Medical Imaging Interaction Toolkit  2018.4.99-08619e4f
Medical Imaging Interaction Toolkit
mitk::GIFFirstOrderStatistics Class Reference

#include <mitkGIFFirstOrderStatistics.h>

Inheritance diagram for mitk::GIFFirstOrderStatistics:
Collaboration diagram for mitk::GIFFirstOrderStatistics:

Public Member Functions

 mitkClassMacro (GIFFirstOrderStatistics, AbstractGlobalImageFeature)
 Calculates first order statistics of the given image. More...
 
Pointer Clone () const
 
 GIFFirstOrderStatistics ()
 
FeatureListType CalculateFeatures (const Image *image, const Image *mask, const Image *maskNoNAN) override
 
void AddArguments (mitkCommandLineParser &parser) const override
 
- Public Member Functions inherited from mitk::AbstractGlobalImageFeature
 mitkClassMacro (AbstractGlobalImageFeature, BaseData)
 
FeatureListType CalculateFeatures (const Image *image, const Image *mask)
 Calculates the feature of this abstact interface. Does not necessarily considers the parameter settings. More...
 
FeatureListType CalculateFeaturesSlicewise (const Image::Pointer &image, const Image::Pointer &mask, int sliceID)
 Calculates the given feature Slice-wise. Might not be availble for an individual filter! More...
 
virtual void CalculateAndAppendFeaturesSliceWise (const Image::Pointer &image, const Image::Pointer &mask, int sliceID, FeatureListType &featureList, bool checkParameterActivation=true)
 Calculates the feature of this abstact interface. Does not necessarily considers the parameter settings. More...
 
void CalculateAndAppendFeatures (const Image *image, const Image *mask, const Image *maskNoNAN, FeatureListType &featureList, bool checkParameterActivation=true)
 Calculates the feature of this abstact interface. Does not necessarily considers the parameter settings. More...
 
virtual void SetPrefix (std::string _arg)
 
virtual void SetShortName (std::string _arg)
 
virtual void SetLongName (std::string _arg)
 
virtual void SetFeatureClassName (std::string _arg)
 
virtual void SetDirection (int _arg)
 
void SetParameters (ParametersType param)
 
virtual std::string GetPrefix () const
 
virtual std::string GetShortName () const
 
virtual std::string GetLongName () const
 
virtual std::string GetFeatureClassName () const
 
virtual ParametersType GetParameters () const
 
virtual IntensityQuantifier::Pointer GetQuantifier ()
 
virtual int GetDirection () const
 
virtual void SetMinimumIntensity (double _arg)
 
virtual void SetUseMinimumIntensity (bool _arg)
 
virtual void SetMaximumIntensity (double _arg)
 
virtual void SetUseMaximumIntensity (bool _arg)
 
virtual double GetMinimumIntensity () const
 
virtual bool GetUseMinimumIntensity () const
 
virtual double GetMaximumIntensity () const
 
virtual bool GetUseMaximumIntensity () const
 
virtual void SetBinsize (double _arg)
 
virtual void SetUseBinsize (bool _arg)
 
virtual double GetBinsize () const
 
virtual bool GetUseBinsize () const
 
virtual void SetMorphMask (mitk::Image::Pointer _arg)
 
virtual mitk::Image::Pointer GetMorphMask () const
 
virtual void SetBins (int _arg)
 
virtual void SetUseBins (bool _arg)
 
virtual bool GetUseBins () const
 
virtual int GetBins () const
 
virtual void SetIgnoreMask (bool _arg)
 
virtual bool GetIgnoreMask () const
 
virtual void SetEncodeParametersInFeaturePrefix (bool _arg)
 
virtual bool GetEncodeParametersInFeaturePrefix () const
 
virtual void EncodeParametersInFeaturePrefixOn ()
 
virtual void EncodeParametersInFeaturePrefixOff ()
 
std::string GetOptionPrefix () const
 
void SetRequestedRegionToLargestPossibleRegion () override
 Set the RequestedRegion to the LargestPossibleRegion. More...
 
bool RequestedRegionIsOutsideOfTheBufferedRegion () override
 Determine whether the RequestedRegion is outside of the BufferedRegion. More...
 
bool VerifyRequestedRegion () override
 Verify that the RequestedRegion is within the LargestPossibleRegion. More...
 
void SetRequestedRegion (const itk::DataObject *) override
 Set the requested region from this data object to match the requested region of the data object passed in as a parameter. More...
 
bool IsEmpty () const override
 Check whether object contains data (at least at one point in time), e.g., a set of points may be empty. More...
 
