ITK  6.0.0
Insight Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | Protected Member Functions | Private Attributes | List of all members
itk::CurvesLevelSetFunction< TImageType, TFeatureImageType > Class Template Reference

#include <itkCurvesLevelSetFunction.h>

Detailed Description

template<typename TImageType, typename TFeatureImageType = TImageType>
class itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >

This function is used in CurvesLevelSetImageFilter to segment structures in images based on user supplied edge potential map.

CurvesLevelSetFunction is a subclass of the generic LevelSetFunction.
It is useful for segmentations based on a user supplied edge potential map which has values close to zero in regions near edges (or high image gradient) and values close to one in regions with relatively constant intensity. Typically, the edge potential map is a function of the gradient, for example:

\[ g(I) = 1 / ( 1 + | (\nabla * G)(I)| ) \]

\[ g(I) = \exp^{-|(\nabla * G)(I)|} \]

where \( I \) is image intensity and \( (\nabla * G) \) is the derivative of Gaussian operator.

In this function both the propagation term \( (\nabla * G) \)#317
and the curvature spatial modifier term $ \( Z(\mathbf{x}) \) are taken directly from the edge potential image. The edge potential image is set via the SetFeatureImage() method. An advection term \( A(\mathbf{x}) \) is constructed from the negative gradient of the edge potential image. This term behaves like a doublet attracting the contour to the edges.
This implementation is based on:
L. Lorigo, O. Faugeras, W.E.L. Grimson, R. Keriven, R. Kikinis, A. Nabavi, and C.-F. Westin, Curves: Curve evolution for vessel segmentation. Medical Image Analysis, 5:195-206, 2001.
See also
LevelSetFunction
SegmentationLevelSetImageFunction
GeodesicActiveContourLevelSetImageFilter

Definition at line 62 of file itkCurvesLevelSetFunction.h.

+ Inheritance diagram for itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >:
+ Collaboration diagram for itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >:

Public Types

using ConstPointer = SmartPointer< const Self >
 
using FeatureImageType = TFeatureImageType
 
using FloatOffsetType = typename SuperSuperclass::FloatOffsetType
 
using GlobalDataStruct = typename SuperSuperclass::GlobalDataStruct
 
using PixelType = typename SuperSuperclass::PixelType
 
using Pointer = SmartPointer< Self >
 
using Self = CurvesLevelSetFunction
 
using Superclass = SegmentationLevelSetFunction< TImageType, TFeatureImageType >
 
using SuperSuperclass = LevelSetFunction< TImageType >
 
- Public Types inherited from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >
using ConstPointer = SmartPointer< const Self >
 
using ContinuousIndexType = typename InterpolatorType::ContinuousIndexType
 
using FeatureImageType = TFeatureImageType
 
using FeatureScalarType = typename FeatureImageType::PixelType
 
using IndexType = typename ImageType::IndexType
 
using InterpolatorType = LinearInterpolateImageFunction< ImageType >
 
using Pointer = SmartPointer< Self >
 
using Self = SegmentationLevelSetFunction
 
using Superclass = LevelSetFunction< TImageType >
 
using VectorImageType = Image< VectorType, Self::ImageDimension >
 
using VectorInterpolatorType = VectorLinearInterpolateImageFunction< VectorImageType >
 
- Public Types inherited from itk::LevelSetFunction< TImageType >
using ConstPointer = SmartPointer< const Self >
 
using Pointer = SmartPointer< Self >
 
using ScalarValueType = PixelType
 
using Self = LevelSetFunction
 
using Superclass = FiniteDifferenceFunction< TImageType >
 
using TimeStepType = double
 
using VectorType = FixedArray< ScalarValueType, Self::ImageDimension >
 
- Public Types inherited from itk::FiniteDifferenceFunction< TImageType >
using ConstPointer = SmartPointer< const Self >
 
using DefaultBoundaryConditionType = ZeroFluxNeumannBoundaryCondition< ImageType >
 
using FloatOffsetType = Vector< float, Self::ImageDimension >
 
using ImageType = TImageType
 
using NeighborhoodScalesType = Vector< PixelRealType, Self::ImageDimension >
 
using NeighborhoodType = ConstNeighborhoodIterator< TImageType, DefaultBoundaryConditionType >
 
using PixelRealType = double
 
using PixelType = typename ImageType::PixelType
 
using Pointer = SmartPointer< Self >
 
using RadiusType = typename ConstNeighborhoodIterator< TImageType >::RadiusType
 
using Self = FiniteDifferenceFunction
 
using Superclass = LightObject
 
using TimeStepType = double
 
- Public Types inherited from itk::LightObject
using ConstPointer = SmartPointer< const Self >
 
using Pointer = SmartPointer< Self >
 
using Self = LightObject
 

Public Member Functions

void CalculateAdvectionImage () override
 
void CalculateSpeedImage () override
 
ScalarValueType CurvatureSpeed (const NeighborhoodType &neighborhood, const FloatOffsetType &offset, GlobalDataStruct *gd) const override
 
const char * GetNameOfClass () const override
 
void Initialize (const RadiusType &r) override
 
void SetDerivativeSigma (const double v)
 
double GetDerivativeSigma ()
 
