mia-2dmyomilles {-i string} {-o string} [ options ...]


This program is use to run a modified version of the ICA based registration approach described in

Milles et al. 'Fully Automated Motion Correction in First-Pass Myocardial Perfusion MR Image Sequences', Trans. Med. Imaging., 27(11), 1611-1621, 2008.

Changes include the extraction of the quasi-periodic movement in free breathingly acquired data sets and the option to run affine or rigid registration instead of the optimization of translations only.



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

input perfusion data set

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

output perfusion data set

-r, --registered=STRING

file name base for registered files


save synthetic reference images to this file base


save cropped image set to this file


save the features images resulting from the ICA and some intermediate images used for the RV-LV segmentation with the given file name base to PNG files. Also save the coefficients of the initial best and the final IC mixing matrix.

Help & Info

-V, --verbose=warning; dict

verbosity of output, print messages of given level and higher priorities. Supported priorities starting at lowest level are:

debug:Debug output
message:Normal messages
info:Low level messages
error:Report errors
fatal:Report only fatal errors
trace:Function call trace
fail:Report test failures
--copyright=(); bool

print copyright information

-h, --help=(); bool

print this help

-?, --usage=(); bool

print a short help

--version=(); bool

print the version number and exit


--fastica=internal; factory

FastICA implementationto be used. For supported plug-ins see Plugin type: fastica/implementation

-C, --components=0; ulong

ICA components 0 = automatic estimation


normalized ICs


don't strip the mean from the mixing curves

-g, --guess

use initial guess for myocardial perfusion

-s, --segscale=1.4; float

segment and scale the crop box around the LV (0=no segmentation)

-k, --skip=0; ulong

skip images at the beginning of the series as they are of other modalities

-m, --max-ica-iter=400; ulong

maximum number of iterations in ICA

-E, --segmethod=features; dict

Segmentation method

delta-peak:difference of the peak enhancement images
delta-feature:difference of the feature images
features:feature images


--threads=-1; int

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).


-c, --cost=ssd; stringSTRING

registration criterion

-O, --optimizer=gsl:opt=simplex,step=1.0; factory

Optimizer used for minimization. For supported plug-ins see Plugin type: minimizer/singlecost

-f, --transForm=rigid; factory

transformation type. For supported plug-ins see Plugin type: 2dimage/transform

-l, --mg-levels=3; ulong

multi-resolution levels

-R, --reference=-1; int

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 movement

-P, --passes=2; ulong

registration passes


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'.

mia-2dmyomilles   -i segment.set -o registered.set -k 2


Gert Wollny