ITK  4.2.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | Protected Member Functions | Protected Attributes | Static Protected Attributes | Private Attributes
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage > Class Template Reference

#include <itkSparseFieldLevelSetImageFilter.h>

+ Inheritance diagram for itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >:
+ Collaboration diagram for itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef OutputImageType::IndexType IndexType
typedef TInputImage InputImageType
typedef std::vector
< LayerPointerType
LayerListType
typedef ObjectStore
< LayerNodeType
LayerNodeStorageType
typedef
SparseFieldLevelSetNode
< IndexType
LayerNodeType
typedef LayerType::Pointer LayerPointerType
typedef SparseFieldLayer
< LayerNodeType
LayerType
typedef
Superclass::NeighborhoodScalesType 
NeighborhoodScalesType
typedef TOutputImage OutputImageType
typedef SmartPointer< SelfPointer
typedef Superclass::RadiusType RadiusType
typedef
SparseFieldLevelSetImageFilter 
Self
typedef Image< StatusType,
itkGetStaticConstMacro(ImageDimension) > 
StatusImageType
typedef signed char StatusType
typedef
FiniteDifferenceImageFilter
< TInputImage, TOutputImage > 
Superclass
typedef Superclass::TimeStepType TimeStepType
typedef std::vector< ValueTypeUpdateBufferType
typedef OutputImageType::ValueType ValueType
- Public Types inherited from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >
typedef
FiniteDifferenceFunction
< TOutputImage > 
FiniteDifferenceFunctionType
typedef TInputImage::PixelType InputPixelType
typedef NumericTraits
< InputPixelType >::ValueType 
InputPixelValueType
typedef TOutputImage::PixelType OutputPixelType
typedef NumericTraits
< OutputPixelType >::ValueType 
OutputPixelValueType
typedef OutputPixelType PixelType
- Public Types inherited from itk::InPlaceImageFilter< TInputImage, TOutputImage >
typedef
InputImageType::ConstPointer 
InputImageConstPointer
typedef InputImageType::PixelType InputImagePixelType
typedef InputImageType::Pointer InputImagePointer
typedef InputImageType::RegionType InputImageRegionType
typedef
Superclass::OutputImagePixelType 
OutputImagePixelType
typedef
Superclass::OutputImagePointer 
OutputImagePointer
typedef
Superclass::OutputImageRegionType 
OutputImageRegionType
- Public Types inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
- Public Types inherited from itk::ImageSource< TOutputImage >
typedef
Superclass::DataObjectIdentifierType 
DataObjectIdentifierType
typedef DataObject::Pointer DataObjectPointer
typedef
Superclass::DataObjectPointerArraySizeType 
DataObjectPointerArraySizeType
- Public Types inherited from itk::ProcessObject
typedef std::vector
< DataObjectPointer
DataObjectPointerArray
typedef std::vector
< DataObjectIdentifierType
NameArray
- Public Types inherited from itk::Object
- Public Types inherited from itk::LightObject

