#include <itkRegistrationParameterScalesFromJacobian.h>

Detailed Description

template<typename TMetric>
class itk::RegistrationParameterScalesFromJacobian< TMetric >

Implements a registration helper class for estimating scales of transform parameters from Jacobian norms.

Its input includes the fixed/moving images and transform objects, which can be obtained from the metric object.

The scale of a parameter is estimated from the averaged squared norm of the Jacobian w.r.t the parameter. The averaging is done over a sampling of the image domain. The sampling by default is a uniform random distribution.

Definition at line 42 of file itkRegistrationParameterScalesFromJacobian.h.

Inheritance diagram for itk::RegistrationParameterScalesFromJacobian< TMetric >:

Collaboration diagram for itk::RegistrationParameterScalesFromJacobian< TMetric >:

Public Types
using	ConstPointer = SmartPointer< const Self >

using	Pointer = SmartPointer< Self >

using	Self = RegistrationParameterScalesFromJacobian

using	Superclass = RegistrationParameterScalesEstimator< TMetric >

Public Types inherited from itk::RegistrationParameterScalesEstimator< TMetric >
using	ConstPointer = SmartPointer< const Self >

using	FixedTransformConstPointer = typename FixedTransformType::ConstPointer

using	FixedTransformType = typename MetricType::FixedTransformType

using	JacobianType = typename TMetric::JacobianType

using	MetricConstPointer = typename MetricType::ConstPointer

using	MetricPointer = typename MetricType::Pointer

using	MetricType = TMetric

using	MovingTransformConstPointer = typename MovingTransformType::ConstPointer

using	MovingTransformType = typename MetricType::MovingTransformType

using	Pointer = SmartPointer< Self >

using	SamplePointContainerType = std::vector< VirtualPointType >

using	SamplingStrategyType = SamplingStrategyEnum

using	Self = RegistrationParameterScalesEstimator

using	Superclass = OptimizerParameterScalesEstimatorTemplate< typename TMetric::ParametersValueType >

using	VirtualImageConstPointer = typename TMetric::VirtualImageConstPointer

using	VirtualImagePointer = typename TMetric::VirtualImagePointer

using	VirtualImageType = typename TMetric::VirtualImageType

using	VirtualIndexType = typename TMetric::VirtualIndexType

using	VirtualPointSetPointer = typename TMetric::VirtualPointSetPointer

using	VirtualPointSetType = typename TMetric::VirtualPointSetType

using	VirtualPointType = typename TMetric::VirtualPointType

using	VirtualRegionType = typename TMetric::VirtualRegionType

using	VirtualSizeType = typename TMetric::VirtualSizeType

using	VirtualSpacingType = typename TMetric::VirtualSpacingType

Public Types inherited from itk::OptimizerParameterScalesEstimatorTemplate< TMetric::ParametersValueType >
using	ConstPointer = SmartPointer< const Self >

using	FloatType = TMetric::ParametersValueType

using	ParametersType = OptimizerParameters< TMetric::ParametersValueType >

using	Pointer = SmartPointer< Self >

using	ScalesType = OptimizerParameters< TMetric::ParametersValueType >

using	Self = OptimizerParameterScalesEstimatorTemplate

using	Superclass = Object

Public Types inherited from itk::Object
using	ConstPointer = SmartPointer< const Self >

using	Pointer = SmartPointer< Self >

using	Self = Object

using	Superclass = LightObject

Public Types inherited from itk::LightObject
using	ConstPointer = SmartPointer< const Self >

using	Pointer = SmartPointer< Self >

using	Self = LightObject

Public Member Functions
void	EstimateLocalStepScales (const ParametersType &step, ScalesType &localStepScales) override

void	EstimateScales (ScalesType &parameterScales) override

FloatType	EstimateStepScale (const ParametersType &step) override

const char *	GetNameOfClass () const override

Public Member Functions inherited from itk::RegistrationParameterScalesEstimator< TMetric >
void	EstimateLocalStepScales (const ParametersType &step, ScalesType &localStepScales) override=0

