Analyzeparticles: Difference between revisions

From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search
imported>Donal
 
(53 intermediate revisions by 3 users not shown)
Line 5: Line 5:
===Synopsis===
===Synopsis===


: [X model] = analyzeparticles(X, options);                             
: [imgdso, model] = analyzeparticles(x, options);                             
: [X model] = analyzeparticles(X);                                     
: [imgdso, model] = analyzeparticles(x);                                     
: [X model] = analyzeparticles(X, model);
: [imgdso, model] = analyzeparticles(x, model);


===Description===
===Description===


The particle analysis functionality is used to automatically identify particle-like areas in an image and to return information about the identified particles’ characteristics such as their area, shape and pixel values. A particle is considered to be an isolated contiguous region of pixels within the image which have similar intensity values or color values. Particles are also known as “connected regions” or “blobs”.
Particle analysis is used to identify particle-like areas in an image and return information about the identified particles’ characteristics such as their area, shape and pixel values. A particle is considered to be an isolated contiguous region of pixels within the image which have similar intensity values or color values. Particles are also known as “connected regions” or “blobs”.


Our image analysis software can analyze Particles in images using either the “analyzeparticles” Matlab function or the “Particle Analysis” GUI, which is a graphical interface to that function.  The analyzeparticles function itself is implemented using the ImageJ image analysis package (http://rsb.info.nih.gov/ij/) which is included with MIA. Analyzeparticles integrates the ImageJ “Analyze Particles” feature into MIA so it can be conveniently used with the Eigenvector dataset object and the other MIA/PLS_Toolbox tools.
Our image analysis software can analyze particles in images using either the “analyzeparticles” Matlab function or the “Particle Analysis” GUI, which is a graphical interface to that function.  The analyzeparticles function itself is implemented using the ImageJ image analysis package (http://rsb.info.nih.gov/ij/) which is included with our software. Analyzeparticles integrates the ImageJ “Analyze Particles” feature into our software so it can be conveniently used with the Eigenvector dataset object and the other MIA/PLS_Toolbox tools.


====Inputs====
====Inputs====


* '''x''' = Image dataset object with one or more slabs,
* '''x''' = image dataset object with one or more slabs,
* '''y''' = Y-block (predicted block) class "double" or "dataset", containing numeric values,
* '''model''' = previously generated model of type 'ANALYZEPARTICLES' (when applying model to new data).
* '''model''' = previously generated model (when applying model to new data).


====Outputs====
====Outputs====
 
* '''imgdso''' = input imgdso modified with addition of classesets identifying particles. One classset has a class for each particle. Pixels within particle j have class = j. Non particle pixels have class = 0. Second classset has one class for all particles. Pixels within any particle have class = 1. Non particle pixels have class = 0.
* '''model''' = a standard model structure model with the following fields (see MODELSTRUCT):
* '''model''' = a standard model structure model with the following fields (see [[Standard Model Structure]]):
** '''modeltype''': 'SVM',
** '''modeltype''': 'ANALYZEPARTICLES',
** '''datasource''': structure array with information about input data,
** '''datasource''': structure array with information about input data,
** '''date''': date of creation,
** '''date''': date of creation,
** '''time''': time of creation,
** '''time''': time of creation,
** '''info''': additional model information,
** '''info''': additional model information,
** '''pred''': 2 element cell array with
** '''particletable''': A dataset containing the requested particle properties,
*** model predictions for each input block (when options.blockdetail='normal' x-block predictions are not saved and this will be an empty array)
***  Rows are particles,
***  Columns represent properties, identified by particletable.label{2}.
** '''allparticles''': a vector with one entry per pixel, value = 0 if pixel is not a particle pixel, 1 otherwise.
** '''particles''': a vector with one entry per pixel, value = j, where j = 0, 1, ...n if pixel is part of particle number j.
** '''foreground''': a vector with one entry per pixel, value = 0 or 255, showing the binary image representing all possible particle pixels.
** '''detail''': sub-structure with additional model details and results, including:
** '''detail''': sub-structure with additional model details and results, including:
*** model.detail.svm.model: Matlab version of the libsvm svm_model (Java)
*** model.detail.thresholdValue: the threshold value used in forming the binary image,
*** model.detail.svm.cvscan: results of CV parameter scan
*** model.detail.height: height of the image (in pixels),
*** model.detail.svm.outlier: results of outlier detection (one-class svm)
*** model.detail.width: width of the image (in pixels),
 
*** model.detail.nparticles: number of identified particles,
* '''pred''' a structure, similar to '''model''' for the new data.
*** model.detail.ij: contains the Java evri.ij.plugin.ParticlesAnalyzer object.