Public Member Functions

virtual ::itk::LightObject::Pointer CreateAnother (void) const
virtual const char * GetNameOfClass () const
 typedef (Concept::EqualityComparable< typename TOutputImage::PixelType >) OutputEqualityComparableCheck
 typedef (Concept::Convertible< double, typename TOutputImage::PixelType >) DoubleConvertibleToOutputCheck
 typedef (Concept::OStreamWritable< typename TOutputImage::PixelType >) OutputOStreamWritableCheck
virtual void SetNumberOfLayers (unsigned int _arg)
virtual unsigned int GetNumberOfLayers () const
virtual void SetIsoSurfaceValue (ValueType _arg)
virtual ValueType GetIsoSurfaceValue () const
virtual void SetInterpolateSurfaceLocation (bool _arg)
virtual bool GetInterpolateSurfaceLocation () const
void InterpolateSurfaceLocationOn ()
void InterpolateSurfaceLocationOff ()
- Public Member Functions inherited from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >
virtual const
FiniteDifferenceFunctionType::Pointer
GetDifferenceFunction () const
virtual const IdentifierTypeGetElapsedIterations ()
virtual bool GetIsInitialized ()
virtual void SetDifferenceFunction (FiniteDifferenceFunctionType *_arg)
virtual void SetIsInitialized (bool _arg)
void SetStateToInitialized ()
void SetStateToUninitialized ()
virtual void SetNumberOfIterations (IdentifierType _arg)
virtual const IdentifierTypeGetNumberOfIterations ()
virtual void SetUseImageSpacing (bool _arg)
virtual void UseImageSpacingOn ()
virtual void UseImageSpacingOff ()
virtual const bool & GetUseImageSpacing ()
virtual void SetMaximumRMSError (double _arg)
virtual const double & GetMaximumRMSError ()
virtual void SetRMSChange (double _arg)
virtual const double & GetRMSChange ()
virtual void SetManualReinitialization (bool _arg)
virtual const bool & GetManualReinitialization ()
virtual void ManualReinitializationOn ()
virtual void ManualReinitializationOff ()
- Public Member Functions inherited from itk::InPlaceImageFilter< TInputImage, TOutputImage >
virtual bool CanRunInPlace () const
virtual void SetInPlace (bool _arg)
virtual bool GetInPlace () const
virtual void InPlaceOn ()
virtual void InPlaceOff ()
- Public Member Functions inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
const InputImageTypeGetInput (void) const
const InputImageTypeGetInput (unsigned int idx) const
virtual void PopBackInput ()
virtual void PopFrontInput ()
virtual void PushBackInput (const InputImageType *image)
virtual void PushFrontInput (const InputImageType *image)
virtual void SetInput (const InputImageType *image)
virtual void SetInput (unsigned int, const TInputImage *image)
- Public Member Functions inherited from itk::ImageSource< TOutputImage >
OutputImageTypeGetOutput (unsigned int idx)
virtual void GraftNthOutput (unsigned int idx, DataObject *output)
virtual void GraftOutput (DataObject *output)
virtual void GraftOutput (const DataObjectIdentifierType &key, DataObject *output)
OutputImageTypeGetOutput (void)
const OutputImageTypeGetOutput (void) const
virtual
ProcessObject::DataObjectPointer 
MakeOutput (ProcessObject::DataObjectPointerArraySizeType idx)
- Public Member Functions inherited from itk::ProcessObject
virtual void AbortGenerateDataOff ()
virtual void AbortGenerateDataOn ()
virtual void EnlargeOutputRequestedRegion (DataObject *)
virtual const bool & GetAbortGenerateData ()
NameArray GetInputNames () const
MultiThreader * GetMultiThreader () const
DataObjectPointerArraySizeType GetNumberOfIndexedInputs () const
DataObjectPointerArraySizeType GetNumberOfInputs () const
DataObjectPointerArraySizeType GetNumberOfOutputs () const
virtual
DataObjectPointerArraySizeType 
GetNumberOfValidRequiredInputs () const
NameArray GetOutputNames () const
virtual const float & GetProgress ()
NameArray GetRequiredInputNames () const
bool HasInput (const DataObjectIdentifierType &key) const
bool HasOutput (const DataObjectIdentifierType &key) const
virtual DataObjectPointer MakeOutput (const DataObjectIdentifierType &)
virtual void PrepareOutputs ()
virtual void PropagateRequestedRegion (DataObject *output)
virtual void ResetPipeline ()
virtual void SetAbortGenerateData (bool _arg)
virtual void SetProgress (float _arg)
virtual void Update ()
virtual void UpdateLargestPossibleRegion ()
virtual void UpdateOutputData (DataObject *output)
virtual void UpdateOutputInformation ()
void UpdateProgress (float amount)
DataObjectPointerArray GetInputs ()
DataObjectPointerArray GetOutputs ()
DataObjectPointerArray GetIndexedInputs ()
DataObjectPointerArray GetIndexedOutputs ()
DataObjectPointerArraySizeType GetNumberOfIndexedOutputs () const
virtual void SetReleaseDataFlag (bool flag)
virtual bool GetReleaseDataFlag () const
void ReleaseDataFlagOn ()
void ReleaseDataFlagOff ()
virtual void SetReleaseDataBeforeUpdateFlag (bool _arg)
virtual const bool & GetReleaseDataBeforeUpdateFlag ()
virtual void ReleaseDataBeforeUpdateFlagOn ()
virtual void ReleaseDataBeforeUpdateFlagOff ()
virtual void SetNumberOfThreads (ThreadIdType _arg)
virtual const ThreadIdTypeGetNumberOfThreads ()
- Public Member Functions inherited from itk::Object
unsigned long AddObserver (const EventObject &event, Command *)
unsigned long AddObserver (const EventObject &event, Command *) const
virtual void DebugOff () const
virtual void DebugOn () const
CommandGetCommand (unsigned long tag)
bool GetDebug () const
MetaDataDictionaryGetMetaDataDictionary (void)
const MetaDataDictionaryGetMetaDataDictionary (void) const
virtual unsigned long GetMTime () const
virtual const TimeStampGetTimeStamp () const
bool HasObserver (const EventObject &event) const
void InvokeEvent (const EventObject &)
void InvokeEvent (const EventObject &) const
virtual void Modified () const
virtual void Register () const
void RemoveAllObservers ()
void RemoveObserver (unsigned long tag)
void SetDebug (bool debugFlag) const
void SetMetaDataDictionary (const MetaDataDictionary &rhs)
virtual void SetReferenceCount (int)
virtual void UnRegister () const
- Public Member Functions inherited from itk::LightObject
virtual void Delete ()
virtual int GetReferenceCount () const
 itkCloneMacro (Self)
void Print (std::ostream &os, Indent indent=0) const