FloatType	EstimateMaximumStepSize () override

void	EstimateScales (ScalesType &scales) override=0

FloatType	EstimateStepScale (const ParametersType &step) override=0

const char *	GetNameOfClass () const override

virtual void	SetScalesSamplingStrategy ()

virtual void	SetStepScaleSamplingStrategy ()

virtual void	SetMetric (MetricType *_arg)

virtual const MetricType *	GetMetric () const

virtual void	SetTransformForward (bool _arg)

virtual bool	GetTransformForward () const

virtual void	TransformForwardOn ()

virtual void	SetVirtualDomainPointSet (const VirtualPointSetType *_arg)

virtual const VirtualPointSetType *	GetVirtualDomainPointSet () const

virtual void	SetCentralRegionRadius (IndexValueType _arg)

virtual IndexValueType	GetCentralRegionRadius () const

Public Member Functions inherited from itk::OptimizerParameterScalesEstimatorTemplate< TMetric::ParametersValueType >
virtual void	EstimateLocalStepScales (const ParametersType &step, ScalesType &localStepScales)=0

virtual FloatType	EstimateMaximumStepSize ()=0

virtual void	EstimateScales (ScalesType &scales)=0

virtual FloatType	EstimateStepScale (const ParametersType &step)=0

const char *	GetNameOfClass () const override

Public Member Functions inherited from itk::Object
unsigned long	AddObserver (const EventObject &event, Command *cmd) const

unsigned long	AddObserver (const EventObject &event, std::function< void(const EventObject &)> function) const

LightObject::Pointer	CreateAnother () const override

virtual void	DebugOff () const

virtual void	DebugOn () const

Command *	GetCommand (unsigned long tag)

bool	GetDebug () const

MetaDataDictionary &	GetMetaDataDictionary ()

const MetaDataDictionary &	GetMetaDataDictionary () const

virtual ModifiedTimeType	GetMTime () const

const char *	GetNameOfClass () const override

virtual const TimeStamp &	GetTimeStamp () const

bool	HasObserver (const EventObject &event) const

void	InvokeEvent (const EventObject &)

void	InvokeEvent (const EventObject &) const

virtual void	Modified () const

void	Register () const override

void	RemoveAllObservers ()

void	RemoveObserver (unsigned long tag) const

void	SetDebug (bool debugFlag) const

void	SetReferenceCount (int) override

void	UnRegister () const noexcept override

void	SetMetaDataDictionary (const MetaDataDictionary &rhs)

void	SetMetaDataDictionary (MetaDataDictionary &&rrhs)

virtual void	SetObjectName (std::string _arg)

virtual const std::string &	GetObjectName () const

Public Member Functions inherited from itk::LightObject
Pointer	Clone () const

virtual Pointer	CreateAnother () const

virtual void	Delete ()

virtual const char *	GetNameOfClass () const

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::Object
static bool	GetGlobalWarningDisplay ()

static void	GlobalWarningDisplayOff ()

static void	GlobalWarningDisplayOn ()

static Pointer	New ()

static void	SetGlobalWarningDisplay (bool val)

Static Public Member Functions inherited from itk::LightObject
static void	BreakOnError ()

static Pointer	New ()

Protected Member Functions
void	ComputeSampleStepScales (const ParametersType &step, ScalesType &sampleScales)

void	PrintSelf (std::ostream &os, Indent indent) const override

	RegistrationParameterScalesFromJacobian ()=default

	~RegistrationParameterScalesFromJacobian () override=default

Protected Member Functions inherited from itk::RegistrationParameterScalesEstimator< TMetric >
bool	CheckAndSetInputs ()

bool	CheckGeneralAffineTransform ()

template<typename TTransform >
bool	CheckGeneralAffineTransformTemplated ()

void	ComputeSquaredJacobianNorms (const VirtualPointType &point, ParametersType &squareNorms)

SizeValueType	GetDimension ()

SizeValueType	GetNumberOfLocalParameters ()

virtual SamplingStrategyType	GetSamplingStrategy ()

const TransformBaseTemplate< typename TMetric::MeasureType > *	GetTransform ()

