brains:BRAINSClassPlugs

From NITRC Wiki

Return to brains:MainPage

Summary

This program will generate exemplars of pure tissue. These have also been termed plugs. Random regions of the specified size are selected and those with a minimum variance are retained. The retained plugs are then clustered using k-means to separate the samples in gray matter, white matter, and CSF. The plugs will then be used by brains:BRAINSTissueClassify to perform the classic BRAINS continuous tissue classification.

Authors

• Vincent A. Magnotta
• Greg Harris

Usage

BRAINSClassPlugs  [--returnparameterfile <std::string>]
                  [--processinformationaddress <std::string>] [--xml]
                  [--echo] [--vbPlugs <std::string>] [--bloodImage <T1
                  |T2|PD>] [--bloodMode <Manual|Top|Bottom>]
                  [--numberOfClassPlugs <std::vector<int>>]
                  [--partitions <std::vector<int>>] [--plugSize
                  <float>] [--varOutlier <float>] [--meanOutlier
                  <float>] [--permissiveness <float>] [--coverage
                  <float>] [--numberOfPlugs <int>] [--randomSeed
                  <int>] [--pdClassMeans <std::vector<float>>]
                  [--t2ClassMeans <std::vector<float>>]
                  [--t1ClassMeans <std::vector<float>>]
                  [--plugClassNames <std::vector<std::string>>]
                  [--csfPlugs <std::string>] [--wmPlugs <std::string>]
                  [--gmPlugs <std::string>] [--searchVolume
                  <std::string>] [--pdVolume <std::string>]
                  [--t2Volume <std::string>] [--t1Volume
                  <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)

--vbPlugs <std::string>
Plugs for Venous Blood

--bloodImage <T1|T2|PD>
Image to be used for defining venous blood. Used if Blood Mode is either Top or Bottom (default: T1)

--bloodMode <Manual|Top|Bottom>
Used to define how blood is defined (default: Manual)

--numberOfClassPlugs <std::vector<int>>
Number of class plugs for GM, WM, and CSF (default: 4000,2000,200)

--partitions <std::vector<int>>
Number of partitions in X, Y, and Z (default: 1,1,1)

--plugSize <float>
Plug Size (default: 2)

--varOutlier <float>
Plug Varience Outlier (default: 10)

--meanOutlier <float>
Plug Mean Outlier (default: 1.25)

--permissiveness <float>
Plug permissiveness (default: 0.5)

--coverage <float>
Plug coverage for serach space (0-1) (default: 0.85)

--numberOfPlugs <int>
Number of plugs to consider for class exemplars (default: 4000)

--randomSeed <int>
Seed for random number generator (default: 0)

--pdClassMeans <std::vector<float>>
Class means based on the PD weighted image (default: 173.143585 ,140.521729,190.218933,47.0)

--t2ClassMeans <std::vector<float>>
Class means based on the T2 weighted image (default: 117.773056 ,84.270554,222.857208,68.8)

--t1ClassMeans <std::vector<float>>
Class means based on the T1 weighted image (default: 80.186111 ,113.979065,30.087282,10.8)

--plugClassNames <std::vector<std::string>>
Fixed Image Mask (default: gm,wm,csf)

--csfPlugs <std::string>
Plugs for CSF

--wmPlugs <std::string>
Plugs for White Matter

--gmPlugs <std::string>
Plugs for Grey Matter

--searchVolume <std::string>
Search Volume

--pdVolume <std::string>
PD Volume

--t2Volume <std::string>
T2 Volume

--t1Volume <std::string>
T1 Volume

--, --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

Gray Matter Plugs

White Matter Plugs

References

1. Harris G, Andreasen NC, Cizadlo T, Bailey JM, Bockholt HJ, Magnotta VA, Arndt S. Improving tissue classification in MRI: a three-dimensional multispectral discriminant analysis method with automated training class selection. J Comput Assist Tomogr. 1999 Jan-Feb;23(1):144-54.

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.