===Options===
===Options===
''options'' =  a structure array with the following fields:
''options'' =  a structure array with the following fields:


* '''display''': [ 'off' | {'on'} ], governs level of display to command window,
* '''display''': [ 'off' | {'on'} ], governs level of display to command window. 'off' suppresses output,
* '''plots''' [ 'none' | {'final'} ], governs level of plotting,
* '''plots''' [ 'none' | {'final'} ], governs level of plotting,
* '''preprocessing''': {[]} preprocessing structures for x block (see PREPROCESS). NOTE that y-block preprocessing is NOT used with SVMs. Any y-preprocessing will be ignored.
* '''compression''': [{'none'}| 'pca' | 'pls' ] type of data compression to perform on the x-block prior to calculaing or applying the SVM model. 'pca' uses a simple PCA model to compress the information. 'pls' uses either a pls or plsda model (depending on the svmtype). Compression can make the SVM more stable and less prone to overfitting.
* '''blockdetails''': [ {'standard'} | 'all' ], extent of predictions and residuals included in model, 'standard' = only y-block, 'all' x- and y-blocks.
* '''algorithm''': [ 'libsvm' ] algorithm to use. libsvm is default and currently only option.
* '''kerneltype''': [ 'linear' | {'rbf'} ], SVM kernel to use. 'rbf' is default.
* '''svmtype''': [ {'epsilon-svr'} | 'nu-svr' ] Type of SVM to apply. The default is 'epsilon-svr' for regression.
* '''probabilityestimates''': [0| {1} ], whether to train the SVR model for probability estimates, 0 or 1 (default 1)"


* '''cvtimelimit''': Set a time limit (seconds) on individual cross-validation sub-calculation when searching over supplied SVM parameter ranges for optimal parameters. Only relevant if parameter ranges are used for SVM parameters such as cost, epsilon, gamma or nu. Default is 10;
* '''includeholes''': [ 'off' | {'on'} ], holes within particles are included?,
* '''splits''': Number of subsets to divide data into when applying n-fold cross validation. Default is 5.
* '''includeedgeparticles''': [ {'off'} | 'on' ], include particles intersecting the image's edge?,
* '''gamma''': Value(s) to use for LIBSVM kernel gamma parameter. Default is 15 values from 10^-6 to 10, spaced uniformly in log.
* '''thresholdslab''': Index of dataset slab to use for creating binary image. Default = [],
* '''cost''': Value(s) to use for LIBSVM 'c' parameter. Default is 11 values from 10^-3 to 100, spaced uniformly in log.
* '''thresholdvalue''': Value to use as threshold when creating binary image,
* '''epsilon''': Value(s) to use for LIBSVM 'p' parameter (epsilon in loss function). Default is the set of values [1.0, 0.1, 0.01].
* '''reversemask''': [ 'off' | {'on'}] reverse the particle binary mask? ('on' means find bright particles. See below).
* '''nu''': Value(s) to use for LIBSVM 'n' parameter (nu of nu-SVC, and nu-SVR). Default is the set of values [0.2, 0.5, 0.8].
* '''apply_abs''': [ {'off'} | 'on' ] apply absolute value to data initially?
* '''outliernu''': Value to use for nu in LIBSVM's one-class svm outlier detection. (0.05).
The following four options represent criteria which potential particles must satisfy to be considered particles:
* '''minsize''': Lower limit to particle area. Default is 50 pixels,
* '''maxsize''': Upper limit to particle area. Default is infinite,
* '''mincircularity''': Lower limit to particle circularity. Default = 0.0,
* '''maxcircularity''': Upper limit to particle circularity. Default = 1.0,
The remaining options indicate whether these additional particle properties should be measured and reported:
* '''particleminmax''': [ {'off'} | 'on' ] measure particle min and max values,
* '''particlemedian''': [ {'off'} | 'on' ] measure particle median value,
* '''particlestddev''': [ {'off'} | 'on' ] measure particle standard deviation value,
* '''particleperimeter''': [ {'off'} | 'on' ] measure length of particle perimeter (pixels),
* '''particleshape''': [ {'off'} | 'on' ] measure particle shape parameters (Conc., AR, Round, Solidity),
* '''particleferet''': [ {'off'} | 'on' ] measure Feret diameters of particle.


