Medical Imaging Interaction Toolkit  2021.02.99-4e0dbe47
Medical Imaging Interaction Toolkit
mitk::GIFFirstOrderHistogramStatistics Class Reference

Calulates first order features based on a histogram. More...

#include <mitkGIFFirstOrderHistogramStatistics.h>

Inheritance diagram for mitk::GIFFirstOrderHistogramStatistics:
Collaboration diagram for mitk::GIFFirstOrderHistogramStatistics:

Public Member Functions

 mitkClassMacro (GIFFirstOrderHistogramStatistics, AbstractGlobalImageFeature)
 
Pointer Clone () const
 
 GIFFirstOrderHistogramStatistics ()
 
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

Calulates first order features based on a histogram.

This class can be used to calculate first order features based on a histogram. For each feature, two variations are given, once the value of the feature that is obtained if the mean intensity of the histogram bins is used and the histogram bin that corresponds to the feature value. See AbstractGlobalImageFeature for more information on the histogram initialization. The histogram gives a probability \(p_i\) for the intensity \(x_i\) that is linked to the bin \(i\). The histogram bins start at index 1.

This feature calculator is activated by the option "<b>-first-order-histogram</b>" or "<b>-foh</b>". Beside the options for the histogram definitions, which are given in the description of AbstractGlobalImageFeature , no additional parameters are available.

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

The resulting features are:

  • First Order Histogram::Mean Value: The mean intensity of all voxels, calulated by \( \mu_x = \sum p_i x_i\).
  • First Order Histogram::Variance Value The variance intensity is calculated as : \( \sigma^2 = \sum p_i (x_i - \mu_x)^2\).
  • First Order Histogram::Skewness Value:

    \[ skewness = \frac{\sum p_i (x_i - \mu_x)^3}{\sigma^3} \]

  • First Order Histogram::Excess Kurtosis Value:

    \[ skewness = \frac{\sum p_i (x_i - \mu_x)^4}{\sigma^4} - 3 \]

  • First Order Histogram::Median Value: The median intensity value based on the histogram values.
  • First Order Histogram::Minimum Value: The minimum observed intensity value.
  • First Order Histogram::Percentile 10 Value: The intensity that is equal or greater than 10% of all observed intensities.
  • First Order Histogram::Percentile 90 Value: The intensity that is equal or greater than 90% of all observed intensities.
  • First Order Histogram::Maximum Value: The maximum observerd intensity value.
  • First Order Histogram::Mode Value: The most common intensity value, i.e. the value of the bin with the highest probability.
  • First Order Histogram::Interquantile Range Value: The intensity difference between Percentile 75% ( \( P75\)) and Percentile 25% ( \( P25\)).
  • First Order Histogram::Range Value: The difference between the observed maximum and minimum intensity.
  • First Order Histogram::Mean Absolute Deviation Value:

    \[ \textup{mean absolute deviation} = \sum p_i \left \| (x_i - \mu_x) \right \| \]

  • First Order Histogram::Robust Mean Value: The mean of all intensities between the 10% and 90% quantile.
  • First Order Histogram::Robust Mean Absolute Deviation Value: The Mean absolute deviation for all values between the 10% and 90% quantile. It is based on the robust mean value.
  • First Order Histogram::Median Absolute Deviation Value:

    \[ \textup{mean absolute deviation} = \sum p_i \left \| (x_i - \textup{median}) \right \| \]

  • First Order Histogram::Coefficient of Variation Value:

    \[ \frac{\sigma_x}{\mu_x} \]

  • First Order Histogram::Quantile coefficient of Dispersion Value:

    \[ \textup{Quantile coefficient of Dispersion} = \frac{P75 - P25}{P75 + P25} \]

  • First Order Histogram::Entropy Value: The entropy is only based on histogram bins with a probability greater than 0.0000001:

    \[ \textup{entropy} = - \sum p_i \textup{log}_2 p_i \]

  • First Order Histogram::Uniformity Value: \( \sum p_i^2 \)
  • First Order Histogram::Mean Index: The mean index of all voxels, calulated by \( \mu_i = \sum p_i i\).
  • First Order Histogram::Variance Index: The variance index is calculated as : \( \sigma_i^2 = \sum p_i (i - \mu_i)^2\).
  • First Order Histogram::Skewness Index:

    \[ skewness = \frac{\sum p_i (i - \mu_i)^3}{\sigma_i^3} \]