VirtualIndexType	GetVirtualDomainCentralIndex ()

VirtualRegionType	GetVirtualDomainCentralRegion ()

bool	IsBSplineTransform ()

bool	IsDisplacementFieldTransform ()

void	PrintSelf (std::ostream &os, Indent indent) const override

	RegistrationParameterScalesEstimator ()

virtual void	SampleVirtualDomain ()

void	SampleVirtualDomainFully ()

void	SampleVirtualDomainRandomly ()

void	SampleVirtualDomainWithCentralRegion ()

void	SampleVirtualDomainWithCorners ()

void	SampleVirtualDomainWithPointSet ()

void	SampleVirtualDomainWithRegion (VirtualRegionType region)

virtual void	SetNumberOfRandomSamples (SizeValueType _arg)

virtual void	SetSamplingStrategy (SamplingStrategyType _arg)

bool	TransformHasLocalSupportForScalesEstimation ()

template<typename TTargetPointType >
void	TransformPoint (const VirtualPointType &point, TTargetPointType &mappedPoint)

template<typename TContinuousIndexType >
void	TransformPointToContinuousIndex (const VirtualPointType &point, TContinuousIndexType &mappedIndex)

void	UpdateTransformParameters (const ParametersType &deltaParameters)

	~RegistrationParameterScalesEstimator () override=default

Protected Member Functions inherited from itk::OptimizerParameterScalesEstimatorTemplate< TMetric::ParametersValueType >
	OptimizerParameterScalesEstimatorTemplate ()=default

void	PrintSelf (std::ostream &os, Indent indent) const override

	~OptimizerParameterScalesEstimatorTemplate () override=default

Protected Member Functions inherited from itk::Object
	Object ()

bool	PrintObservers (std::ostream &os, Indent indent) const

void	PrintSelf (std::ostream &os, Indent indent) const override

virtual void	SetTimeStamp (const TimeStamp &timeStamp)

	~Object () override

Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer	InternalClone () const

	LightObject ()

virtual void	PrintHeader (std::ostream &os, Indent indent) const

virtual void	PrintSelf (std::ostream &os, Indent indent) const

virtual void	PrintTrailer (std::ostream &os, Indent indent) const

virtual	~LightObject ()

Additional Inherited Members
Static Public Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric >
static constexpr SizeValueType	FixedDimension = TMetric::FixedDimension

static constexpr SizeValueType	MovingDimension = TMetric::MovingDimension

static constexpr SizeValueType	VirtualDimension = TMetric::VirtualDimension

Protected Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric >
IndexValueType	m_CentralRegionRadius {}

MetricPointer	m_Metric {}

SizeValueType	m_NumberOfRandomSamples {}

SamplePointContainerType	m_SamplePoints {}

TimeStamp	m_SamplingTime {}

VirtualPointSetType::ConstPointer	m_VirtualDomainPointSet {}

Protected Attributes inherited from itk::LightObject
std::atomic< int >	m_ReferenceCount {}

Static Protected Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric >
static constexpr SizeValueType	SizeOfSmallDomain = 1000

Member Typedef Documentation

◆ ConstPointer

template<typename TMetric >

using itk::RegistrationParameterScalesFromJacobian< TMetric >::ConstPointer = SmartPointer<const Self>

Definition at line 51 of file itkRegistrationParameterScalesFromJacobian.h.

◆ Pointer

template<typename TMetric >

using itk::RegistrationParameterScalesFromJacobian< TMetric >::Pointer = SmartPointer<Self>

Definition at line 50 of file itkRegistrationParameterScalesFromJacobian.h.

◆ Self

template<typename TMetric >

using itk::RegistrationParameterScalesFromJacobian< TMetric >::Self = RegistrationParameterScalesFromJacobian

Standard class type aliases.

Definition at line 48 of file itkRegistrationParameterScalesFromJacobian.h.

◆ Superclass

template<typename TMetric >

using itk::RegistrationParameterScalesFromJacobian< TMetric >::Superclass = RegistrationParameterScalesEstimator<TMetric>

Definition at line 49 of file itkRegistrationParameterScalesFromJacobian.h.

