ITK  5.3.0
Insight Toolkit
Classes | Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | Protected Member Functions | Private Types | Private Member Functions | Private Attributes | List of all members
itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage > Class Template Reference

#include <itkMattesMutualInformationImageToImageMetric.h>

+ Inheritance diagram for itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >:
+ Collaboration diagram for itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >:

Classes

struct  MMIMetricPerThreadStruct
 

Public Types

using ConstPointer = SmartPointer< const Self >
 
using JointPDFDerivativesType = Image< PDFValueType, 3 >
 
using JointPDFType = Image< PDFValueType, 2 >
 
using OffsetValueType = typename FixedImageType::OffsetValueType
 
using PDFValueType = double
 
using Pointer = SmartPointer< Self >
 
using Self = MattesMutualInformationImageToImageMetric
 
using Superclass = ImageToImageMetric< TFixedImage, TMovingImage >
 
- Public Types inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
using ConstPointer = SmartPointer< const Self >
 
using CoordinateRepresentationType = typename Superclass::ParametersValueType
 
using FixedImageConstPointer = typename FixedImageType::ConstPointer
 
using FixedImageIndexContainer = std::vector< FixedImageIndexType >
 
using FixedImageIndexType = typename FixedImageType::IndexType
 
using FixedImageIndexValueType = typename FixedImageIndexType::IndexValueType
 
using FixedImageMaskConstPointer = typename FixedImageMaskType::ConstPointer
 
using FixedImageMaskPointer = typename FixedImageMaskType::Pointer
 
using FixedImageMaskType = SpatialObject< Self::FixedImageDimension >
 
using FixedImagePixelType = typename TFixedImage::PixelType
 
using FixedImagePointType = typename TransformType::InputPointType
 
using FixedImageRegionType = typename FixedImageType::RegionType
 
using FixedImageType = TFixedImage
 
using GradientImageFilterPointer = typename GradientImageFilterType::Pointer
 
using GradientImageFilterType = GradientRecursiveGaussianImageFilter< MovingImageType, GradientImageType >
 
using GradientImagePointer = SmartPointer< GradientImageType >
 
using GradientImageType = Image< GradientPixelType, Self::MovingImageDimension >
 
using GradientPixelType = CovariantVector< RealType, Self::MovingImageDimension >
 
using InputPointType = typename TransformType::InputPointType
 
using InterpolatorPointer = typename InterpolatorType::Pointer
 
using InterpolatorType = InterpolateImageFunction< MovingImageType, CoordinateRepresentationType >
 
using MovingImageConstPointer = typename MovingImageType::ConstPointer
 
using MovingImageIndexType = typename MovingImageType::IndexType
 
using MovingImageMaskConstPointer = typename MovingImageMaskType::ConstPointer
 
using MovingImageMaskPointer = typename MovingImageMaskType::Pointer
 
using MovingImageMaskType = SpatialObject< Self::MovingImageDimension >
 
using MovingImagePixelType = typename TMovingImage::PixelType
 
using MovingImagePointType = typename TransformType::OutputPointType
 
using MovingImageType = TMovingImage
 
using MultiThreaderType = MultiThreaderBase
 
using OutputPointType = typename TransformType::OutputPointType
 
using Pointer = SmartPointer< Self >
 
using RealType = typename NumericTraits< MovingImagePixelType >::RealType
 
using Self = ImageToImageMetric
 
using Superclass = SingleValuedCostFunction
 
using TransformJacobianType = typename TransformType::JacobianType
 
using TransformParametersType = typename TransformType::ParametersType
 
using TransformPointer = typename TransformType::Pointer
 
using TransformType = Transform< CoordinateRepresentationType, Self::MovingImageDimension, Self::FixedImageDimension >
 