===Algorithm===
===Algorithm===
There are two stages to particle analysis of an image dataset object (DSO). The first stage is to obtain a binary image where image pixel values are either 0 or 1 where one value represents non-particle pixels and the other represents potential particle pixels.  This is usually accomplished by specifying a threshold level where pixel  having values below or above the threshold value are assigned value 0 or 1. If the image DSO has multiple slabs then one slab must be selected to determine the binary image or else the average of all the slabs can be used. A pixel assigned value 1 is not automatically part of a particle because other particle criteria can be specified such as a minimum particle area requirement, or other shape restriction. Once these filters are applied there may remain some particle regions.
There are two steps to particle analysis of an image dataset object (DSO). The first step is to obtain a binary image where image pixel values are either 0 or 1 where one value represents non-particle pixels and the other represents potential particle pixels.  This is usually accomplished by specifying a threshold level where pixels having a value below or above the threshold value are assigned value 0 or 1. If no threshold level is specified then one is automatically determined as in the ImageJ auto thresholding method. If the image DSO has multiple slabs then one slab must be selected to determine the binary image or else the average of all the slabs can be used. A pixel assigned value 1 is not automatically part of a particle because other particle criteria can be specified such as a minimum particle area requirement, or other shape restriction. Once these filters are applied there may remain some particle regions.
 
The second step in particle analysis is to calculate the properties of each particle region. Properties include area, perimeter, centroid coordinates, shape properties (circularity, aspect ratio, roundness, and solidity) and Feret’s diameters (Feret  diameter, FeretX, FeretY, FeretAngle and MinFeret). There are other particle properties which depend on the particle’s pixel values including mean, median, minimum, maximum, and standard deviation. These are calculated for each slab for each particle.
 
 
====Measured Particle Properties====
Properties of each particle are returned in the model.particletable DSO. Particles' centroid coordinates (w, h) are always returned. Coordinates are given using the image convention where (x,y) indicates distance in pixels measured from the top left corner of the image, so the top left corner has coordinates (0,0) while the bottom right corner has coordinates (nwidth-1, nheight-1).
*'''X, Y''' are the coordinates of the particle's centroid.
 
Additional particle properties can be obtained by specifying options:
*'''Mean''' = mean pixel value over particle, per slab
*'''Median''' = mean pixel value over particle, per slab
*'''Min''' = minimum pixel value over particle, per slab
*'''Max''' = maximum pixel value over particle, per slab
*'''StdDev''' = standard deviation of pixel values over particle, per slab.
 
Particle properties which only depend on the particle shape (are the same for all slabs) include:
*'''Area''' = area of particle (in square pixels),
*'''Perim.''' = length of particle perimeter in pixel lengths.
:Note that properties with dimensional quantities such as Perimiter or Area are reported in pixels or in axisscale units. Image Axisscale units are used if the image dataset has imageaxisscales for both x and y dimensions. If only one imageaxisscale is present then its units are used for both x and y dimensions. If there are no imageaxisscales present then properties are reported in units of pixels.
 
Particle shape properties:
*'''Circ.''' (circularity = 4π*area/perimeter^2.  A value of 1.0 indicates a perfect circle. As the value approaches 0.0, it indicates an increasingly elongated shape. Values may not be valid for very small particles. Also note that a circular particle with large holes will have smaller area than a circle with that perimeter, so circularity is only accurate if the particle has no holes (or 'includeholes=on'). A circular particle with large holes will have small solidity.
 
*'''AR''' (aspect ratio)  = major_axis/minor_axis.
 
*'''Round''' (roundness)  = 4*area/(π*major_axis^2), or the inverse of the aspect ratio.
 
*'''Solidity'''          = area/convex area.
 
Particle Feret diameters,
Feret's Diameter is the longest distance between any two points along the particle boundary, also known as maximum caliper. The angle (0-180 degrees) of the Feret's diameter is displayed as FeretAngle, as well as the minimum caliper diameter (MinFeret).
 
*'''Feret'''        = Feret's diameter of particle (length in pixels)
 
*'''FeretX'''      = Coordinate of one end of Feret's diameter.
 