- Public Member Functions inherited from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >
virtual void AllocateAdvectionImage ()
 
virtual void AllocateSpeedImage ()
 
const char * GetNameOfClass () const override
 
void Initialize (const RadiusType &r) override
 
virtual void ReverseExpansionDirection ()
 
virtual const FeatureImageTypeGetFeatureImage () const
 
virtual void SetFeatureImage (const FeatureImageType *f)
 
virtual ImageTypeGetSpeedImage ()
 
void SetSpeedImage (ImageType *s)
 
virtual VectorImageTypeGetAdvectionImage () const
 
void SetAdvectionImage (VectorImageType *s)
 
- Public Member Functions inherited from itk::LevelSetFunction< TImageType >
virtual ScalarValueType Compute3DMinimalCurvature (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd=0)
 
virtual ScalarValueType ComputeCurvatureTerm (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd=0)
 
TimeStepType ComputeGlobalTimeStep (void *GlobalData) const override
 
virtual ScalarValueType ComputeMeanCurvature (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd=0)
 
virtual ScalarValueType ComputeMinimalCurvature (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd=0)
 
PixelType ComputeUpdate (const NeighborhoodType &it, void *globalData, const FloatOffsetType &=FloatOffsetType(0.0)) override
 
virtual ScalarValueType CurvatureSpeed (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *=nullptr) const
 
void * GetGlobalDataPointer () const override
 
bool GetUseMinimalCurvature () const
 
virtual ScalarValueType LaplacianSmoothingSpeed (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *=0) const
 
void ReleaseGlobalDataPointer (void *GlobalData) const override
 
void SetUseMinimalCurvature (bool b)
 
void UseMinimalCurvatureOff ()
 
void UseMinimalCurvatureOn ()
 
virtual void SetAdvectionWeight (const ScalarValueType a)
 
ScalarValueType GetAdvectionWeight () const
 
virtual void SetPropagationWeight (const ScalarValueType p)
 
ScalarValueType GetPropagationWeight () const
 
virtual void SetCurvatureWeight (const ScalarValueType c)
 
ScalarValueType GetCurvatureWeight () const
 
void SetLaplacianSmoothingWeight (const ScalarValueType c)
 
ScalarValueType GetLaplacianSmoothingWeight () const
 
void SetEpsilonMagnitude (const ScalarValueType e)
 
ScalarValueType GetEpsilonMagnitude () const
 
- Public Member Functions inherited from itk::FiniteDifferenceFunction< TImageType >
const NeighborhoodScalesType ComputeNeighborhoodScales () const
 
const RadiusTypeGetRadius () const
 
void GetScaleCoefficients (PixelRealType vals[ImageDimension]) const
 
virtual void InitializeIteration ()
 
void SetRadius (const RadiusType &r)
 
void SetScaleCoefficients (const PixelRealType vals[ImageDimension])
 
- Public Member Functions inherited from itk::LightObject
Pointer Clone () const
 
virtual Pointer CreateAnother () const
 
virtual void Delete ()
 
virtual int GetReferenceCount () const
 
void Print (std::ostream &os, Indent indent=0) const
 
virtual void Register () const
 
virtual void SetReferenceCount (int)
 
virtual void UnRegister () const noexcept
 

Static Public Member Functions

static Pointer New ()
 
- Static Public Member Functions inherited from itk::LevelSetFunction< TImageType >
static double GetMaximumCurvatureTimeStep ()
 
static double GetMaximumPropagationTimeStep ()
 
static Pointer New ()
 
static void SetMaximumCurvatureTimeStep (double n)
 
static void SetMaximumPropagationTimeStep (double n)
 
- Static Public Member Functions inherited from itk::LightObject
static void BreakOnError ()
 
static Pointer New ()
 

Static Public Attributes

static constexpr unsigned int ImageDimension = Superclass::ImageDimension
 
- Static Public Attributes inherited from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >
static constexpr unsigned int ImageDimension = Superclass::ImageDimension
 
- Static Public Attributes inherited from itk::LevelSetFunction< TImageType >
static constexpr unsigned int ImageDimension = Superclass::ImageDimension
 
