#include <itkSyNImageRegistrationMethod.h>

Inheritance diagram for itk::SyNImageRegistrationMethod< TFixedImage, TMovingImage, TTransform >:

Collaboration diagram for itk::SyNImageRegistrationMethod< TFixedImage, TMovingImage, TTransform >:

Public Types
typedef CompositeTransform < RealType, ImageDimension >	CompositeTransformType
typedef SmartPointer< const Self >	ConstPointer
typedef TransformType::DerivativeType	DerivativeType
typedef DerivativeType::ValueType	DerivativeValueType
typedef DisplacementFieldType::Pointer	DisplacementFieldPointer
typedef TransformType::DisplacementFieldType	DisplacementFieldType
typedef DisplacementFieldType::PixelType	DisplacementVectorType
typedef FixedImageType::Pointer	FixedImagePointer
typedef TFixedImage	FixedImageType
typedef MetricType::MeasureType	MeasureType
typedef MetricType::Pointer	MetricPointer
typedef Superclass::MetricType	MetricType
typedef MovingImageType::Pointer	MovingImagePointer
typedef TMovingImage	MovingImageType
typedef Array< SizeValueType >	NumberOfIterationsArrayType
typedef SmartPointer< Self >	Pointer
typedef TransformType::ScalarType	RealType
typedef SyNImageRegistrationMethod	Self
typedef ImageRegistrationMethodv4 < TFixedImage, TMovingImage, TTransform >	Superclass
typedef CompositeTransformType::TransformType	TransformBaseType
typedef TransformOutputType::Pointer	TransformOutputPointer
typedef Superclass::TransformOutputType	TransformOutputType
typedef TransformType::Pointer	TransformPointer
typedef TTransform	TransformType
typedef MetricType::VirtualImageType	VirtualImageType
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const

virtual void	SetLearningRate (RealType _arg)
virtual RealType	GetLearningRate () const

virtual void	SetNumberOfIterationsPerLevel (NumberOfIterationsArrayType _arg)
virtual NumberOfIterationsArrayType	GetNumberOfIterationsPerLevel () const

virtual void	SetConvergenceThreshold (RealType _arg)
virtual RealType	GetConvergenceThreshold () const

virtual void	SetDownsampleImagesForMetricDerivatives (bool _arg)
virtual bool	GetDownsampleImagesForMetricDerivatives () const

virtual void	SetAverageMidPointGradients (bool _arg)
virtual bool	GetAverageMidPointGradients () const

virtual void	SetGaussianSmoothingVarianceForTheUpdateField (RealType _arg)
virtual const RealType &	GetGaussianSmoothingVarianceForTheUpdateField ()

virtual void	SetGaussianSmoothingVarianceForTheTotalField (RealType _arg)
virtual const RealType &	GetGaussianSmoothingVarianceForTheTotalField ()
Static Public Member Functions
static Pointer	New ()
Static Public Attributes
static const unsigned int	ImageDimension = TFixedImage::ImageDimension
Protected Member Functions
virtual DisplacementFieldPointer	ComputeUpdateField (const TFixedImage , const TransformBaseType , const TMovingImage , const TransformBaseType , MeasureType &)
virtual DisplacementFieldPointer	GaussianSmoothDisplacementField (const DisplacementFieldType *, const RealType)
virtual void	GenerateData ()
virtual void	InitializeRegistrationAtEachLevel (const SizeValueType)
virtual void	PrintSelf (std::ostream &os, Indent indent) const
virtual void	StartOptimization ()
	SyNImageRegistrationMethod ()
virtual	~SyNImageRegistrationMethod ()
Private Member Functions
void	operator= (const Self &)
	SyNImageRegistrationMethod (const Self &)
Private Attributes
bool	m_AverageMidPointGradients
RealType	m_ConvergenceThreshold
bool	m_DownsampleImagesForMetricDerivatives
RealType	m_GaussianSmoothingVarianceForTheTotalField
RealType	m_GaussianSmoothingVarianceForTheUpdateField
RealType	m_LearningRate
TransformPointer	m_MiddleToFixedTransform
TransformPointer	m_MiddleToMovingTransform
NumberOfIterationsArrayType	m_NumberOfIterationsPerLevel

Detailed Description

template<typename TFixedImage, typename TMovingImage, typename TTransform = DisplacementFieldTransform<double, GetImageDimension<TFixedImage>::ImageDimension>>
class itk::SyNImageRegistrationMethod< TFixedImage, TMovingImage, TTransform >

Interface method for the performing greedy SyN image registration.

For greedy SyN we use m_Transform to map the time-parameterized middle image to the fixed image (and vice versa using m_Transform->GetInverseDisplacementField() ). We employ another ivar, m_InverseTransform, to map the time-parameterized middle image to the moving image.

Output: The output is the updated transform which has been added to the composite transform.

This implementation is based on the source code in Advanced Normalization Tools (ANTs)

Avants, B. B.; Tustison, N. J.; Song, G.; Cook, P. A.; Klein, A. & Gee, J. C. A reproducible evaluation of ANTs similarity metric performance in brain image registration. Neuroimage, Penn Image Computing and Science Laboratory, University of Pennsylvania, 2011, 54, 2033-2044

The original paper discussing the method is here:

Avants, B. B.; Epstein, C. L.; Grossman, M. & Gee, J. C. Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med Image Anal, Department of Radiology, University of Pennsylvania, 2008, 12, 26-41

The method evolved since that time with crucial contributions from Gang Song and Nick Tustison. Though similar in spirit, this implementation is not identical.

Todo:: Need to allow the fixed image to have a composite transform.

Author:: Nick Tustison; Brian Avants

Definition at line 74 of file itkSyNImageRegistrationMethod.h.