Solve an Eikonal equation using Fast Marching. More...

#include <sitkFastMarchingImageFilter.h>

Inheritance diagram for itk::simple::FastMarchingImageFilter:

Collaboration diagram for itk::simple::FastMarchingImageFilter:

Detailed Description

Solve an Eikonal equation using Fast Marching.

Fast marching solves an Eikonal equation where the speed is always non-negative and depends on the position only. Starting from an initial position on the front, fast marching systematically moves the front forward one grid point at a time.

Updates are performed using an entropy satisfy scheme where only "upwind" neighborhoods are used. This implementation of Fast Marching uses a std::priority_queue to locate the next proper grid position to update.

Fast Marching sweeps through N grid points in (N log N) steps to obtain the arrival time value as the front propagates through the grid.

Implementation of this class is based on Chapter 8 of "Level Set Methods and Fast Marching Methods", J.A. Sethian, Cambridge Press, Second edition, 1999.

This class is templated over the level set image type and the speed image type. The initial front is specified by two containers: one containing the known points and one containing the trial points. Alive points are those that are already part of the object, and trial points are considered for inclusion. In order for the filter to evolve, at least some trial points must be specified. These can for instance be specified as the layer of pixels around the alive points.

The speed function can be specified as a speed image or a speed constant. The speed image is set using the method SetInput() . If the speed image is nullptr, a constant speed function is used and is specified using method the SetSpeedConstant() .

If the speed function is constant and of value one, fast marching results in an approximate distance function from the initial alive points. FastMarchingImageFilter is used in the ReinitializeLevelSetImageFilter object to create a signed distance function from the zero level set.

The algorithm can be terminated early by setting an appropriate stopping value. The algorithm terminates when the current arrival time being processed is greater than the stopping value.

There are two ways to specify the output image information ( LargestPossibleRegion, Spacing, Origin): (a) it is copied directly from the input speed image or (b) it is specified by the user. Default values are used if the user does not specify all the information.

The output information is computed as follows. If the speed image is nullptr or if the OverrideOutputInformation is set to true, the output information is set from user specified parameters. These parameters can be specified using methods SetOutputRegion() , SetOutputSpacing() , SetOutputDirection() , and SetOutputOrigin() . Else if the speed image is not nullptr, the output information is copied from the input speed image.

For an alternative implementation, see itk::FastMarchingImageFilter .

Possible Improvements: In the current implementation, std::priority_queue only allows taking nodes out from the front and putting nodes in from the back. To update a value already on the heap, a new node is added to the heap. The defunct old node is left on the heap. When it is removed from the top, it will be recognized as invalid and not used. Future implementations can implement the heap in a different way allowing the values to be updated. This will generally require some sift-up and sift-down functions and an image of back-pointers going from the image to heap in order to locate the node which is to be updated.

See also: FastMarchingImageFilterBase; LevelSetTypeDefault; itk::simple::FastMarching for the procedural interface; itk::FastMarchingImageFilter for the Doxygen on the original ITK class.

Examples: FastMarchingSegmentation/FastMarchingSegmentation.cxx.

Definition at line 68 of file sitkFastMarchingImageFilter.h.

Public Types
using	PixelIDTypeList = BasicPixelIDTypeList

using	Self = FastMarchingImageFilter

Public Types inherited from itk::simple::ImageFilter
using	Self = ImageFilter

Public Types inherited from itk::simple::ProcessObject
using	Self = ProcessObject

Public Member Functions
Self &	AddTrialPoint (std::vector< unsigned int > point)
	Add TrialPoints point. More...

Self &	ClearTrialPoints ()
	Remove all TrialPoints points. More...

Image	Execute (const Image &image1)

	FastMarchingImageFilter ()

std::vector< double >	GetInitialTrialValues () const

std::string	GetName () const

double	GetNormalizationFactor () const

double	GetStoppingValue () const

std::vector< std::vector< unsigned int > >	GetTrialPoints () const

Self &	SetInitialTrialValues (std::vector< double > InitialTrialValues)
	Set the initial seed values for corresponding trial points. More...

Self &	SetNormalizationFactor (double NormalizationFactor)

Self &	SetStoppingValue (double StoppingValue)

Self &	SetTrialPoints (std::vector< std::vector< unsigned int > > TrialPoints)

std::string	ToString () const

virtual	~FastMarchingImageFilter ()

Public Member Functions inherited from itk::simple::ImageFilter
	ImageFilter ()

virtual	~ImageFilter ()=0

Public Member Functions inherited from itk::simple::ProcessObject
virtual void	Abort ()

virtual int	AddCommand (itk::simple::EventEnum event, const std::function< void()> &func)
	Directly add a callback to observe an event. More...

virtual int	AddCommand (itk::simple::EventEnum event, itk::simple::Command &cmd)
	Add a Command Object to observer the event. More...

virtual float	GetProgress () const
	An Active Measurement of the progress of execution. More...

virtual bool	HasCommand (itk::simple::EventEnum event) const
	Query of this object has any registered commands for event. More...