- Public Member Functions inherited from mitk::BaseData
virtual std::vector< std::string > GetClassHierarchy () const
 
virtual const char * GetClassName () const
 
BaseProperty::ConstPointer GetConstProperty (const std::string &propertyKey, const std::string &contextName="", bool fallBackOnDefaultContext=true) const override
 Get property by its key. More...
 
std::vector< std::string > GetPropertyKeys (const std::string &contextName="", bool includeDefaultContext=false) const override
 Query keys of existing properties. More...
 
std::vector< std::string > GetPropertyContextNames () const override
 Query names of existing contexts. More...
 
BasePropertyGetNonConstProperty (const std::string &propertyKey, const std::string &contextName="", bool fallBackOnDefaultContext=true) override
 Get property by its key. More...
 
void SetProperty (const std::string &propertyKey, BaseProperty *property, const std::string &contextName="", bool fallBackOnDefaultContext=false) override
 Add new or change existent property. More...
 
void RemoveProperty (const std::string &propertyKey, const std::string &contextName="", bool fallBackOnDefaultContext=false) override
 Removes a property. If the property does not exist, nothing will be done. More...
 
const mitk::TimeGeometryGetTimeGeometry () const
 Return the TimeGeometry of the data as const pointer. More...
 
const mitk::TimeGeometryGetTimeSlicedGeometry () const
 Return the TimeGeometry of the data as const pointer. More...
 
mitk::TimeGeometryGetTimeGeometry ()
 Return the TimeGeometry of the data as pointer. More...
 
const mitk::TimeGeometryGetUpdatedTimeGeometry ()
 Return the TimeGeometry of the data. More...
 
const mitk::TimeGeometryGetUpdatedTimeSliceGeometry ()
 Return the TimeGeometry of the data. More...
 
virtual void Expand (unsigned int timeSteps)
 Expands the TimeGeometry to a number of TimeSteps. More...
 
const mitk::BaseGeometryGetUpdatedGeometry (int t=0)
 Return the BaseGeometry of the data at time t. More...
 
mitk::BaseGeometryGetGeometry (int t=0) const
 Return the geometry, which is a TimeGeometry, of the data as non-const pointer. More...
 
void UpdateOutputInformation () override
 Update the information for this BaseData (the geometry in particular) so that it can be used as an output of a BaseProcess. More...
 
void CopyInformation (const itk::DataObject *data) override
 Copy information from the specified data set. More...
 
virtual bool IsInitialized () const
 Check whether the data has been initialized, i.e., at least the Geometry and other header data has been set. More...
 
virtual void Clear ()
 Calls ClearData() and InitializeEmpty();. More...
 
virtual bool IsEmptyTimeStep (unsigned int t) const
 Check whether object contains data (at a specified time), e.g., a set of points may be empty. More...
 
void ExecuteOperation (Operation *operation) override
 overwrite if the Data can be called by an Interactor (StateMachine). More...
 
virtual void SetGeometry (BaseGeometry *aGeometry3D)
 Set the BaseGeometry of the data, which will be referenced (not copied!). Assumes the data object has only 1 time step ( is a 3D object ) and creates a new TimeGeometry which saves the given BaseGeometry. If an TimeGeometry has already been set for the object, it will be replaced after calling this function. More...
 
virtual void SetTimeGeometry (TimeGeometry *geometry)
 Set the TimeGeometry of the data, which will be referenced (not copied!). More...
 
virtual void SetClonedGeometry (const BaseGeometry *aGeometry3D)
 Set a clone of the provided Geometry as Geometry of the data. Assumes the data object has only 1 time step ( is a 3D object ) and creates a new TimeGeometry. If an TimeGeometry has already been set for the object, it will be replaced after calling this function. More...
 