- Static Public Attributes inherited from itk::FiniteDifferenceFunction< TImageType >
static constexpr unsigned int ImageDimension = ImageType::ImageDimension
 

Protected Member Functions

 CurvesLevelSetFunction ()
 
void PrintSelf (std::ostream &os, Indent indent) const override
 
 ~CurvesLevelSetFunction () override=default
 
- Protected Member Functions inherited from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >
VectorType AdvectionField (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd) const override
 
ScalarValueType PropagationSpeed (const NeighborhoodType &, const FloatOffsetType &, GlobalDataStruct *gd) const override
 
 SegmentationLevelSetFunction ()
 
 ~SegmentationLevelSetFunction () override=default
 
- Protected Member Functions inherited from itk::LevelSetFunction< TImageType >
 LevelSetFunction ()
 
void PrintSelf (std::ostream &os, Indent indent) const override
 
 ~LevelSetFunction () override=default
 
- Protected Member Functions inherited from itk::FiniteDifferenceFunction< TImageType >
 FiniteDifferenceFunction ()
 
 ~FiniteDifferenceFunction () override=default
 
- Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer InternalClone () const
 
 LightObject ()
 
virtual void PrintHeader (std::ostream &os, Indent indent) const
 
virtual void PrintTrailer (std::ostream &os, Indent indent) const
 
virtual ~LightObject ()
 

Private Attributes

OffsetValueType m_Center { 0 }
 
double m_DerivativeSigma { 1.0 }
 
OffsetValueType m_xStride [ImageDimension] {}
 
std::slice x_slice [ImageDimension]
 

Additional Inherited Members

- Static Protected Member Functions inherited from itk::LevelSetFunction< TImageType >
static VectorType InitializeZeroVectorConstant ()
 
- Protected Attributes inherited from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >
VectorImageType::Pointer m_AdvectionImage {}
 
FeatureImageType::ConstPointer m_FeatureImage {}
 
InterpolatorType::Pointer m_Interpolator {}
 
ImageType::Pointer m_SpeedImage {}
 
VectorInterpolatorType::Pointer m_VectorInterpolator {}
 
- Protected Attributes inherited from itk::LevelSetFunction< TImageType >
ScalarValueType m_AdvectionWeight {}
 
OffsetValueType m_Center { 0 }
 
ScalarValueType m_CurvatureWeight {}
 
ScalarValueType m_EpsilonMagnitude {}
 
ScalarValueType m_LaplacianSmoothingWeight {}
 
ScalarValueType m_PropagationWeight {}
 
bool m_UseMinimalCurvature { false }
 
OffsetValueType m_xStride [Self::ImageDimension] {}
 
std::slice x_slice [Self::ImageDimension]
 
- Protected Attributes inherited from itk::FiniteDifferenceFunction< TImageType >
RadiusType m_Radius {}
 
PixelRealType m_ScaleCoefficients [ImageDimension] {}
 
- Protected Attributes inherited from itk::LightObject
std::atomic< int > m_ReferenceCount {}
 
- Static Protected Attributes inherited from itk::LevelSetFunction< TImageType >
static double m_DT
 
static double m_WaveDT
 
static VectorType m_ZeroVectorConstant
 

Member Typedef Documentation

◆ ConstPointer

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::ConstPointer = SmartPointer<const Self>

Definition at line 72 of file itkCurvesLevelSetFunction.h.

◆ FeatureImageType

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::FeatureImageType = TFeatureImageType

Definition at line 73 of file itkCurvesLevelSetFunction.h.

◆ FloatOffsetType

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::FloatOffsetType = typename SuperSuperclass::FloatOffsetType

Definition at line 88 of file itkCurvesLevelSetFunction.h.

◆ GlobalDataStruct

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::GlobalDataStruct = typename SuperSuperclass::GlobalDataStruct

Definition at line 89 of file itkCurvesLevelSetFunction.h.

◆ PixelType

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::PixelType = typename SuperSuperclass::PixelType

Extract some parameters from the superclass.

Definition at line 82 of file itkCurvesLevelSetFunction.h.

◆ Pointer

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::Pointer = SmartPointer<Self>

Definition at line 71 of file itkCurvesLevelSetFunction.h.

◆ Self

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::Self = CurvesLevelSetFunction

Standard class type aliases.

Definition at line 68 of file itkCurvesLevelSetFunction.h.

◆ Superclass

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::Superclass = SegmentationLevelSetFunction<TImageType, TFeatureImageType>

Definition at line 69 of file itkCurvesLevelSetFunction.h.