*'''FeretY'''      = Coordinate of one end of Feret's diameter.
 
*'''FeretAngle'''  = Angle between Feret's diameter and x-axis.
 
*'''MinFeret'''    = Minimum Feret's diameter (caliper) of particle (length in pixels)
 
====Filtering Particles by Size and Circularity====
The number of particles returned by analyzeparticles can be reduced by specifying a minimum or maximum area or circularity that a particle must have. These values can be specified as options.minsize, options.maxsize, options.mincircularity, options.maxcircularity, or default values will be used.
 
====Reverse Mask to Measure Bright Particles====
The default behavior is to identify particles as connected regions which have intensity above a threshold value. This identifies brighter areas as particles while the rest of the image is considered a darker background. In some images, however, the particles may appear as darker spots on a brighter background. Such particles can be analyzed by setting the input option "reversemask" to "off" instead of its default value "on".


The second stage in particle analysis is to calculate the properties of each particle region. Properties include area, perimeter, centroid coordinates, shape properties (circularity, aspect ratio, roundness, and solidity) and Feret’s diameters (Feret  diameter, FeretX, FeretY, FeretAngle and MinFeret). There are other particle properties which depend on the particle’s pixel values including mean, median, minimum, maximum, and standard deviation. These are calculated for each slab for each particle.
====Handling of Holes Within Particles====
The default behavior of analyzeparticles, option.includeholes = 'on', is to measure a particle's area or mean pixel value, etc. by including all enclosed pixels. Thus any holes within an enclosing particle do contribute to the particle's area or mean pixel value. This behavior can be changed by specifying the input option.includeholes = 'off', which will mean that non-particle pixels within the surrounding particle boundary are not used in calculating the particle area or mean pixel value, etc.. When option.includeholes = 'off' any "child" particles within such a hole are reported as additional particles and do not contribute to the enclosing particle's area and mean, etc. Thus, includeholes = 'off' can lead to identifying more particles. A set of N concentric circles would count as just one particle if includeholes = 'on' but would yield N particles when includeholes = 'off'.


====epsilon-SVR and nu-SVR====
====Handling of Excluded Pixels====
There are two commonly used versions of SVM regression, 'epsilon-SVR' and 'nu-SVR'. The original SVM formulations for Classification (SVC) and Regression (SVR) used parameters C [0, inf) and epsilon[0, inf) to apply a penalty to the optimization for points which were not correctly separated by the classifying hyperplane or for prediction errors greater than epsilon.  Alternative versions of both SVM classification and regression were later developed where these penalty parameters were replaced by an alternative parameter, nu [0,1], which applies a slightly different penalty. The main motivation for the nu versions of SVM is that it has a has a more meaningful interpretation. This is because nu represents an upper bound on the fraction of training samples which are errors (misclassified, or poorly predicted) and a lower bound on the fraction of samples which are support vectors. Some users feel nu is more intuitive to use than C or epsilon.
Pixels which are flagged as excluded by the dataset object are treated as non-particle pixels.
C/epsilon or nu are just different versions of the penalty parameter. The same optimization problem is solved in either case. Thus it should not matter which form of SVM you use, C versus nu for classification or epsilon versus nu for regression. PLS_Toolbox uses the C and epsilon versions since these were the original formulations and are the most commonly used forms. For more details on 'nu' SVMs see [http://www.csie.ntu.edu.tw/~cjlin/papers/nusvmtutorial.pdf]


===See Also===
===See Also===


[[analysis]], [[svmda]]
[[analysis]], [[particlegui]]

Latest revision as of 12:20, 27 May 2020

Purpose

ANALYZEPARTCLES Identify particles (blobs, connected regions), and their properties, in an image dataset.

Synopsis

[imgdso, model] = analyzeparticles(x, options);
[imgdso, model] = analyzeparticles(x);
[imgdso, model] = analyzeparticles(x, model);

Description

Particle analysis is used to identify particle-like areas in an image and return information about the identified particles’ characteristics such as their area, shape and pixel values. A particle is considered to be an isolated contiguous region of pixels within the image which have similar intensity values or color values. Particles are also known as “connected regions” or “blobs”.