virtual void SetClonedTimeGeometry (const TimeGeometry *geometry)
 Set a clone of the provided TimeGeometry as TimeGeometry of the data. More...
 
virtual void SetClonedGeometry (const BaseGeometry *aGeometry3D, unsigned int time)
 Set a clone of the provided geometry as BaseGeometry of a given time step. More...
 
mitk::PropertyList::Pointer GetPropertyList () const
 Get the data's property list. More...
 
void SetPropertyList (PropertyList *propertyList)
 Set the data's property list. More...
 
mitk::BaseProperty::Pointer GetProperty (const char *propertyKey) const
 Get the property (instance of BaseProperty) with key propertyKey from the PropertyList, and set it to this, respectively;. More...
 
void SetProperty (const char *propertyKey, BaseProperty *property)
 
virtual void SetOrigin (const Point3D &origin)
 Convenience method for setting the origin of the BaseGeometry instances of all time steps. More...
 
itk::SmartPointer< mitk::BaseDataSourceGetSource () const
 Get the process object that generated this data object. More...
 
unsigned int GetTimeSteps () const
 Get the number of time steps from the TimeGeometry As the base data has not a data vector given by itself, the number of time steps is defined over the time sliced geometry. In sub classes, a better implementation could be over the length of the data vector. More...
 
unsigned long GetMTime () const override
 Get the modified time of the last change of the contents this data object or its geometry. More...
 
void Graft (const DataObject *) override
 
- Public Member Functions inherited from mitk::OperationActor
 itkTypeMacroNoParent (OperationActor) virtual ~OperationActor()
 
- Public Member Functions inherited from mitk::Identifiable
 Identifiable ()
 
 Identifiable (const UIDType &uid)
 
 Identifiable (const Identifiable &)=delete
 
 Identifiable (Identifiable &&) noexcept
 
virtual ~Identifiable ()
 
Identifiableoperator= (const Identifiable &)=delete
 
Identifiableoperator= (Identifiable &&other) noexcept
 
virtual UIDType GetUID () const
 Get unique ID of an object. More...
 
- Public Member Functions inherited from mitk::IPropertyOwner
 ~IPropertyOwner () override
 
- Public Member Functions inherited from mitk::IPropertyProvider
virtual ~IPropertyProvider ()
 

Static Public Member Functions

static Pointer New ()
 
- Static Public Member Functions inherited from mitk::AbstractGlobalImageFeature
static std::string GenerateLegacyFeatureNameWOEncoding (const FeatureID &id)
 
- Static Public Member Functions inherited from mitk::BaseData
static const char * GetStaticNameOfClass ()
 

Protected Member Functions

FeatureListType DoCalculateFeatures (const Image *image, const Image *mask) override
 
- Protected Member Functions inherited from mitk::AbstractGlobalImageFeature
std::vector< double > SplitDouble (std::string str, char delimiter)
 
void AddQuantifierArguments (mitkCommandLineParser &parser) const
 
void ConfigureQuantifierSettingsByParameters ()
 
virtual void ConfigureSettingsByParameters (const ParametersType &parameters)
 
void InitializeQuantifier (const Image *image, const Image *mask, unsigned int defaultBins=256)
 
std::string QuantifierParameterString () const
 
FeatureID CreateTemplateFeatureID (std::string settingsSuffix="", FeatureID::ParametersType additionalParams={})
 
virtual std::string GenerateLegacyFeatureName (const FeatureID &id) const
 
virtual std::string GenerateLegacyFeatureNamePart (const FeatureID &id) const
 
virtual std::string GenerateLegacyFeatureEncoding (const FeatureID &id) const
 
- Protected Member Functions inherited from mitk::BaseData
 BaseData ()
 
 BaseData (const BaseData &other)
 
 ~BaseData () override
 
virtual void InitializeTimeGeometry (unsigned int timeSteps=1)
 Initialize the TimeGeometry for a number of time steps. The TimeGeometry is initialized empty and evenly timed. In many cases it will be necessary to overwrite this in sub-classes. More...
 