◆ SuperSuperclass

template<typename TImageType , typename TFeatureImageType = TImageType>
using itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::SuperSuperclass = LevelSetFunction<TImageType>

Definition at line 70 of file itkCurvesLevelSetFunction.h.

Constructor & Destructor Documentation

◆ CurvesLevelSetFunction()

template<typename TImageType , typename TFeatureImageType = TImageType>
itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::CurvesLevelSetFunction ( )
inlineprotected

Definition at line 130 of file itkCurvesLevelSetFunction.h.

◆ ~CurvesLevelSetFunction()

template<typename TImageType , typename TFeatureImageType = TImageType>
itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::~CurvesLevelSetFunction ( )
overrideprotecteddefault

Member Function Documentation

◆ CalculateAdvectionImage()

template<typename TImageType , typename TFeatureImageType = TImageType>
void itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::CalculateAdvectionImage ( )
overridevirtual

Compute the advection field from feature image.

Reimplemented from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >.

◆ CalculateSpeedImage()

template<typename TImageType , typename TFeatureImageType = TImageType>
void itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::CalculateSpeedImage ( )
overridevirtual

Compute speed image from feature image.

Reimplemented from itk::SegmentationLevelSetFunction< TImageType, TFeatureImageType >.

◆ CurvatureSpeed()

template<typename TImageType , typename TFeatureImageType = TImageType>
ScalarValueType itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::CurvatureSpeed ( const NeighborhoodType neighborhood,
const FloatOffsetType offset,
GlobalDataStruct gd 
) const
inlineoverride

The curvature speed is same as the propagation speed.

Definition at line 105 of file itkCurvesLevelSetFunction.h.

◆ GetDerivativeSigma()

template<typename TImageType , typename TFeatureImageType = TImageType>
double itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::GetDerivativeSigma ( )
inline

Set/Get the sigma for the Gaussian kernel used to compute the gradient of the feature image needed for the advection term of the equation.

Definition at line 120 of file itkCurvesLevelSetFunction.h.

◆ GetNameOfClass()

template<typename TImageType , typename TFeatureImageType = TImageType>
const char* itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::GetNameOfClass ( ) const
overridevirtual

◆ Initialize()

template<typename TImageType , typename TFeatureImageType = TImageType>
void itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::Initialize ( const RadiusType r)
overridevirtual

This method creates the appropriate member variable operators for the level-set calculations. The argument to this function is a the radius necessary for performing the level-set calculations.

Reimplemented from itk::LevelSetFunction< TImageType >.

◆ New()

template<typename TImageType , typename TFeatureImageType = TImageType>
static Pointer itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::New ( )
static

Method for creation through the object factory.

◆ PrintSelf()

template<typename TImageType , typename TFeatureImageType = TImageType>
void itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const
inlineoverrideprotectedvirtual

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes.

Reimplemented from itk::FiniteDifferenceFunction< TImageType >.

Definition at line 143 of file itkCurvesLevelSetFunction.h.

◆ SetDerivativeSigma()

template<typename TImageType , typename TFeatureImageType = TImageType>
void itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::SetDerivativeSigma ( const double  v)
inline

Set/Get the sigma for the Gaussian kernel used to compute the gradient of the feature image needed for the advection term of the equation.

Definition at line 115 of file itkCurvesLevelSetFunction.h.

Member Data Documentation

◆ ImageDimension

template<typename TImageType , typename TFeatureImageType = TImageType>
constexpr unsigned int itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::ImageDimension = Superclass::ImageDimension
staticconstexpr

Extract some parameters from the superclass.

Definition at line 93 of file itkCurvesLevelSetFunction.h.

◆ m_Center

template<typename TImageType , typename TFeatureImageType = TImageType>
OffsetValueType itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::m_Center { 0 }
private

The offset of the center pixel in the neighborhood.

Definition at line 154 of file itkCurvesLevelSetFunction.h.

◆ m_DerivativeSigma

template<typename TImageType , typename TFeatureImageType = TImageType>
double itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::m_DerivativeSigma { 1.0 }
private

Definition at line 159 of file itkCurvesLevelSetFunction.h.

◆ m_xStride

template<typename TImageType , typename TFeatureImageType = TImageType>
OffsetValueType itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::m_xStride[ImageDimension] {}
private

Stride length along the y-dimension.

Definition at line 157 of file itkCurvesLevelSetFunction.h.

◆ x_slice

template<typename TImageType , typename TFeatureImageType = TImageType>
std::slice itk::CurvesLevelSetFunction< TImageType, TFeatureImageType >::x_slice[ImageDimension]
private

Slices for the ND neighborhood.

Definition at line 151 of file itkCurvesLevelSetFunction.h.


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