Our image analysis software can analyze particles in images using either the “analyzeparticles” Matlab function or the “Particle Analysis” GUI, which is a graphical interface to that function. The analyzeparticles function itself is implemented using the ImageJ image analysis package (http://rsb.info.nih.gov/ij/) which is included with our software. Analyzeparticles integrates the ImageJ “Analyze Particles” feature into our software so it can be conveniently used with the Eigenvector dataset object and the other MIA/PLS_Toolbox tools.

Inputs

  • x = image dataset object with one or more slabs,
  • model = previously generated model of type 'ANALYZEPARTICLES' (when applying model to new data).

Outputs

  • imgdso = input imgdso modified with addition of classesets identifying particles. One classset has a class for each particle. Pixels within particle j have class = j. Non particle pixels have class = 0. Second classset has one class for all particles. Pixels within any particle have class = 1. Non particle pixels have class = 0.
  • model = a standard model structure model with the following fields (see Standard Model Structure):
    • modeltype: 'ANALYZEPARTICLES',
    • datasource: structure array with information about input data,
    • date: date of creation,
    • time: time of creation,
    • info: additional model information,
    • particletable: A dataset containing the requested particle properties,
      • Rows are particles,
      • Columns represent properties, identified by particletable.label{2}.
    • allparticles: a vector with one entry per pixel, value = 0 if pixel is not a particle pixel, 1 otherwise.
    • particles: a vector with one entry per pixel, value = j, where j = 0, 1, ...n if pixel is part of particle number j.
    • foreground: a vector with one entry per pixel, value = 0 or 255, showing the binary image representing all possible particle pixels.
    • detail: sub-structure with additional model details and results, including:
      • model.detail.thresholdValue: the threshold value used in forming the binary image,
      • model.detail.height: height of the image (in pixels),
      • model.detail.width: width of the image (in pixels),
      • model.detail.nparticles: number of identified particles,
      • model.detail.ij: contains the Java evri.ij.plugin.ParticlesAnalyzer object.

Options

options = a structure array with the following fields:

  • display: [ 'off' | {'on'} ], governs level of display to command window. 'off' suppresses output,
  • plots [ 'none' | {'final'} ], governs level of plotting,
  • includeholes: [ 'off' | {'on'} ], holes within particles are included?,
  • includeedgeparticles: [ {'off'} | 'on' ], include particles intersecting the image's edge?,
  • thresholdslab: Index of dataset slab to use for creating binary image. Default = [],
  • thresholdvalue: Value to use as threshold when creating binary image,
  • reversemask: [ 'off' | {'on'}] reverse the particle binary mask? ('on' means find bright particles. See below).
  • apply_abs: [ {'off'} | 'on' ] apply absolute value to data initially?

The following four options represent criteria which potential particles must satisfy to be considered particles:

  • minsize: Lower limit to particle area. Default is 50 pixels,
  • maxsize: Upper limit to particle area. Default is infinite,
  • mincircularity: Lower limit to particle circularity. Default = 0.0,
  • maxcircularity: Upper limit to particle circularity. Default = 1.0,

The remaining options indicate whether these additional particle properties should be measured and reported:

  • particleminmax: [ {'off'} | 'on' ] measure particle min and max values,
  • particlemedian: [ {'off'} | 'on' ] measure particle median value,
  • particlestddev: [ {'off'} | 'on' ] measure particle standard deviation value,
  • particleperimeter: [ {'off'} | 'on' ] measure length of particle perimeter (pixels),
  • particleshape: [ {'off'} | 'on' ] measure particle shape parameters (Conc., AR, Round, Solidity),
  • particleferet: [ {'off'} | 'on' ] measure Feret diameters of particle.

Algorithm

There are two steps to particle analysis of an image dataset object (DSO). The first step is to obtain a binary image where image pixel values are either 0 or 1 where one value represents non-particle pixels and the other represents potential particle pixels. This is usually accomplished by specifying a threshold level where pixels having a value below or above the threshold value are assigned value 0 or 1. If no threshold level is specified then one is automatically determined as in the ImageJ auto thresholding method. If the image DSO has multiple slabs then one slab must be selected to determine the binary image or else the average of all the slabs can be used. A pixel assigned value 1 is not automatically part of a particle because other particle criteria can be specified such as a minimum particle area requirement, or other shape restriction. Once these filters are applied there may remain some particle regions.