	ProcessObject ()

virtual void	RemoveAllCommands ()
	Remove all registered commands. More...

virtual	~ProcessObject ()

virtual void	DebugOn ()

virtual void	DebugOff ()

virtual bool	GetDebug () const

virtual void	SetDebug (bool debugFlag)

virtual void	SetNumberOfThreads (unsigned int n)

virtual unsigned int	GetNumberOfThreads () const

virtual void	SetNumberOfWorkUnits (unsigned int n)

virtual unsigned int	GetNumberOfWorkUnits () const

Private Types
using	MemberFunctionType = Image(Self::*)(const Image &image1)

Private Member Functions
template<class TImageType >
Image	ExecuteInternal (const Image &image1)

Private Attributes
std::vector< double >	m_InitialTrialValues {std::vector<double>()}

std::unique_ptr< detail::MemberFunctionFactory< MemberFunctionType > >	m_MemberFactory

double	m_NormalizationFactor {1.0}

double	m_StoppingValue {std::numeric_limits<double>::max()/2.0}

std::vector< std::vector< unsigned int > >	m_TrialPoints {std::vector< std::vector<unsigned int > >()}

Friends
struct	detail::MemberFunctionAddressor< MemberFunctionType >

Additional Inherited Members
Static Public Member Functions inherited from itk::simple::ProcessObject
static bool	GetGlobalDefaultDebug ()

static void	GlobalDefaultDebugOff ()

static void	GlobalDefaultDebugOn ()

static void	SetGlobalDefaultDebug (bool debugFlag)

static void	GlobalWarningDisplayOn ()

static void	GlobalWarningDisplayOff ()

static void	SetGlobalWarningDisplay (bool flag)

static bool	GetGlobalWarningDisplay ()

static double	GetGlobalDefaultCoordinateTolerance ()
	Access the global tolerance to determine congruent spaces. More...

static void	SetGlobalDefaultCoordinateTolerance (double)
	Access the global tolerance to determine congruent spaces. More...

static double	GetGlobalDefaultDirectionTolerance ()
	Access the global tolerance to determine congruent spaces. More...

static void	SetGlobalDefaultDirectionTolerance (double)
	Access the global tolerance to determine congruent spaces. More...

static bool	SetGlobalDefaultThreader (const std::string &threader)
	Set/Get the default threader used for process objects. More...

static std::string	GetGlobalDefaultThreader ()
	Set/Get the default threader used for process objects. More...

static void	SetGlobalDefaultNumberOfThreads (unsigned int n)

static unsigned int	GetGlobalDefaultNumberOfThreads ()
	Set/Get the default threader used for process objects. More...

Protected Member Functions inherited from itk::simple::ImageFilter
void	CheckImageMatchingDimension (const Image &image1, const Image &image2, const std::string &image2Name)

void	CheckImageMatchingPixelType (const Image &image1, const Image &image2, const std::string &image2Name)

void	CheckImageMatchingSize (const Image &image1, const Image &image2, const std::string &image2Name)

Protected Member Functions inherited from itk::simple::ProcessObject
virtual unsigned long	AddITKObserver (const itk::EventObject &, itk::Command *)

virtual itk::ProcessObject *	GetActiveProcess ()

virtual void	OnActiveProcessDelete ()

virtual void	onCommandDelete (const itk::simple::Command *cmd) noexcept

virtual void	PreUpdate (itk::ProcessObject *p)

virtual void	RemoveITKObserver (EventCommand &e)

Protected Member Functions inherited from itk::simple::NonCopyable
	NonCopyable ()=default

	NonCopyable (const NonCopyable &)=delete

NonCopyable &	operator= (const NonCopyable &)=delete

Static Protected Member Functions inherited from itk::simple::ImageFilter
template<class TImageType >
static void	FixNonZeroIndex (TImageType *img)

Static Protected Member Functions inherited from itk::simple::ProcessObject
template<class TImageType >
static TImageType::ConstPointer	CastImageToITK (const Image &img)

template<class TPixelType , unsigned int VImageDimension, unsigned int VLength, template< typename, unsigned int > class TVector>
static Image	CastITKToImage (itk::Image< TVector< TPixelType, VLength >, VImageDimension > *img)

template<unsigned int VImageDimension, unsigned int VLength, template< unsigned int > class TVector>
static Image	CastITKToImage (itk::Image< TVector< VLength >, VImageDimension > *img)

template<class TImageType >
static Image	CastITKToImage (TImageType *img)

static const itk::EventObject &	GetITKEventObject (EventEnum e)

template<typename T >
static std::ostream &	ToStringHelper (std::ostream &os, const T &v)

static std::ostream &	ToStringHelper (std::ostream &os, const char &v)

static std::ostream &	ToStringHelper (std::ostream &os, const signed char &v)

static std::ostream &	ToStringHelper (std::ostream &os, const unsigned char &v)

Member Typedef Documentation

◆ MemberFunctionType

using itk::simple::FastMarchingImageFilter::MemberFunctionType = Image (Self::*)( const Image& image1 )

private

Setup for member function dispatching

Definition at line 142 of file sitkFastMarchingImageFilter.h.

◆ PixelIDTypeList

using itk::simple::FastMarchingImageFilter::PixelIDTypeList = BasicPixelIDTypeList

Define the pixels types supported by this filter

Definition at line 80 of file sitkFastMarchingImageFilter.h.

◆ Self

using itk::simple::FastMarchingImageFilter::Self = FastMarchingImageFilter

Definition at line 70 of file sitkFastMarchingImageFilter.h.

Constructor & Destructor Documentation

◆ ~FastMarchingImageFilter()

virtual itk::simple::FastMarchingImageFilter::~FastMarchingImageFilter ( )

virtual

Destructor

◆ FastMarchingImageFilter()

itk::simple::FastMarchingImageFilter::FastMarchingImageFilter ( )

Default Constructor that takes no arguments and initializes default parameters

Member Function Documentation

◆ AddTrialPoint()

Self& itk::simple::FastMarchingImageFilter::AddTrialPoint ( std::vector< unsigned int > point )

inline

Add TrialPoints point.

Examples: FastMarchingSegmentation/FastMarchingSegmentation.cxx.

Definition at line 93 of file sitkFastMarchingImageFilter.h.

References itk::point().

◆ ClearTrialPoints()

Self& itk::simple::FastMarchingImageFilter::ClearTrialPoints ( )

inline

Remove all TrialPoints points.

Definition at line 95 of file sitkFastMarchingImageFilter.h.

◆ Execute()

Image itk::simple::FastMarchingImageFilter::Execute ( const Image & image1 )

Execute the filter on the input image

Examples: FastMarchingSegmentation/FastMarchingSegmentation.cxx.

◆ ExecuteInternal()

template<class TImageType >

Image itk::simple::FastMarchingImageFilter::ExecuteInternal ( const Image & image1 )

private

◆ GetInitialTrialValues()

std::vector<double> itk::simple::FastMarchingImageFilter::GetInitialTrialValues ( ) const

inline

Definition at line 125 of file sitkFastMarchingImageFilter.h.

◆ GetName()

std::string itk::simple::FastMarchingImageFilter::GetName ( ) const

inlinevirtual

Name of this class

Implements itk::simple::ProcessObject.

Definition at line 128 of file sitkFastMarchingImageFilter.h.

◆ GetNormalizationFactor()

double itk::simple::FastMarchingImageFilter::GetNormalizationFactor ( ) const

inline

Set/Get the Normalization Factor for the Speed Image . The values in the Speed Image is divided by this factor. This allows the use of images with integer pixel types to represent the speed.

Definition at line 106 of file sitkFastMarchingImageFilter.h.

◆ GetStoppingValue()

double itk::simple::FastMarchingImageFilter::GetStoppingValue ( ) const

inline

Get the Fast Marching algorithm Stopping Value.

Definition at line 116 of file sitkFastMarchingImageFilter.h.

◆ GetTrialPoints()

std::vector< std::vector< unsigned int > > itk::simple::FastMarchingImageFilter::GetTrialPoints ( ) const

inline

Get the container of Trial Points representing the initial front.

Definition at line 91 of file sitkFastMarchingImageFilter.h.

◆ SetInitialTrialValues()

Self& itk::simple::FastMarchingImageFilter::SetInitialTrialValues ( std::vector< double > InitialTrialValues )

inline

Set the initial seed values for corresponding trial points.

Definition at line 121 of file sitkFastMarchingImageFilter.h.

◆ SetNormalizationFactor()

Self& itk::simple::FastMarchingImageFilter::SetNormalizationFactor ( double NormalizationFactor )

inline

Set/Get the Normalization Factor for the Speed Image . The values in the Speed Image is divided by this factor. This allows the use of images with integer pixel types to represent the speed.

Definition at line 101 of file sitkFastMarchingImageFilter.h.

◆ SetStoppingValue()

Self& itk::simple::FastMarchingImageFilter::SetStoppingValue ( double StoppingValue )

inline

Set the Fast Marching algorithm Stopping Value. The Fast Marching algorithm is terminated when the value of the smallest trial point is greater than the stopping value.