brains:BRAINSKmeansClusterSamples

From NITRC Wiki

Return to brains:mainPage

Summary

This program will perform a Kmeans clustering on to perform a tissue classification on a T1 weighted image. Currently, you need to provide a brain mask. The best solution is to use the SkullStrip program now included in BRAINS. The resulting classification will generate 6 classes. Three classes will be inside the brain region (GM, WM, and CSF) and three will be outside the brain (Air, Fat, muscle/marrow). The input should be a T1 weighted image. In future this could be generalized to other contrasts, but currently the initial class means assume a T1 intensity profile for the classes.

DEFINE the CLass label values

Authors

• Vincent A. Magnotta
• Greg Harris

Usage

 BRAINSKmeansClusterSamples  [--returnparameterfile <std::string>]
                             [--processinformationaddress <std::string>] 
                             [--xml] [--echo]
                             [--outputLabelMapVolume <std::string>]
                             [--labelThresholdValue <int>]
                             [--numberOfStdDeviations <float>]
                             [--input3DSkullStripVolume <std::string>] 
                             [--inputVolume <std::string>] 
                             [--] [--version]
                             [-h]

Where:

--returnparameterfile <std::string>
Filename in which to write simple return parameters (int, float, int-vector, etc.) as opposed to bulk return parameters (image, geometry, transform, measurement, table).

--processinformationaddress <std::string>
Address of a structure to store process information (progress, abort, etc.). (default: 0)

--xml
Produce xml description of command line arguments (default: 0)

--echo
Echo the command line arguments (default: 0)

--outputLabelMapVolume <std::string>
Required: name of output LabelMap image K-Means segmentation

--labelThresholdValue <int>
Mask label to threshold mask for defining the brain (default: 6)

--numberOfStdDeviations <float>
Number of standard deviations above the mean to clip bright arterial blood from input image (default: 0)

--input3DSkullStripVolume <std::string>
Required: input 3DSkullStrip result image file name. If you want to fake this at the moment, you must sum a brain mask 5 times over!

--inputVolume <std::string>
Required: input T1 weighted image file name

--, --ignore_rest
Ignores the rest of the labeled arguments following this flag.

--version
Displays version information and exits.

--h, --help
Displays usage information and exits.

Figures

References

Acknowledgements

This work was developed by the University of Iowa Departments of Radiology and Psychiatry. This software was supported in part of NIH/NINDS award NS050568.