =(input, string)

Study image.

weight = 1; float

weight of cost function.

labelimage

Similarity cost function that maps labels of two images and handles label-preserving multi-resolution processing., supported parameters are:

debug = 0; int in [0, 1]

write the distance transforms to a 3D image.

maxlabel = 256; int in [2, 32000]

maximum number of labels to consider.

ref =(input, string)

Reference image.

src =(input, string)

Study image.

weight = 1; float

weight of cost function.

maskedimage

Generalized masked image similarity cost function that also handles multi-resolution processing. The provided masks should be densly filled regions in multi-resolution 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 plug-ins see PLUGINS:2dimage/maskedcost

ref =(input, string)

Reference image.

ref-mask =(input, string)

Reference image mask (binary).

src =(input, string)

Study image.

src-mask =(input, string)

Study image mask (binary).

weight = 1; float

weight of cost function.

PLUGINS: 2dimage/io

bmp

BMP 2D-image 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: .@

 

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 2D-image 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 2D-image 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.

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.

mbins = 64; uint in [1, 256]

Number of histogram bins used for the moving image.

mkernel = [bspline:d=3]; factory

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

rbins = 64; uint in [1, 256]

Number of histogram bins used for the reference image.

rkernel = [bspline:d=0]; factory

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

ncc

normalized cross correlation with masking support.

(no parameters)

ssd

Sum of squared differences with masking.

(no parameters)

PLUGINS: 2dimage/transform

affine

Affine transformation (six degrees of freedom)., supported parameters are:

imgboundary = mirror; factory

image interpolation boundary conditions. For supported plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

rigid

Rigid transformations (i.e. rotation and translation, three degrees of freedom)., supported parameters are:

imgboundary = mirror; factory

image interpolation boundary conditions. For supported plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

rot-center = [[0,0]]; 2dfvector

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

rotation

Rotation transformations (i.e. rotation about a given center, one degree of freedom)., supported parameters are:

imgboundary = mirror; factory

image interpolation boundary conditions. For supported plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

rot-center = [[0,0]]; 2dfvector

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

spline

Free-form transformation that can be described by a set of B-spline coefficients and an underlying B-spline kernel., supported parameters are:

anisorate = [[0,0]]; 2dfvector

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

imgboundary = mirror; factory

image interpolation boundary conditions. For supported plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

kernel = [bspline:d=3]; factory

transformation spline kernel.. For supported plug-ins see PLUGINS:1d/splinekernel

penalty = ; factory

Transformation penalty term. For supported plug-ins see PLUGINS:2dtransform/splinepenalty

rate = 10; float in [1, inf)

isotropic coefficient rate in pixels.

translate

Translation only (two degrees of freedom), supported parameters are:

imgboundary = mirror; factory

image interpolation boundary conditions. For supported plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

vf

This plug-in 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 plug-ins see PLUGINS:1d/splinebc

imgkernel = [bspline:d=3]; factory

image interpolator kernel. For supported plug-ins see PLUGINS:1d/splinekernel

PLUGINS: 2dtransform/splinepenalty

divcurl

divcurl penalty on the transformation, supported parameters are:

curl = 1; float in [0, inf)

penalty weight on curl.

div = 1; float in [0, inf)

penalty weight on divergence.

norm = 0; bool

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.

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 in 'segment.set' by first using automatic ICA estimation to run the linear registration and then the PGT registration. Skip two images at the beginning and otherwiese use the default parameters. Store the result in 'registered.set'.

mia-2dmyoicapgt -i segment.set -o registered.set -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'.