itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage > Class Template Reference

A base class which defines the API for implementing a special class of image segmentation filters using level set methods. More...

#include <itkSegmentationLevelSetImageFilter.h>

Inheritance diagram for itk::SegmentationLevelSetImageFilter:

[legend]Collaboration diagram for itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >:

[legend]List of all members.

Public Types
typedef SegmentationLevelSetImageFilter	Self
typedef SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::ValueType	ValueType
typedef Superclass::IndexType	IndexType
typedef Superclass::TimeStepType	TimeStepType
typedef Superclass::OutputImageType	OutputImageType
typedef Superclass::InputImageType	InputImageType
typedef SegmentationLevelSetFunction< TOutputImage >	SegmentationFunctionType
typedef SegmentationFunctionType::FeatureImageType	FeatureImageType
Public Methods
virtual const char *	GetClassName () const
virtual SegmentationFunctionType::ImageType *	GetSpeedImage () const
virtual void	SetMaximumRMSError (ValueType _arg)
virtual ValueType	GetMaximumRMSError ()
virtual void	SetMaximumIterations (unsigned int _arg)
virtual unsigned int	GetMaximumIterations ()
virtual void	SetFeatureImage (FeatureImageType *f)
virtual FeatureImageType *	GetFeatureImage () const
void	SetUseNegativeFeaturesOn ()
void	SetUseNegativeFeaturesOff ()
virtual void	SetUseNegativeFeatures (bool _arg)
virtual bool	GetUseNegativeFeatures ()
virtual void	SetFeatureScaling (ValueType _arg)
virtual ValueType	GetFeatureScaling ()
virtual void	SetCurvatureScaling (ValueType _arg)
virtual ValueType	GetCurvatureScaling ()
virtual void	SetSegmentationFunction (SegmentationFunctionType *s)
virtual SegmentationFunctionType *	GetSegmentationFunction ()
Protected Methods
virtual	~SegmentationLevelSetImageFilter ()
	SegmentationLevelSetImageFilter ()
virtual void	PrintSelf (std::ostream &os, Indent indent) const
void	GenerateData ()
bool	Halt ()
virtual void	InitializeIteration ()
Protected Attributes
bool	m_UseNegativeFeatures
ValueType	m_FeatureScaling
ValueType	m_CurvatureScaling

---

Detailed Description

template<class TInputImage, class TOutputImage>
class itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >

A base class which defines the API for implementing a special class of image segmentation filters using level set methods.

OVERVIEW

This object defines the framework for a class of segmentation filters which use level set methods. These filters work by constructing a ``feature image'' onto which the evolving level set locks as it moves. In the feature image, values that are close to zero are associated with object boundaries. An original (or preprocessed) image is given to the filter as the feature image and a seed for the level set is given as the input of the filter. The seed is converted into a level set embedding which propagates according to the features calculated from the original image.

INPUTS

The input to any subclass of this filter is the seed image for the initial level set embedding. As with other subclasses of the SparseLevelSetImageFilter, the type of the input image is is not important. The (RequestedRegion) size of the seed image must, however, match the (RequestedRegion) size of the feature image.

Depending on the particular application and filter that you are using, the feature image should be preprocessed with some type of noise reduction filtering. The feature image should be of a floating point type (floats or doubles). You may need to cast your image to this type before attaching it to this filter.

OUTPUTS

The output of any subclass of this filter is a level set embedding as described in SparseFieldLevelSetImageFilter. The zero crossings of the output image give the pixels closest to the level set boundary. By ITK convention, positive values are pixels inside the segmented region and negative values are pixels outside the segmented region.

PARAMETERS

The MaximumRMSChange parameter is used to determine when the solution has converged. A lower value will result in a tighter-fitting solution, but will require more computations. Too low a value could put the solver into an infinite loop unless a reasonable MaximumIterations parameter is set. Values should always be greater than 0.0 and less than 1.0.

The MaximumIterations parameter can be used to halt the solution after a specified number of iterations, overriding the MaximumRMSChange halting criteria.

The UseNegativeFeatures parameter tells the function object to reverse the sign of the feature image, which also reverses the INSIDE OUTSIDE sign convention.

The FeatureScaling parameter controls the magnitude of the features calculated for use in the level set propagation speed. This is important in controlling the relative effect of the feature values versus the curvature values (and possibly other terms). Default value is 1.0.

The CurvatureScaling parameter controls the magnitude of the curvature values which are calculated on the evolving isophote. This is important in controlling the relative effect of curvature in the calculation. Default value is 1.0.

Todo:

Use a second input image for the feature image instead of keeping the feature image as a parameter. This may be tricky because the feature image may be of a different type as the first input (seed image) and so the default pipeline mechanism will have to be modified. When this is done, however, it will allow the feature image to be properly updated in a unified pipeline with the seed image.

Definition at line 100 of file itkSegmentationLevelSetImageFilter.h.

---

Member Typedef Documentation

template<class TInputImage, class TOutputImage> typedef SmartPointer<const Self> itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::ConstPointer

Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 108 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SegmentationFunctionType::FeatureImageType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::FeatureImageType

Feature image type Definition at line 121 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::IndexType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::IndexType

Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 112 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::InputImageType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::InputImageType

Information derived from the image types. Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 115 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::OutputImageType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::OutputImageType

Some convenient typedefs. Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 114 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SmartPointer<Self> itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::Pointer

Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 107 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SegmentationLevelSetFunction<TOutputImage> itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SegmentationFunctionType

The generic level set function type Definition at line 118 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SegmentationLevelSetImageFilter itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::Self

Standard class typedefs Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 105 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SparseFieldLevelSetImageFilter<TInputImage, TOutputImage> itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::Superclass

Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 106 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::TimeStepType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::TimeStepType

Typedefs from the superclass Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 113 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::ValueType

Inherited typedef from the superclass. Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >. Definition at line 111 of file itkSegmentationLevelSetImageFilter.h.

