NAME¶

gmm - Gaussian mixture model segmentation

SYNOPSIS¶

gmm InputImage OutputImage PriorImages

DESCRIPTION¶

Segment an image into c classes using the EM algorithm for Gaussian mixtures with optional priors.

OPTIONS¶

Global Toolkit Options (these are shared by all CMTK tools)¶

--help

Write list of basic command line options to standard output.

--help-all

Write complete list of basic and advanced command line options to standard output.

--wiki

Write list of command line options to standard output in MediaWiki markup.

--man

Write man page source in 'nroff' markup to standard output.

--xml

Write command line syntax specification in XML markup (for Slicer integration).

--version

Write toolkit version to standard output.

--echo

Write the current command line to standard output.

--verbose-level <integer>

Set verbosity level.

--verbose, -v

Increment verbosity level by 1 (deprecated; supported for backward compatibility).

--threads <integer>

Set maximum number of parallel threads (for POSIX threads and OpenMP).

General Classification Parameters¶

--mask <string>, -m <string>

Path to foreground mask image. If this is not provided, the input image is used as its own mask, but this does not work properly if the input image itself has pixels with zero or negative values. [Default: NONE]

--classes <integer>, -c <integer>

Number of classes. [Default: 3]

--iterations <integer>, -n <integer>

Number of EM iterations. [Default: 10]

Handling of Priors¶

--priors-init-only

Use priors for initialization only.

--prior-epsilon <double>, -e <double>

Small value to add to all class priors to eliminate zero priors. [Default: 0]

Output Parameters¶

--probability-maps, -p

Write probability maps. The file names for these maps will be generated from the output image path by inserting '_prob#' before the file format suffix, where '#' is the index of the respective class, numbered starting at 1 (zero is background).

AUTHORS¶

Torsten Rohlfing, with contributions from Michael P. Hasak, Greg Jefferis, Calvin R. Maurer, and Daniel B. Russakoff

LICENSE¶

http://www.fsf.org/licensing/licenses/gpl.html

BUGS¶

Report bugs at http://nitrc.org/projects/cmtk/

ACKNOWLEDGMENTS¶

From April 2009 through September 2011, CMTK Development and Maintenance was supported by the National Institute of Biomedical Imaging and Bioengineering under Grant No.R01 EB008381 (PI: Torsten Rohlfing).