Linux Certif

Toute la documentation sur la certification Linux LPI

ImageMath

NAME

ImageMath - part of ANTS registration suite

DESCRIPTION

Usage: ./ImageMath ImageDimension OutputImage.ext Operator Image1.ext Image2.extOrFloat

some options output text files

The last two arguments can be an image or float value Valid Operators : m (multiply) ,

+

(add) ,

- (subtract)

,

/ (divide)

,

^ (power)

,

exp -- take exponent exp(imagevalue*value) addtozero overadd abs total -- sums up values in an image (img2 is the mask) Decision -- computes result=1./(1.+exp(-1.0*( pix1-0.25)/pix2))

Neg (Produce Image Negative ) , G Image1.ext s (Smooth with Gaussian of sigma = s )

MD Image1.ext

s ( Morphological Dilation with radius s ) ,

ME Image1.ext s ( Morphological Erosion with radius s ) ,

MO Image1.ext s ( Morphological Opening with radius s )

MC Image1.ext ( Morphological Closing with radius s )

GD Image1.ext

s ( Grayscale Dilation with radius s ) ,

GE Image1.ext s ( Grayscale Erosion with radius s ) ,

GO Image1.ext s ( Grayscale Opening with radius s )

GC Image1.ext ( Grayscale Closing with radius s )

D (DistanceTransform) ,

Segment Image1.ext N-Classes LocalityVsGlobalityWeight-In-ZeroToOneRange

OptionalPriorImages ( Segment an Image with option of Priors , weight 1 => maximally local/prior-based )

Grad Image.ext S ( Gradient magnitude with sigma s -- if normalize, then output in range [0, 1] ) ,

Laplacian Image.ext S normalize? ( laplacian computed with sigma s --

if normalize, then output in range [0, 1] ) ,

Normalize image.ext opt ( Normalize to [0,1] option instead divides by average value )

PH (Print Header) ,

Byte ( Convert to Byte image in [0,255] )

LabelStats labelimage.ext valueimage.nii ( compute volumes / masses of objects in a label image -- write to text file )

ROIStatistics labelimage.ext valueimage.nii ( see the code )

DiceAndMinDistSum

LabelImage1.ext LabelImage2.ext OptionalDistImage -- outputs DiceAndMinDistSum and Dice Overlap to text log file + optional distance image

Lipschitz

VectorFieldName -- prints to cout & writes to image

InvId VectorFieldName

VectorFieldName -- prints to cout & writes to image

GetLargestComponent InputImage {MinObjectSize}

-- get largest object in image

ThresholdAtMean

Image %ofMean

FlattenImage

Image %ofMax -- replaces values greater than %ofMax*Max to the value %ofMax*Max

stack Image1.nii.gz Image2.nii.gz --- will put these 2 images in the same volume CorruptImage Image NoiseLevel Smoothing TileImages NumColumns ImageList* RemoveLabelInterfaces ImageIn EnumerateLabelInterfaces ImageIn ColoredImageOutname NeighborFractionToIgnore FitSphere GM-ImageIn {WM-Image} {MaxRad-Default=5} HistogramMatch SourceImage ReferenceImage {NumberBins-Default=255} {NumberPoints-Default=64} PadImage ImageIn Pad-Number ( if Pad-Number is negative, de-Padding occurs ) Where Image ValueToLookFor maskImage-option tolerance --- the where function from IDL TensorFA DTImage TensorColor DTImage --- produces RGB values identifying principal directions TensorToVector DTImage WhichVec --- produces vector field identifying one of the principal directions, 2 = largest eigenvalue TensorToVectorComponent DTImage WhichVec --- 0 => 2 produces component of the principal vector field , i.e. largest eigenvalue. 3 = 8 => gets values from the tensor TensorIOTest DTImage --- will write the DT image back out ... tests I/O processes for consistency. MakeImage SizeX SizeY {SizeZ} SetOrGetPixel ImageIn Get/Set-Value IndexX IndexY {IndexZ} -- for example ImageMath 2 outimage.nii SetOrGetPixel Image Get 24 34 -- gets the value at 24, 34

ImageMath 2 outimage.nii SetOrGetPixel Image 1.e9

24 34 -- this sets 1.e9 as the value at 23 34

you can also pass a boolean at the end to force the physical space to be used

TensorMeanDiffusion DTImage CompareHeadersAndImages Image1 Image2 --- tries to find and fix header error! output is the repaired image with new header. never use this if you trust your header information. CountVoxelDifference Image1 Image2 Mask --- the where function from IDL stack image1 image2 --- stack image2 onto image1 CorrelationUpdate Image1 Image2 RegionRadius --- in voxels , Compute update that makes Image2 more like Image1 ConvertImageToFile imagevalues.nii {Optional-ImageMask.nii} -- will write voxel values to a file PValueImage TValueImage dof ConvertToGaussian TValueImage sigma-float ConvertImageSetToMatrix rowcoloption Mask.nii *images.nii -- each row/column contains image content extracted from mask applied to images in *img.nii ConvertVectorToImage Mask.nii vector.nii -- the vector contains image content extracted from a mask - here we return the vector to its spatial origins as image content TriPlanarView ImageIn.nii.gz PercentageToClampLowIntensity PercentageToClampHiIntensity x-slice y-slice z-slice TruncateImageIntensity inputImage {lowerQuantile=0.05} {upperQuantile=0.95} {numberOfBins=65} {binary-maskImage} FillHoles Image parameter : parameter = ratio of edge at object to edge at background = 1 is a definite hole bounded by object only, 0.99 is close -- default of parameter > 1 will fill all holes

PropagateLabelsThroughMask

speed/binaryimagemask.nii.gz initiallabelimage.nii.gz Optional-Stopping-Value -- final output is the propagated label image

optional stopping value -- higher values allow more distant propagation FastMarchingSegmentation speed/binaryimagemask.nii.gz initiallabelimage.nii.gz Optional-Stopping-Value -- final output is the propagated label image optional stopping value -- higher values allow more distant propagation ExtractSlice volume.nii.gz slicetoextract --- will extract slice number from last dimension of volume (2,3,4) dimensions