---

Constructor & Destructor Documentation

template<class TInputImage, class TOutputImage> virtual itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::~SegmentationLevelSetImageFilter (    )  [inline, protected, virtual]

Definition at line 191 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SegmentationLevelSetImageFilter (    )  [protected]

---

Member Function Documentation

template<class TInputImage, class TOutputImage> void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GenerateData (    )  [protected, virtual]

Overridden from ProcessObject to set certain values before starting the finite difference solver and then create an appropriate output Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual const char* itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetClassName (    )  const [virtual]

Run-time type information (and related methods). Reimplemented from itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetCurvatureScaling (    )  [virtual]

Set/Get the scaling of the curvature.

template<class TInputImage, class TOutputImage> virtual FeatureImageType* itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetFeatureImage (    )  const [inline, virtual]

Set/Get the feature image to be used for speed function of the level set equation Definition at line 145 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> virtual ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetFeatureScaling (    )  [virtual]

Set/Get the scaling of the propagation speed.

template<class TInputImage, class TOutputImage> virtual unsigned int itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetMaximumIterations (    )  [virtual]

Set/Get the maximum number of iterations allowed for the solver. This prevents infinite loops if a solution "bounces".

template<class TInputImage, class TOutputImage> virtual ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetMaximumRMSError (    )  [virtual]

Set/Get the maximum RMS error allowed for the solution. The solver will halt once this threshold has been reached.

template<class TInputImage, class TOutputImage> virtual SegmentationFunctionType* itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetSegmentationFunction (    )  [inline, virtual]

Set the segmentation function. In general, this should only be called by a subclass of this object. It is made public to allow itk::Command objects access. Definition at line 186 of file itkSegmentationLevelSetImageFilter.h. References HardConnectedComponentImageFilter::PrintSelf().

template<class TInputImage, class TOutputImage> virtual SegmentationFunctionType::ImageType* itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetSpeedImage (    )  const [inline, virtual]

Definition at line 149 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> virtual bool itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::GetUseNegativeFeatures (    )  [virtual]

Set/Get the value of the UseNegativeFeatures flag. This flag controls whether (true) or not (false) the direction of the speed function is reversed. By default, level set segmentation filters take ``inside'' values as positive, and ``outside'' values as negative.

template<class TInputImage, class TOutputImage> bool itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::Halt (    )  [protected, virtual]

Tells the solver when the solution has converged within the specified parameters. Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::InitializeIteration (    )  [inline, protected, virtual]

Overrides parent implementation Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >. Definition at line 197 of file itkSegmentationLevelSetImageFilter.h. References HardConnectedComponentImageFilter::GenerateData().

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::PrintSelf (  std::ostream &    os, Indent    indent )  const [protected, virtual]

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::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TOutputImage >, and itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetCurvatureScaling (  ValueType    _arg )  [virtual]

Set/Get the scaling of the curvature.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetFeatureImage (  FeatureImageType *    f )  [inline, virtual]

Set/Get the feature image to be used for speed function of the level set equation Definition at line 140 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetFeatureScaling (  ValueType    _arg )  [virtual]

Set/Get the scaling of the propagation speed.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetMaximumIterations (  unsigned int    _arg )  [virtual]

Set/Get the maximum number of iterations allowed for the solver. This prevents infinite loops if a solution "bounces".

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetMaximumRMSError (  ValueType    _arg )  [virtual]

Set/Get the maximum RMS error allowed for the solution. The solver will halt once this threshold has been reached.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetSegmentationFunction (  SegmentationFunctionType *    s )  [virtual]

Set the segmentation function. In general, this should only be called by a subclass of this object. It is made public to allow itk::Command objects access.

template<class TInputImage, class TOutputImage> virtual void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetUseNegativeFeatures (  bool    _arg )  [virtual]

Set/Get the value of the UseNegativeFeatures flag. This flag controls whether (true) or not (false) the direction of the speed function is reversed. By default, level set segmentation filters take ``inside'' values as positive, and ``outside'' values as negative.

template<class TInputImage, class TOutputImage> void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetUseNegativeFeaturesOff (    )  [inline]

This method reverses the speed function direction, effectively changing inside feature values to outside feature values and vice versa Definition at line 159 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> void itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::SetUseNegativeFeaturesOn (    )  [inline]

This method reverses the speed function direction, effectively changing inside feature values to outside feature values and vice versa Definition at line 155 of file itkSegmentationLevelSetImageFilter.h.

---

Member Data Documentation

template<class TInputImage, class TOutputImage> ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::m_CurvatureScaling [protected]

Scalar parameter for curvature. Definition at line 222 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> ValueType itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::m_FeatureScaling [protected]

Scalar parameter for propagation speed. Definition at line 219 of file itkSegmentationLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage> bool itk::SegmentationLevelSetImageFilter< TInputImage, TOutputImage >::m_UseNegativeFeatures [protected]

Flag which sets the inward/outward direction of positive propagation speed. Definition at line 216 of file itkSegmentationLevelSetImageFilter.h.

---

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

• itkSegmentationLevelSetImageFilter.h

---