The second step in particle analysis is to calculate the properties of each particle region. Properties include area, perimeter, centroid coordinates, shape properties (circularity, aspect ratio, roundness, and solidity) and Feret’s diameters (Feret diameter, FeretX, FeretY, FeretAngle and MinFeret). There are other particle properties which depend on the particle’s pixel values including mean, median, minimum, maximum, and standard deviation. These are calculated for each slab for each particle.


Measured Particle Properties

Properties of each particle are returned in the model.particletable DSO. Particles' centroid coordinates (w, h) are always returned. Coordinates are given using the image convention where (x,y) indicates distance in pixels measured from the top left corner of the image, so the top left corner has coordinates (0,0) while the bottom right corner has coordinates (nwidth-1, nheight-1).

  • X, Y are the coordinates of the particle's centroid.

Additional particle properties can be obtained by specifying options:

  • Mean = mean pixel value over particle, per slab
  • Median = mean pixel value over particle, per slab
  • Min = minimum pixel value over particle, per slab
  • Max = maximum pixel value over particle, per slab
  • StdDev = standard deviation of pixel values over particle, per slab.

Particle properties which only depend on the particle shape (are the same for all slabs) include:

  • Area = area of particle (in square pixels),
  • Perim. = length of particle perimeter in pixel lengths.
Note that properties with dimensional quantities such as Perimiter or Area are reported in pixels or in axisscale units. Image Axisscale units are used if the image dataset has imageaxisscales for both x and y dimensions. If only one imageaxisscale is present then its units are used for both x and y dimensions. If there are no imageaxisscales present then properties are reported in units of pixels.

Particle shape properties:

  • Circ. (circularity = 4π*area/perimeter^2. A value of 1.0 indicates a perfect circle. As the value approaches 0.0, it indicates an increasingly elongated shape. Values may not be valid for very small particles. Also note that a circular particle with large holes will have smaller area than a circle with that perimeter, so circularity is only accurate if the particle has no holes (or 'includeholes=on'). A circular particle with large holes will have small solidity.
  • AR (aspect ratio) = major_axis/minor_axis.
  • Round (roundness) = 4*area/(π*major_axis^2), or the inverse of the aspect ratio.
  • Solidity = area/convex area.

Particle Feret diameters, Feret's Diameter is the longest distance between any two points along the particle boundary, also known as maximum caliper. The angle (0-180 degrees) of the Feret's diameter is displayed as FeretAngle, as well as the minimum caliper diameter (MinFeret).

  • Feret = Feret's diameter of particle (length in pixels)
  • FeretX = Coordinate of one end of Feret's diameter.
  • FeretY = Coordinate of one end of Feret's diameter.
  • FeretAngle = Angle between Feret's diameter and x-axis.
  • MinFeret = Minimum Feret's diameter (caliper) of particle (length in pixels)

Filtering Particles by Size and Circularity

The number of particles returned by analyzeparticles can be reduced by specifying a minimum or maximum area or circularity that a particle must have. These values can be specified as options.minsize, options.maxsize, options.mincircularity, options.maxcircularity, or default values will be used.

Reverse Mask to Measure Bright Particles

The default behavior is to identify particles as connected regions which have intensity above a threshold value. This identifies brighter areas as particles while the rest of the image is considered a darker background. In some images, however, the particles may appear as darker spots on a brighter background. Such particles can be analyzed by setting the input option "reversemask" to "off" instead of its default value "on".

Handling of Holes Within Particles

The default behavior of analyzeparticles, option.includeholes = 'on', is to measure a particle's area or mean pixel value, etc. by including all enclosed pixels. Thus any holes within an enclosing particle do contribute to the particle's area or mean pixel value. This behavior can be changed by specifying the input option.includeholes = 'off', which will mean that non-particle pixels within the surrounding particle boundary are not used in calculating the particle area or mean pixel value, etc.. When option.includeholes = 'off' any "child" particles within such a hole are reported as additional particles and do not contribute to the enclosing particle's area and mean, etc. Thus, includeholes = 'off' can lead to identifying more particles. A set of N concentric circles would count as just one particle if includeholes = 'on' but would yield N particles when includeholes = 'off'.

Handling of Excluded Pixels

Pixels which are flagged as excluded by the dataset object are treated as non-particle pixels.

See Also

analysis, particlegui

Retrieved from "https://www.wiki.eigenvector.com/index.php?title=Analyzeparticles&oldid=11054"