Constructor & Destructor Documentation

◆ RegistrationParameterScalesFromJacobian()

template<typename TMetric >

itk::RegistrationParameterScalesFromJacobian< TMetric >::RegistrationParameterScalesFromJacobian ( )

protecteddefault

◆ ~RegistrationParameterScalesFromJacobian()

template<typename TMetric >

itk::RegistrationParameterScalesFromJacobian< TMetric >::~RegistrationParameterScalesFromJacobian ( )

overrideprotecteddefault

Member Function Documentation

◆ ComputeSampleStepScales()

template<typename TMetric >

void itk::RegistrationParameterScalesFromJacobian< TMetric >::ComputeSampleStepScales	(	const ParametersType &	step,
		ScalesType &	sampleScales
	)

protected

Compute the step scales for samples, i.e. the impacts on each sampled voxel from a change on the transform.

◆ EstimateLocalStepScales()

template<typename TMetric >

void itk::RegistrationParameterScalesFromJacobian< TMetric >::EstimateLocalStepScales	(	const ParametersType &	step,
		ScalesType &	localStepScales
	)

overridevirtual

Estimate the scales of local steps. For each voxel, computes the impact of a step on its location as in EstimateStepScale(). Then this impact is attributed to the corresponding local parameters.

Implements itk::RegistrationParameterScalesEstimator< TMetric >.

◆ EstimateScales()

template<typename TMetric >

void itk::RegistrationParameterScalesFromJacobian< TMetric >::EstimateScales ( ScalesType & parameterScales )

overridevirtual

Estimate parameter scales from average Jacobian norms. For each parameter, compute the squared norm of its transform Jacobian, then average the squared norm over the sample points. This average is used as the scale of this parameter.

Implements itk::RegistrationParameterScalesEstimator< TMetric >.

◆ EstimateStepScale()

template<typename TMetric >

FloatType itk::RegistrationParameterScalesFromJacobian< TMetric >::EstimateStepScale ( const ParametersType & step )

overridevirtual

Estimate the scale for \(\Delta p\), the step of change on parameters. The step scale describes the impact of \(\Delta p\) on the transform.

Let us denote the transform by

\[ T(x, p) = T(x, p_0 + t * \Delta p) \]

where \(x\) is the coordinates of a voxel, \(p = p_0+t*\Delta p\) is the transform parameters, and \(t\) is the step factor.

At a specific voxel at \(x\), the step scale w.r.t. \(\Delta p\) is defined here as

\[ |\frac{dT}{dt}| = |\frac{\partial T}{\partial p} * \Delta p |. \]

For multiple voxels, we average the above formula to get the overall step scale.

Implements itk::RegistrationParameterScalesEstimator< TMetric >.

◆ GetNameOfClass()

template<typename TMetric >

const char * itk::RegistrationParameterScalesFromJacobian< TMetric >::GetNameOfClass ( ) const

overridevirtual

See also: LightObject::GetNameOfClass()

Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.

◆ New()

template<typename TMetric >

static Pointer itk::RegistrationParameterScalesFromJacobian< TMetric >::New ( )

static

New macro for creation of through a Smart Pointer.

◆ PrintSelf()

template<typename TMetric >

void itk::RegistrationParameterScalesFromJacobian< TMetric >::PrintSelf	(	std::ostream &	os,
		Indent	indent
	)		const

overrideprotectedvirtual

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::RegistrationParameterScalesEstimator< TMetric >.

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

itkRegistrationParameterScalesFromJacobian.h

Detailed Description

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Additional Inherited Members

Member Typedef Documentation

◆ ConstPointer

◆ Pointer

◆ Self

◆ Superclass

Constructor & Destructor Documentation

◆ RegistrationParameterScalesFromJacobian()

◆ ~RegistrationParameterScalesFromJacobian()

Member Function Documentation

◆ ComputeSampleStepScales()

◆ EstimateLocalStepScales()

◆ EstimateScales()

◆ EstimateStepScale()

◆ GetNameOfClass()

◆ New()

◆ PrintSelf()