virtual void InitializeTimeSlicedGeometry (unsigned int timeSteps=1)
 Initialize the TimeGeometry for a number of time steps. The TimeGeometry is initialized empty and evenly timed. In many cases it will be necessary to overwrite this in sub-classes. More...
 
virtual void ClearData ()
 reset to non-initialized state, release memory More...
 
virtual void InitializeEmpty ()
 Pure virtual; Must be used in subclasses to get a data object to a valid state. Should at least create one empty object and call Superclass::InitializeTimeGeometry() to ensure an existing valid geometry. More...
 
void PrintSelf (std::ostream &os, itk::Indent indent) const override
 
- Protected Member Functions inherited from mitk::Identifiable
virtual void SetUID (const UIDType &uid)
 

Additional Inherited Members

- Public Types inherited from mitk::AbstractGlobalImageFeature
typedef std::vector< std::pair< FeatureID, double > > FeatureListType
 
using ParametersType = FeatureID::ParametersType
 
- Public Types inherited from mitk::BaseData
typedef BaseData Self
 
typedef itk::DataObject Superclass
 
typedef itk::SmartPointer< SelfPointer
 
typedef itk::SmartPointer< const SelfConstPointer
 
- Public Types inherited from mitk::Identifiable
using UIDType = std::string
 
- Protected Attributes inherited from mitk::BaseData
bool m_LastRequestedRegionWasOutsideOfTheBufferedRegion
 
unsigned int m_SourceOutputIndexDuplicate
 
bool m_Initialized
 

Detailed Description

Definition at line 22 of file mitkGIFFirstOrderStatistics.h.

Constructor & Destructor Documentation

◆ GIFFirstOrderStatistics()

mitk::GIFFirstOrderStatistics::GIFFirstOrderStatistics ( )

Definition at line 271 of file mitkGIFFirstOrderStatistics.cpp.

Member Function Documentation

◆ AddArguments()

void mitk::GIFFirstOrderStatistics::AddArguments ( mitkCommandLineParser parser) const
overridevirtual

Can be called to add all relevant argument for configuring the feature instance to the passed parser instance. Must be implemented be derived classes. For adding the quantifier arguments use AddQuantifierArguments(...) as helper function.

Implements mitk::AbstractGlobalImageFeature.

Definition at line 278 of file mitkGIFFirstOrderStatistics.cpp.

References mitkCommandLineParser::addArgument(), and mitkCommandLineParser::Bool.

◆ CalculateFeatures()

mitk::AbstractGlobalImageFeature::FeatureListType mitk::GIFFirstOrderStatistics::CalculateFeatures ( const Image image,
const Image mask,
const Image maskNoNAN 
)
overridevirtual

Implements mitk::AbstractGlobalImageFeature.

Definition at line 306 of file mitkGIFFirstOrderStatistics.cpp.

References CalculateFeatures().

◆ Clone()

Pointer mitk::GIFFirstOrderStatistics::Clone ( ) const

◆ DoCalculateFeatures()

mitk::AbstractGlobalImageFeature::FeatureListType mitk::GIFFirstOrderStatistics::DoCalculateFeatures ( const Image image,
const Image mask 
)
overrideprotectedvirtual

◆ mitkClassMacro()

mitk::GIFFirstOrderStatistics::mitkClassMacro ( GIFFirstOrderStatistics  ,
AbstractGlobalImageFeature   
)

Calculates first order statistics of the given image.

The first order statistics for the intensity distribution within a given Region of Interest (ROI) is caluclated. The ROI is defined using a mask.

The features are calculated on a quantified image. If the bin-size is too big, the obtained values can be errornous and missleading. It is therefore important to use enough bins. The binned approach is used in order to avoid floating-point related errors.

This feature calculator is activated by the option -first-order or -fo.

The connected areas are based on the binned image, the binning parameters can be set via the default parameters as described in AbstractGlobalImageFeature. It is also possible to determine the dimensionality of the neighbourhood using direction-related commands as described in AbstractGlobalImageFeature. No other options are possible beside these two options.