  • First Order Histogram::Excess Kurtosis Index:

    \[ skewness = \frac{\sum p_i (i - \mu_i)^4}{\sigma_i^4} - 3 \]

  • First Order Histogram::Median Index: The median index value based on the histogram values.
  • First Order Histogram::Minimum Index: The index of the minimum observed intensity value.
  • First Order Histogram::Percentile 10 Index: The index oft the intensity that is equal or greater than 10% of all observed intensities.
  • First Order Histogram::Percentile 90 Index: The index of the intensity that is equal or greater than 90% of all observed intensities.
  • First Order Histogram::Maximum Index: The index of the maximum observerd intensity value.
  • First Order Histogram::Mode Index: The index of the most common intensity value, i.e. the index of the bin with the highest probability.
  • First Order Histogram::Interquantile Range Index: The index difference between Percentile 75% ( \( P75\)) and Percentile 25% ( \( P25\)).
  • First Order Histogram::Range Index: The index difference between the index of the observed maximum and minimum intensity.
  • First Order Histogram::Mean Absolute Deviation Index:

    \[ \textup{mean absolute deviation} = \sum p_i \left \| (i - \mu_i) \right \| \]

  • First Order Histogram::Robust Mean Absolute Deviation Index: The Mean absolute deviation for all values between the 10% and 90% quantile. It is based on the robust mean value.
  • First Order Histogram::Median Absolute Deviation Index:

    \[ \textup{mean absolute deviation} = \sum p_i \left \| (i - \textup{median}) \right \| \]

  • First Order Histogram::Coefficient of Variation Index:

    \[ \frac{\sigma_i}{\mu_i} \]

  • First Order Histogram::Quantile coefficient of Dispersion Index:

    \[ \textup{Quantile coefficient of Dispersion} = \frac{P75 - P25}{P75 + P25} \]

  • First Order Histogram::Entropy Index: The entropy is only based on histogram bins with a probability greater than 0.0000001: \( \textup{entropy} = - \sum p_i \textup{log}_2 p_i \). Note that this is the same as the entropy value.
  • First Order Histogram::Uniformity Index: \( \sum p_i^2 \). Note that this is the same as the uniformity value.
  • First Order Histogram::Maximum Gradient: The maximum difference between the probability of three neighbouring bins. For bins at the edge of the histogram, only two bins are used for the calulation.
  • First Order Histogram::Maximum Gradient Index: The index of the bin that belongs to the maximum gradient.
  • First Order Histogram::Minimum Gradient: The minimum difference between the probability of three neighbouring bins. For bins at the edge of the histogram, only two bins are used for the calulation.
  • First Order Histogram::Minimum Gradient Index:The index of the bin that belongs to the minimum gradient.
  • First Order Histogram::Robust Mean Index: The mean index of all intensities between the 10% and 90% quantile.
  • First Order Histogram::Number of Bins: The number of bins in the histogram. This is rather for control, as this parameter is likely to be determined by the configuration rather than the image.
  • First Order Histogram::Bin Size: The binsize of the bins from the histogram. This is rather for control, as this parameter is likely to be determined by the configuration rather than the image.

Definition at line 88 of file mitkGIFFirstOrderHistogramStatistics.h.

Constructor & Destructor Documentation

◆ GIFFirstOrderHistogramStatistics()

mitk::GIFFirstOrderHistogramStatistics::GIFFirstOrderHistogramStatistics ( )

Member Function Documentation

◆ AddArguments()

void mitk::GIFFirstOrderHistogramStatistics::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.

◆ CalculateFeatures()

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

◆ Clone()

Pointer mitk::GIFFirstOrderHistogramStatistics::Clone ( ) const

◆ DoCalculateFeatures()

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

◆ mitkClassMacro()

mitk::GIFFirstOrderHistogramStatistics::mitkClassMacro ( GIFFirstOrderHistogramStatistics  ,
AbstractGlobalImageFeature   
)

◆ New()

static Pointer mitk::GIFFirstOrderHistogramStatistics::New ( )
static

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