Static Public Member Functions

static Pointer New ()

Static Public Attributes

static const unsigned int ImageDimension = TOutputImage::ImageDimension
- Static Public Attributes inherited from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >
- Static Public Attributes inherited from itk::InPlaceImageFilter< TInputImage, TOutputImage >
static const unsigned int InputImageDimension = TInputImage::ImageDimension
static const unsigned int OutputImageDimension = TOutputImage::ImageDimension
- Static Public Attributes inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
- Static Public Attributes inherited from itk::ImageSource< TOutputImage >

Protected Member Functions

void AllocateUpdateBuffer ()
void ApplyUpdate (const TimeStepType &dt)
TimeStepType CalculateChange ()
virtual ValueType CalculateUpdateValue (const IndexType &, const TimeStepType &dt, const ValueType &value, const ValueType &change)
void ConstructActiveLayer ()
void ConstructLayer (StatusType from, StatusType to)
void CopyInputToOutput ()
virtual ValueType GetValueOne () const
virtual ValueType GetValueZero () const
void Initialize ()
void InitializeActiveLayerValues ()
virtual void InitializeBackgroundPixels ()
virtual void PostProcessOutput ()
void ProcessOutsideList (LayerType *OutsideList, StatusType ChangeToStatus)
void ProcessStatusList (LayerType *InputList, LayerType *OutputList, StatusType ChangeToStatus, StatusType SearchForStatus)
void PropagateAllLayerValues ()
void PropagateLayerValues (StatusType from, StatusType to, StatusType promote, int InOrOut)
void UpdateActiveLayerValues (TimeStepType dt, LayerType *StatusUpList, LayerType *StatusDownList)
 SparseFieldLevelSetImageFilter ()
 ~SparseFieldLevelSetImageFilter ()
virtual void PrintSelf (std::ostream &os, Indent indent) const
- Protected Member Functions inherited from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >
 FiniteDifferenceImageFilter ()
virtual void GenerateData ()
virtual void GenerateInputRequestedRegion ()
virtual bool Halt ()
virtual void InitializeIteration ()
virtual TimeStepType ResolveTimeStep (const std::vector< TimeStepType > &timeStepList, const std::vector< bool > &valid) const
virtual void SetElapsedIterations (IdentifierType _arg)
virtual bool ThreadedHalt (void *)
virtual ~FiniteDifferenceImageFilter ()
- Protected Member Functions inherited from itk::InPlaceImageFilter< TInputImage, TOutputImage >
virtual void AllocateOutputs ()
virtual bool GetRunningInPlace () const
 InPlaceImageFilter ()
virtual void ReleaseInputs ()
 ~InPlaceImageFilter ()
- Protected Member Functions inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
virtual void CallCopyInputRegionToOutputRegion (OutputImageRegionType &destRegion, const InputImageRegionType &srcRegion)
virtual void CallCopyOutputRegionToInputRegion (InputImageRegionType &destRegion, const OutputImageRegionType &srcRegion)
 ImageToImageFilter ()
virtual void VerifyInputInformation ()
 ~ImageToImageFilter ()
void PushBackInput (const DataObject *input)
void PushFrontInput (const DataObject *input)
- Protected Member Functions inherited from itk::ImageSource< TOutputImage >
virtual void AfterThreadedGenerateData ()
virtual void BeforeThreadedGenerateData ()
 ImageSource ()
virtual unsigned int SplitRequestedRegion (unsigned int i, unsigned int num, OutputImageRegionType &splitRegion)
virtual void ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, ThreadIdType threadId)
virtual ~ImageSource ()
- Protected Member Functions inherited from itk::ProcessObject
virtual void AddInput (DataObject *input)
virtual void AddOutput (DataObject *output)
bool AddRequiredInputName (const DataObjectIdentifierType &)
virtual void CacheInputReleaseDataFlags ()
virtual void GenerateOutputInformation ()
virtual void GenerateOutputRequestedRegion (DataObject *output)
virtual const
DataObjectPointerArraySizeType
GetNumberOfRequiredInputs ()
virtual const
DataObjectPointerArraySizeType
GetNumberOfRequiredOutputs ()
bool IsIndexedName (const DataObjectIdentifierType &) const
bool IsRequiredInputName (const DataObjectIdentifierType &) const
 itkLegacyMacro (virtual void RemoveInput(DataObject *input))
 itkLegacyMacro (virtual void RemoveOutput(DataObject *output))
 itkLegacyMacro (void SetNumberOfInputs(DataObjectPointerArraySizeType num))
 itkLegacyMacro (void SetNumberOfOutputs(DataObjectPointerArraySizeType num))
DataObjectPointerArraySizeType MakeIndexFromName (const DataObjectIdentifierType &) const
DataObjectIdentifierType MakeNameFromIndex (DataObjectPointerArraySizeType) const
 ProcessObject ()
virtual void PropagateResetPipeline ()
virtual void RemoveInput (const DataObjectIdentifierType &key)
virtual void RemoveInput (DataObjectPointerArraySizeType)
virtual void RemoveOutput (const DataObjectIdentifierType &key)
virtual void RemoveOutput (DataObjectPointerArraySizeType idx)
bool RemoveRequiredInputName (const DataObjectIdentifierType &)
virtual void RestoreInputReleaseDataFlags ()
virtual void SetInput (const DataObjectIdentifierType &key, DataObject *input)
virtual void SetNthInput (DataObjectPointerArraySizeType num, DataObject *input)
virtual void SetNthOutput (DataObjectPointerArraySizeType num, DataObject *output)
void SetNumberOfIndexedInputs (DataObjectPointerArraySizeType num)
void SetNumberOfIndexedOutputs (DataObjectPointerArraySizeType num)
virtual void SetNumberOfRequiredInputs (DataObjectPointerArraySizeType)
virtual void SetNumberOfRequiredOutputs (DataObjectPointerArraySizeType _arg)
virtual void SetOutput (const DataObjectIdentifierType &key, DataObject *output)
virtual void SetPrimaryInput (DataObject *input)
virtual void SetPrimaryOutput (DataObject *output)
void SetRequiredInputNames (const NameArray &)
virtual void VerifyPreconditions ()
 ~ProcessObject ()
DataObjectGetInput (const DataObjectIdentifierType &key)
const DataObjectGetInput (const DataObjectIdentifierType &key) const
DataObjectGetInput (DataObjectPointerArraySizeType)
const DataObjectGetInput (DataObjectPointerArraySizeType idx) const
DataObjectGetPrimaryInput ()
const DataObjectGetPrimaryInput () const
DataObjectGetOutput (const DataObjectIdentifierType &key)
const DataObjectGetOutput (const DataObjectIdentifierType &key) const
DataObjectGetOutput (DataObjectPointerArraySizeType idx)
const DataObjectGetOutput (DataObjectPointerArraySizeType idx) const
DataObjectGetPrimaryOutput ()
const DataObjectGetPrimaryOutput () const
- Protected Member Functions inherited from itk::Object
 Object ()
bool PrintObservers (std::ostream &os, Indent indent) const
virtual void SetTimeStamp (const TimeStamp &time)
virtual ~Object ()
- 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 ()