The features are calculated based on a mask. It is assumed that the mask is of the type of an unsigned short image. All voxels with the value 1 are treated as masked.

The following features are then defined using the (binned) voxel intensity \( x_i \) of each voxel, the probability an intensity \( p_x \), and the overall number of voxels within the mask \( N_v \):

  • First Order::Mean: The mean intensity within the ROI

    \[ \textup{Mean}= \mu = \frac{1}{N_v} \sum x_i \]

  • First Order::Unbiased Variance: An unbiased estimation of the variance:

    \[ \textup{Unbiased Variance} = \frac{1}{N_v - 1} \sum \left( x_i - \mu \right)^2 \]

  • First Order::Biased Variance: An biased estimation of the variance. If not specified otherwise, this is used as the variance:

    \[ \textup{Biased Variance} = \sigma^2 = \frac{1}{N_v} \sum \left( x_i - \mu \right)^2 \]

  • First Order::Unbiased Standard Deviation: Estimation of diversity within the intensity values

    \[ \textup{Unbiased Standard Deviation} = \sqrt{\frac{1}{N_v-1} \sum \left( x_i - \mu \right)^2} \]

  • First Order::Biased Standard Deviation: Estimation of diversity within the intensity values

    \[ \textup{Biased Standard Deviation} = \sigma = \sqrt{\frac{1}{N_v} \sum \left( x_i - \mu \right)^2} \]

  • First Order::Skewness:

    \[ \textup{Skewness} = \frac{\frac{1}{N_v} \sum \left( x_i - \mu \right)^3}{\sigma^3} \]

  • First Order::Kurtosis: The kurtosis is a measurement of the peakness of the given distirbution:

    \[ \textup{Kurtosis} = \frac{\frac{1}{N_v} \sum \left( x_i - \mu \right)^4}{\sigma^4} \]

  • First Order::Excess Kurtosis: The kurtosis is a measurement of the peakness of the given distirbution. The excess kurtosis is similar to the kurtosis, but is corrected by a fisher correction, ensuring that a gaussian distribution has an excess kurtosis of 0.

    \[ \textup{Excess Kurtosis} = \frac{\frac{1}{N_v} \sum \left( x_i - \mu \right)^4}{\sigma^4} - 3 \]

  • First Order::Median: The median is defined as the median of the all intensities in the ROI.
  • First Order::Minimum: The minimum is defined as the minimum of the all intensities in the ROI.
  • First Order::05th Percentile: \( P_{5\%} \) The 5% percentile. 5% of all voxel do have this or a lower intensity.
  • First Order::10th Percentile: \( P_{10\%} \) The 10% percentile. 10% of all voxel do have this or a lower intensity.
  • First Order::15th Percentile: \( P_{15\%} \) The 15% percentile. 15% of all voxel do have this or a lower intensity.
  • First Order::20th Percentile: \( P_{20\%} \) The 20% percentile. 20% of all voxel do have this or a lower intensity.
  • First Order::25th Percentile: \( P_{25\%} \) The 25% percentile. 25% of all voxel do have this or a lower intensity.
  • First Order::30th Percentile: \( P_{30\%} \) The 30% percentile. 30% of all voxel do have this or a lower intensity.
  • First Order::35th Percentile: \( P_{35\%} \) The 35% percentile. 35% of all voxel do have this or a lower intensity.
  • First Order::40th Percentile: \( P_{40\%} \) The 40% percentile. 40% of all voxel do have this or a lower intensity.
  • First Order::45th Percentile: \( P_{45\%} \) The 45% percentile. 45% of all voxel do have this or a lower intensity.
  • First Order::50th Percentile: \( P_{50\%} \) The 50% percentile. 50% of all voxel do have this or a lower intensity.
  • First Order::55th Percentile: \( P_{55\%} \) The 55% percentile. 55% of all voxel do have this or a lower intensity.
  • First Order::60th Percentile: \( P_{60\%} \) The 60% percentile. 60% of all voxel do have this or a lower intensity.
  • First Order::65th Percentile: \( P_{65\%} \) The 65% percentile. 65% of all voxel do have this or a lower intensity.
  • First Order::70th Percentile: \( P_{70\%} \) The 70% percentile. 70% of all voxel do have this or a lower intensity.
  • First Order::75th Percentile: \( P_{75\%} \) The 75% percentile. 75% of all voxel do have this or a lower intensity.
  • First Order::80th Percentile: \( P_{80\%} \) The 80% percentile. 80% of all voxel do have this or a lower intensity.
  • First Order::85th Percentile: \( P_{85\%} \) The 85% percentile. 85% of all voxel do have this or a lower intensity.
  • First Order::90th Percentile: \( P_{90\%} \) The 90% percentile. 90% of all voxel do have this or a lower intensity.
  • First Order::95th Percentile: \( P_{95\%} \) The 95% percentile. 95% of all voxel do have this or a lower intensity.
  • First Order::Maximum: The maximum is defined as the minimum of the all intensities in the ROI.
  • First Order::Range: The range of intensity values is defined as the difference between the maximum and minimum intensity in the ROI.
  • First Order::Interquartile Range: The difference between the 75% and 25% quantile.
  • First Order::Mean Absolute Deviation: The mean absolute deviation gives the mean distance of each voxel intensity to the overal mean intensity and is a measure of the dispersion of the intensity form the mean value:

    \[ \textup{Mean Absolute Deviation} = \frac{1}{N_v} \sum \left \| x_i - \mu \right \| \]

  • First Order::Robust Mean: The mean intensity within the ROI for all voxels between the 10% and 90% quantile:

    \[ \textup{Robust Mean}= \mu_R = \frac{1}{N_{vr}} \sum x_i \]

  • First Order::Robust Mean Absolute Deviation: The absolute deviation of all intensities within the ROI for all voxels between the 10% and 90% quantilefrom the robust mean intensity:

    \[ \textup{Robust Mean Absolute Deviation}= \mu_R = \frac{1}{N_{vr}} \sum \left \| x_i - \mu_R \right \| \]

  • First Order::Median Absolute Deviation: Similar to the mean absolute deviation, but uses the median instead of the mean to measure the center of the distribution.
  • First Order::Coefficient Of Variation: Measures the dispersion of the intensity distribution:

    \[ \textup{Coefficient Of Variation} = \frac{sigma}{\mu} \]

  • First Order::Quantile Coefficient Of Dispersion: A robust alternative to teh coefficient of variance:

    \[ \textup{Quantile Coefficient Of Dispersion} = \frac{P_{75\%} - P_{25\%} }{P_{75\%} + P_{25\%}} \]

  • First Order::Energy: The intensity energy:

    \[ \textup{Energy} = \sum x_i ^2 \]

  • First Order::Root Mean Square: Root mean square is an important measure for the error.

    \[ \textup{Root Mean Square} = \sqrt{\frac{\sum x_i ^2}{N_v}} \]

  • First Order::Uniformity:

    \[ \textup{Uniformity} = \sum p_x^2 \]

  • First Order::Entropy:

    \[ \textup{Entropy} = - \sum p_x \textup{log}_2(p_x) \]

  • First Order::Entropy:

    \[ \textup{Entropy} = - \sum p_x \textup{log}_2(p_x) \]

  • First Order::Covered Image Intensity Range: Percentage of the image intensity range (maximum - minimum in whole image) that is covered by the ROI.
  • First Order::Sum: The sum of all intensities. It is correlated to the mean intensity.

    \[ \textup{Sum} = \sum x_i \]

  • First Order::Mode: The most common intensity.
  • First Order::Mode Probability: The likelihood of the most common intensity.
  • First Order::Number Of Voxels: \( N_v \) the number of voxels covered by the ROI.
  • First Order::Image Dimension: The dimensionality of the image (e.g. 2D, 3D, etc.).
  • First Order::Number Of Voxels: The product of all spacing along all dimensions. In 3D, this is equal to the volume.
  • First Order::Number Of Voxels: The volume of a single voxel. If the dimensionality is only 2D, this is the surface of an voxel.

◆ New()

static Pointer mitk::GIFFirstOrderStatistics::New ( )
static

The documentation for this class was generated from the following files: