Deformably register two images using a PDE algorithm. More...

#include <itkPDEDeformableRegistrationFilter.h>

Inheritance diagram for itk::PDEDeformableRegistrationFilter< TFixedImage, TMovingImage, TDisplacementField >:

Collaboration diagram for itk::PDEDeformableRegistrationFilter< TFixedImage, TMovingImage, TDisplacementField >:

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef DisplacementFieldType::Pointer	DisplacementFieldPointer
typedef TDisplacementField	DisplacementFieldType
typedef Superclass::FiniteDifferenceFunctionType	FiniteDifferenceFunctionType
typedef FixedImageType::ConstPointer	FixedImageConstPointer
typedef FixedImageType::Pointer	FixedImagePointer
typedef TFixedImage	FixedImageType
typedef MovingImageType::ConstPointer	MovingImageConstPointer
typedef MovingImageType::Pointer	MovingImagePointer
typedef TMovingImage	MovingImageType
typedef Superclass::OutputImageType	OutputImageType
typedef PDEDeformableRegistrationFunction < FixedImageType, MovingImageType, DisplacementFieldType >	PDEDeformableRegistrationFunctionType
typedef SmartPointer< Self >	Pointer
typedef PDEDeformableRegistrationFilter	Self
typedef FixedArray< double, ImageDimension >	StandardDeviationsType
typedef DenseFiniteDifferenceImageFilter < TDisplacementField, TDisplacementField >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
DisplacementFieldType *	GetDisplacementField ()
const FixedImageType *	GetFixedImage (void) const
const MovingImageType *	GetMovingImage (void) const
virtual const char *	GetNameOfClass () const
virtual std::vector < SmartPointer< DataObject > >::size_type	GetNumberOfValidRequiredInputs () const
virtual const StandardDeviationsType &	GetStandardDeviations ()
virtual const StandardDeviationsType &	GetUpdateFieldStandardDeviations ()
void	SetFixedImage (const FixedImageType *ptr)
void	SetInitialDisplacementField (const DisplacementFieldType *ptr)
void	SetMovingImage (const MovingImageType *ptr)
virtual void	StopRegistration ()

virtual void	SetSmoothDisplacementField (bool _arg)
virtual bool	GetSmoothDisplacementField () const
virtual void	SmoothDisplacementFieldOn ()
virtual void	SmoothDisplacementFieldOff ()

virtual void	SetStandardDeviations (StandardDeviationsType _arg)
virtual void	SetStandardDeviations (double value)

virtual void	SetSmoothUpdateField (bool _arg)
virtual bool	GetSmoothUpdateField () const
virtual void	SmoothUpdateFieldOn ()
virtual void	SmoothUpdateFieldOff ()

virtual void	SetUpdateFieldStandardDeviations (StandardDeviationsType _arg)
virtual void	SetUpdateFieldStandardDeviations (double value)

virtual void	SetMaximumError (double _arg)
virtual double	GetMaximumError () const
Static Public Member Functions
static Pointer	New ()
Static Public Attributes
static const unsigned int	ImageDimension = Superclass::ImageDimension
Protected Member Functions
virtual void	CopyInputToOutput ()
virtual void	GenerateInputRequestedRegion ()
virtual void	GenerateOutputInformation ()
virtual bool	Halt ()
virtual void	Initialize ()
virtual void	InitializeIteration ()
virtual void	PostProcessOutput ()
virtual void	SmoothDisplacementField ()
virtual void	SmoothUpdateField ()
Private Member Functions
void	operator= (const Self &)
	PDEDeformableRegistrationFilter (const Self &)
Private Attributes
double	m_MaximumError
unsigned int	m_MaximumKernelWidth
bool	m_SmoothDisplacementField
bool	m_SmoothUpdateField
StandardDeviationsType	m_StandardDeviations
bool	m_StopRegistrationFlag
DisplacementFieldPointer	m_TempField
StandardDeviationsType	m_UpdateFieldStandardDeviations
virtual void	SetMaximumKernelWidth (unsigned int _arg)
virtual unsigned int	GetMaximumKernelWidth () const
	PDEDeformableRegistrationFilter ()
	~PDEDeformableRegistrationFilter ()
void	PrintSelf (std::ostream &os, Indent indent) const

Detailed Description

template<class TFixedImage, class TMovingImage, class TDisplacementField>
class itk::PDEDeformableRegistrationFilter< TFixedImage, TMovingImage, TDisplacementField >

Deformably register two images using a PDE algorithm.

PDEDeformableRegistrationFilter is a base case for filter implementing a PDE deformable algorithm that register two images by computing the displacement field which will map a moving image onto a fixed image.

A displacement field is represented as a image whose pixel type is some vector type with at least N elements, where N is the dimension of the fixed image. The vector type must support element access via operator []. It is assumed that the vector elements behave like floating point scalars.

This class is templated over the fixed image type, moving image type and the displacement Field type.

The input fixed and moving images are set via methods SetFixedImage and SetMovingImage respectively. An initial displacement field maybe set via SetInitialDisplacementField or SetInput. If no initial field is set, a zero field is used as the initial condition.

The output displacement field can be obtained via methods GetOutput or GetDisplacementField.

The PDE algorithm is run for a user defined number of iterations. Typically the PDE algorithm requires period Gaussin smoothing of the displacement field to enforce an elastic-like condition. The amount of smoothing is governed by a set of user defined standard deviations (one for each dimension).

In terms of memory, this filter keeps two internal buffers: one for storing the intermediate updates to the field and one for double-buffering when smoothing the displacement field. Both buffers are the same type and size as the output displacement field.

This class make use of the finite difference solver hierarchy. Update for each iteration is computed using a PDEDeformableRegistrationFunction.

Warning:: This filter assumes that the fixed image type, moving image type and displacement field type all have the same number of dimensions.

See also:: PDEDeformableRegistrationFunction.

Definition at line 73 of file itkPDEDeformableRegistrationFilter.h.