Protected Attributes

double m_ConstantGradientValue
ValueType m_IsoSurfaceValue
LayerNodeStorageType::Pointer m_LayerNodeStore
LayerListType m_Layers
SparseFieldCityBlockNeighborList
< NeighborhoodIterator
< OutputImageType > > 
m_NeighborList
unsigned int m_NumberOfLayers
OutputImageType::Pointer m_ShiftedImage
StatusImageType::Pointer m_StatusImage
UpdateBufferType m_UpdateBuffer
- Protected Attributes inherited from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >
IdentifierType m_ElapsedIterations
bool m_IsInitialized
bool m_ManualReinitialization
double m_MaximumRMSError
IdentifierType m_NumberOfIterations
double m_RMSChange

Static Protected Attributes

static StatusType m_StatusActiveChangingDown
static StatusType m_StatusActiveChangingUp
static StatusType m_StatusBoundaryPixel
static StatusType m_StatusChanging
static StatusType m_StatusNull
static ValueType m_ValueOne
static ValueType m_ValueZero

Private Attributes

bool m_BoundsCheckingActive
bool m_InterpolateSurfaceLocation
 SparseFieldLevelSetImageFilter (const Self &)
void operator= (const Self &)

Additional Inherited Members


Detailed Description

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

This class implements a finite difference partial differential equation solver for evolving surfaces embedded in volumes as level-sets.

