mia-2dmyocard-icaseries {-i string} [ options ...]


This program is used to run a ICA on a series of myocardial perfusion images given in a segmentation set in order to create sythetic references that can be used for motion correction by image registration. If the aim is to run a full motion compensation then it is better run mia-2dmyoica-nonrigid, since this program is essentially the same without the registration bits.



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

input perfusion data set

-r, --references=(output); string

File name base for the reference images. Image type and numbering scheme are taken from the input images.

-c, --save-cropped=(output); string

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

--save-feature=(output); string

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

-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).


Evaluate the synthetic references from set segment.set and save them to refXXXX.??? by using five independend components, and skipping 2 images. Per default a bounding box around the LV will be segmented and scaled by 1.4 and the cropped images will be saved to cropXXXX.??? and a segmentation set cropped.set is created. The image file type ??? is deducted from the input images in segment.set.

mia-2dmyocard-icaseries -i segment.set -r ref -o ref -k 2 -C 5


Gert Wollny