The ``sparse field'' approach to the level-set model is a logical extension of the classical narrow band technique, which seeks to minimize computational effort by restricting calculations to those pixels in a region of interest around the moving surface (the $k$-level curve). The sparse field method uses a narrow band that is exactly the width needed to calculate changes on the level curve for the next time step. Because the band of grid points under consideration is so sparse, this approach has several advantages: the algorithm does exactly the number of calculations needed to determine the next position of the $k$-level curve, and the distance transform around the level curve can be recomputed at each iteration.
The sparse field algorithm works by constructing a linked list of indices that are adjacent to the $k$-level set. These indices are called the ``active set''. The values at these active set indices define the position of the $k$-level curve. The active set indices are shifted to follow the distance transform embedding of the $k$-level curve as their values move in and out of a fixed numerical range about $k$. In this way, the active set is maintained as only those pixels adjacent to the evolving surface. Calculations are then done only at indices contained in the active set.
The city-block neighborhoods of the active set indices are maintained as separate lists called ``layers''. At each iteration, the values at the layers are reinitialized as the distance transform from the active set. The number of layers can be adjusted according to the footprint needed for the calculations on the level curve.
Briefly, the sparse field solver algorithm is as follows:
  1. For each active layer index $x_j$: Compute the change at $u_{x_j}$, the grid point in the embedding, based on local geometry and external forces and using a stable numerical scheme.
  2. For each active layer index $x_j$, add the change to the grid point value and redefine the active set indices and those of its layers based on any value changes which have moved outside of the numerical range allowed for the active set.
  3. Starting with the first layers adjacent to the active set and moving outwards, reconstruct the distance transform by setting values in the layers according to their neighbors. At the very outer layers, add or remove indices which have come into or moved out of the sparse field.
HOW TO USE THIS CLASS
Typically, this class should be subclassed with additional functionality for specific applications. It is possible, however to use this solver as a filter directly by instantiating it and supplying it with an appropriate LevelSetFunction object via the SetDifferenceFunction method. See the subclasses and their associated documentation for more information on using this class. Also see the FiniteDifferenceImageFilter documentation for a general overview of this class of solvers.
INPUTS
This filter takes an itk::Image as input. The appropriate type of input image is entirely determined by the application. As a rule, however, the input type is immediately converted to the output type before processing. This is because the input is not assumed to be a real value type and must be converted to signed, real values for the calculations. The input values will also be shifted by the $k$ isosurface value so that the algorithm only needs to consider the zero level set.
OUTPUTS
The output of the filter is the distance transform embedding of the isosurface as the zero level set. Values INSIDE the surface will be NEGATIVE and values OUTSIDE the surface will be POSITIVE. The distance transform only holds for those indices in layers around the active layer. Elsewhere, the values are a fixed positive or negative that is one greater than the layer of greatest magnitude. In other words, if there are three layers, then inside values reach a minimum of -4.0 and outside values a maximum of 4.0.
PARAMETERS
The NumberOfLayers parameter controls the number of layers inside and outside of the active set (see description above). The sparse field will contain 2*NumberOfLayers+1 lists of indices: the active set and city block neighbors inside and outside the active set. It is important to specify enough layers to cover the footprint of your calculations. Curvature calculations require a minimum of 2 layers. Higher order derivatives and other geometrical measures may require more layers. If too few layers are specified, then the calculations will pull values from the background, which may consist of arbitrary or random values.
The IsoSurfaceValue indicates which value in the input represents the interface of interest. By default, this value is zero. When the solver initializes, it will subtract the IsoSurfaceValue from all values, in the input, shifting the isosurface of interest to zero in the output.
IMPORTANT!
Read the documentation for FiniteDifferenceImageFilter before attempting to use this filter. The solver requires that you specify a FiniteDifferenceFunction to use for calculations. This is set using the method SetDifferenceFunction in the parent class.
REFERENCES
Whitaker, Ross. A Level-Set Approach to 3D Reconstruction from Range Data. International Journal of Computer Vision. V. 29 No. 3, 203-231. 1998.
Sethian, J.A. Level Set Methods. Cambridge University Press. 1996.

Definition at line 230 of file itkSparseFieldLevelSetImageFilter.h.


Member Typedef Documentation

template<class TInputImage, class TOutputImage>
typedef SmartPointer< const Self > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ConstPointer
template<class TInputImage, class TOutputImage>
typedef OutputImageType::IndexType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::IndexType
template<class TInputImage, class TOutputImage>
typedef TInputImage itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::InputImageType
template<class TInputImage, class TOutputImage>
typedef std::vector< LayerPointerType > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::LayerListType

A type for a list of LayerPointerTypes

Definition at line 271 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef ObjectStore< LayerNodeType > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::LayerNodeStorageType

Memory pre-allocator used to manage layer nodes in a multi-threaded environment.

Definition at line 283 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef SparseFieldLevelSetNode< IndexType > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::LayerNodeType

Node type used in sparse field layer lists.

Definition at line 264 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef LayerType::Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::LayerPointerType

Definition at line 268 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef SparseFieldLayer< LayerNodeType > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::LayerType

A list type used in the algorithm.

Reimplemented in itk::SparseFieldFourthOrderLevelSetImageFilter< TInputImage, TOutputImage >.

Definition at line 267 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef Superclass::NeighborhoodScalesType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::NeighborhoodScalesType
template<class TInputImage, class TOutputImage>
typedef TOutputImage itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::OutputImageType
template<class TInputImage, class TOutputImage>
typedef SmartPointer< Self > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::Pointer
template<class TInputImage, class TOutputImage>
typedef Superclass::RadiusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::RadiusType
template<class TInputImage, class TOutputImage>
typedef SparseFieldLevelSetImageFilter itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::Self
template<class TInputImage, class TOutputImage>
typedef Image< StatusType, itkGetStaticConstMacro(ImageDimension) > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::StatusImageType

The type of the image used to index status information. Necessary for the internals of the algorithm.

Definition at line 279 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef signed char itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::StatusType

Type used for storing status information

Definition at line 274 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef FiniteDifferenceImageFilter< TInputImage, TOutputImage > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::Superclass
template<class TInputImage, class TOutputImage>
typedef Superclass::TimeStepType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::TimeStepType
template<class TInputImage, class TOutputImage>
typedef std::vector< ValueType > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::UpdateBufferType

Container type used to store updates to the active layer.

Definition at line 286 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
typedef OutputImageType::ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ValueType

Constructor & Destructor Documentation

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::SparseFieldLevelSetImageFilter ( )
protected

End concept checking

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::~SparseFieldLevelSetImageFilter ( )
protected

End concept checking

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::SparseFieldLevelSetImageFilter ( const Self )
private

The RMS change calculated from each update. Can be used by a subclass to determine halting criteria. Valid only for the previous iteration, not during the current iteration. Calculated in ApplyUpdate. This flag tells the solver whether or not to interpolate for the actual surface location when calculating change at each active layer node. By default this is turned on. Subclasses which do not sample propagation (speed), advection, or curvature terms should turn this flag off.


Member Function Documentation

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::AllocateUpdateBuffer ( )
protectedvirtual

Reserves memory in the update buffer. Called before each iteration.

Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ApplyUpdate ( const TimeStepType dt)
protectedvirtual

Applies the update buffer values to the active layer and reconstructs the sparse field layers for the next iteration.

Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
TimeStepType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::CalculateChange ( )
protectedvirtual

Traverses the active layer list and calculates the change at these indices to be applied in the current iteration.

Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
virtual ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::CalculateUpdateValue ( const IndexType ,
const TimeStepType dt,
const ValueType value,
const ValueType change 
)
inlineprotectedvirtual

This function allows a subclass to override the way in which updates to output values are applied during each iteration. The default simply follows the standard finite difference scheme of scaling the change by the timestep and adding to the value of the previous iteration.

Reimplemented in itk::AntiAliasBinaryImageFilter< TInputImage, TOutputImage >.

Definition at line 342 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ConstructActiveLayer ( )
protected

Constructs the active layer and initialize the first layers inside and outside of the active layer. The active layer defines the position of the zero level set by its values, which are constrained within a range around zero.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ConstructLayer ( StatusType  from,
StatusType  to 
)
protected

Initializes a layer of the sparse field using a previously initialized layer. Builds the list of nodes in m_Layer[to] using m_Layer[from]. Marks values in the m_StatusImage.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::CopyInputToOutput ( )
protectedvirtual

Copies the input to the output image. Processing occurs on the output image, so the data type of the output image determines the precision of the calculations (i.e. double or float). This method overrides the parent class method to do some additional processing.

Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
virtual::itk::LightObject::Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::CreateAnother ( void  ) const
virtual
template<class TInputImage, class TOutputImage>
virtual bool itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetInterpolateSurfaceLocation ( ) const
virtual

Get the RMS change calculated in the PREVIOUS iteration. This value is the square root of the average square of the change value of all pixels updated during the previous iteration. Get/Set the value of the InterpolateSurfaceLocation flag. This flag tells the solver whether or not to interpolate for the surface location when calculating change at a voxel location. Turned on by default. Some applications may not use this value and can safely turn the flag off.

template<class TInputImage, class TOutputImage>
virtual ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetIsoSurfaceValue ( ) const
virtual

Set/Get the value of the isosurface to use in the input image.

template<class TInputImage, class TOutputImage>
virtual const char* itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetNameOfClass ( ) const
virtual
template<class TInputImage, class TOutputImage>
virtual unsigned int itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetNumberOfLayers ( ) const
virtual

Set/Get the number of layers to use in the sparse field. Argument is the number of layers on ONE side of the active layer, so the total layers in the sparse field is 2 * NumberOfLayers +1

template<class TInputImage, class TOutputImage>
virtual ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetValueOne ( ) const
protectedvirtual
template<class TInputImage, class TOutputImage>
virtual ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::GetValueZero ( ) const
protectedvirtual
template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::Initialize ( )
protectedvirtual

Constructs the sparse field layers and initializes their values.

Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::InitializeActiveLayerValues ( )
protected

Initializes the values of the active layer set.

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::InitializeBackgroundPixels ( )
protectedvirtual

This method pre-processes pixels inside and outside the sparse field layers. The default is to set them to positive and negative values, respectively. This is not necessary as part of the calculations, but produces a more intuitive output for the user.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::InterpolateSurfaceLocationOff ( )
inline

See Get/SetInterpolateSurfaceLocation

Definition at line 317 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::InterpolateSurfaceLocationOn ( )
inline

See Get/SetInterpolateSurfaceLocation

Definition at line 315 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
static Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::New ( )
static
template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::operator= ( const Self )
private

The RMS change calculated from each update. Can be used by a subclass to determine halting criteria. Valid only for the previous iteration, not during the current iteration. Calculated in ApplyUpdate. This flag tells the solver whether or not to interpolate for the actual surface location when calculating change at each active layer node. By default this is turned on. Subclasses which do not sample propagation (speed), advection, or curvature terms should turn this flag off.

Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

Reimplemented in itk::SegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::SparseFieldFourthOrderLevelSetImageFilter< TInputImage, TOutputImage >, itk::ThresholdSegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::CannySegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::ShapePriorSegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::AntiAliasBinaryImageFilter< TInputImage, TOutputImage >, itk::GeodesicActiveContourShapePriorLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::VectorThresholdSegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::GeodesicActiveContourLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::CurvesLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::ShapeDetectionLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::LaplacianSegmentationLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >, itk::AnisotropicFourthOrderLevelSetImageFilter< TInputImage, TOutputImage >, itk::IsotropicFourthOrderLevelSetImageFilter< TInputImage, TOutputImage >, and itk::UnsharpMaskLevelSetImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::PostProcessOutput ( )
protectedvirtual

This method packages the output(s) into a consistent format. The default implementation produces a volume with the final solution values in the sparse field, and inside and outside values elsewhere as appropriate.

Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const
protectedvirtual
template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ProcessOutsideList ( LayerType OutsideList,
StatusType  ChangeToStatus 
)
protected
template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ProcessStatusList ( LayerType InputList,
LayerType OutputList,
StatusType  ChangeToStatus,
StatusType  SearchForStatus 
)
protected
template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::PropagateAllLayerValues ( )
protected

Adjusts the values associated with all the index layers of the sparse field by propagating out one layer at a time from the active set. This method also takes care of deleting nodes from the layers which have been marked in the status image as having been moved to other layers.

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::PropagateLayerValues ( StatusType  from,
StatusType  to,
StatusType  promote,
int  InOrOut 
)
protected

Adjusts the values in a single layer "to" using values in a neighboring layer "from". The list of indices in "to" are traversed and assigned new values appropriately. Any indices in "to" without neighbors in "from" are moved into the "promote" layer (or deleted if "promote" is greater than the number of layers). "InOrOut" == 1 indicates this propagation is inwards (more negative). "InOrOut" == 2 indicates this propagation is outwards (more positive).

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::SetInterpolateSurfaceLocation ( bool  _arg)
virtual

Get the RMS change calculated in the PREVIOUS iteration. This value is the square root of the average square of the change value of all pixels updated during the previous iteration. Get/Set the value of the InterpolateSurfaceLocation flag. This flag tells the solver whether or not to interpolate for the surface location when calculating change at a voxel location. Turned on by default. Some applications may not use this value and can safely turn the flag off.

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::SetIsoSurfaceValue ( ValueType  _arg)
virtual

Set/Get the value of the isosurface to use in the input image.

template<class TInputImage, class TOutputImage>
virtual void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::SetNumberOfLayers ( unsigned int  _arg)
virtual

Set/Get the number of layers to use in the sparse field. Argument is the number of layers on ONE side of the active layer, so the total layers in the sparse field is 2 * NumberOfLayers +1

Reimplemented in itk::SparseFieldFourthOrderLevelSetImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::typedef ( Concept::EqualityComparable< typename TOutputImage::PixelType >  )

Begin concept checking This class requires OutputEqualityComparableCheck in the form of ( Concept::EqualityComparable< typename TOutputImage::PixelType > )

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::typedef ( Concept::Convertible< double, typename TOutputImage::PixelType >  )

This class requires DoubleConvertibleToOutputCheck in the form of ( Concept::Convertible< double, typename TOutputImage::PixelType > )

Reimplemented in itk::AntiAliasBinaryImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage>
itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::typedef ( Concept::OStreamWritable< typename TOutputImage::PixelType >  )

This class requires OutputOStreamWritableCheck in the form of ( Concept::OStreamWritable< typename TOutputImage::PixelType > )

template<class TInputImage, class TOutputImage>
void itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::UpdateActiveLayerValues ( TimeStepType  dt,
LayerType StatusUpList,
LayerType StatusDownList 
)
protected

Updates the active layer values using m_UpdateBuffer. Also creates an "up" and "down" list for promotion/demotion of indices leaving the active set.


Member Data Documentation

template<class TInputImage, class TOutputImage>
const unsigned int itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::ImageDimension = TOutputImage::ImageDimension
static
template<class TInputImage, class TOutputImage>
bool itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_BoundsCheckingActive
private

This flag is true when methods need to check boundary conditions and false when methods do not need to check for boundary conditions.

Definition at line 507 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
double itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_ConstantGradientValue
protected

The constant gradient to maintain between isosurfaces in the sparse-field of the level-set image. This value defaults to 1.0

Definition at line 432 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
bool itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_InterpolateSurfaceLocation
protected

The RMS change calculated from each update. Can be used by a subclass to determine halting criteria. Valid only for the previous iteration, not during the current iteration. Calculated in ApplyUpdate. This flag tells the solver whether or not to interpolate for the actual surface location when calculating change at each active layer node. By default this is turned on. Subclasses which do not sample propagation (speed), advection, or curvature terms should turn this flag off.

Definition at line 499 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_IsoSurfaceValue
protected

The value in the input which represents the isosurface of interest.

Definition at line 484 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
LayerNodeStorageType::Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_LayerNodeStore
protected

Storage for layer node objects.

Definition at line 481 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
LayerListType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_Layers
protected

An array which contains all of the layers needed in the sparse field. Layers are organized as follows: m_Layer[0] = active layer, m_Layer[i:odd] = inside layer (i+1)/2, m_Layer[i:even] = outside layer i/2

Definition at line 469 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
SparseFieldCityBlockNeighborList< NeighborhoodIterator< OutputImageType > > itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_NeighborList
protected

Connectivity information for examining neighbor pixels.

Definition at line 424 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
unsigned int itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_NumberOfLayers
protected

The number of layers to use in the sparse field. Sparse field will consist of m_NumberOfLayers layers on both sides of a single active layer. This active layer is the interface of interest, i.e. the zero level set.

Definition at line 475 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
OutputImageType::Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_ShiftedImage
protected

This image is a copy of the input with m_IsoSurfaceValue subtracted from each pixel. This way we only need to consider the zero level set in our calculations. Makes the implementation easier and more efficient.

Definition at line 463 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusActiveChangingDown
staticprotected

Special status value which indicates a pending change to a more negative sparse field.

Definition at line 450 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusActiveChangingUp
staticprotected

Special status value which indicates a pending change to a more positive sparse field.

Definition at line 446 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusBoundaryPixel
staticprotected

Special status value which indicates a pixel is on the boundary of the image

Definition at line 454 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusChanging
staticprotected

Special status value which indicates pending change to another sparse field layer.

Definition at line 442 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusImageType::Pointer itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusImage
protected

An image of status values used internally by the algorithm.

Definition at line 478 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
StatusType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_StatusNull
staticprotected

Special status value used as a default for indices which have no meaningful status.

Definition at line 458 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
UpdateBufferType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_UpdateBuffer
protected

The update buffer used to store change values computed in CalculateChange.

Definition at line 488 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_ValueOne
staticprotected

Multiplicative identity of the ValueType.

Definition at line 435 of file itkSparseFieldLevelSetImageFilter.h.

template<class TInputImage, class TOutputImage>
ValueType itk::SparseFieldLevelSetImageFilter< TInputImage, TOutputImage >::m_ValueZero
staticprotected

Additive identity of the ValueType.

Definition at line 438 of file itkSparseFieldLevelSetImageFilter.h.


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