- Public Types inherited from itk::SingleValuedCostFunction
using ConstPointer = SmartPointer< const Self >
 
using DerivativeType = Array< ParametersValueType >
 
using MeasureType = double
 
using ParametersType = Superclass::ParametersType
 
using ParametersValueType = Superclass::ParametersValueType
 
using Pointer = SmartPointer< Self >
 
using Self = SingleValuedCostFunction
 
using Superclass = CostFunction
 
- Public Types inherited from itk::CostFunctionTemplate< TInternalComputationValueType >
using ConstPointer = SmartPointer< const Self >
 
using ParametersType = OptimizerParameters< TInternalComputationValueType >
 
using ParametersValueType = TInternalComputationValueType
 
using Pointer = SmartPointer< Self >
 
using Self = CostFunctionTemplate
 
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 GetDerivative (const ParametersType &parameters, DerivativeType &derivative) const override
 
virtual const char * GetNameOfClass () const
 
MeasureType GetValue (const ParametersType &parameters) const override
 
void GetValueAndDerivative (const ParametersType &parameters, MeasureType &value, DerivativeType &derivative) const override
 
void Initialize () override
 
virtual void SetNumberOfHistogramBins (SizeValueType _arg)
 
virtual const SizeValueTypeGetNumberOfHistogramBins () const
 
virtual void SetUseExplicitPDFDerivatives (bool _arg)
 
virtual const bool & GetUseExplicitPDFDerivatives () const
 
virtual void UseExplicitPDFDerivativesOn ()
 
const JointPDFType::Pointer GetJointPDF () const
 
const JointPDFDerivativesType::Pointer GetJointPDFDerivatives () const
 
- Public Member Functions inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
virtual void ComputeGradient ()
 
virtual const FixedImageRegionTypeGetFixedImageRegion () const
 
virtual const FixedImagePixelTypeGetFixedImageSamplesIntensityThreshold () const
 
virtual GradientImageTypeGetModifiableGradientImage ()
 
virtual InterpolatorTypeGetModifiableInterpolator ()
 
virtual TransformTypeGetModifiableTransform ()
 
SizeValueType GetNumberOfMovingImageSamples ()
 
unsigned int GetNumberOfParameters () const override
 
virtual const SizeValueTypeGetNumberOfPixelsCounted () const
 
SizeValueType GetNumberOfSpatialSamples ()
 
virtual const bool & GetUseAllPixels () const
 
virtual const bool & GetUseFixedImageIndexes () const
 
virtual const bool & GetUseFixedImageSamplesIntensityThreshold () const
 
virtual const bool & GetUseSequentialSampling () const
 
virtual void MultiThreadingInitialize ()
 
void SetFixedImageIndexes (const FixedImageIndexContainer &indexes)
 
virtual void SetFixedImageRegion (const FixedImageRegionType reg)
 
void SetFixedImageSamplesIntensityThreshold (const FixedImagePixelType &thresh)
 
virtual void SetInterpolator (InterpolatorType *_arg)
 
void SetNumberOfSpatialSamples (SizeValueType num)
 
virtual void SetTransform (TransformType *_arg)
 
void SetTransformParameters (const ParametersType &parameters) const
 
void SetUseAllPixels (bool useAllPixels)
 
void SetUseFixedImageIndexes (bool useIndexes)
 
void SetUseFixedImageSamplesIntensityThreshold (bool useThresh)
 
void SetUseSequentialSampling (bool useSequential)
 
void UseAllPixelsOff ()
 
void UseAllPixelsOn ()
 
virtual void SetFixedImage (const FixedImageType *_arg)
 
virtual const FixedImageTypeGetFixedImage () const
 
virtual void SetMovingImage (const MovingImageType *_arg)
 
virtual const MovingImageTypeGetMovingImage () const
 
virtual void SetMovingImageMask (MovingImageMaskType *_arg)
 
virtual void SetMovingImageMask (const MovingImageMaskType *_arg)
 
virtual const MovingImageMaskTypeGetMovingImageMask () const
 
virtual void SetFixedImageMask (FixedImageMaskType *_arg)
 
virtual void SetFixedImageMask (const FixedImageMaskType *_arg)
 
virtual const FixedImageMaskTypeGetFixedImageMask () const
 
void SetNumberOfWorkUnits (ThreadIdType numberOfThreads)
 
virtual const ThreadIdTypeGetNumberOfWorkUnits () const
 
virtual void SetComputeGradient (bool _arg)
 
virtual const bool & GetComputeGradient () const
 
virtual void ComputeGradientOn ()
 
virtual void SetNumberOfFixedImageSamples (SizeValueType numSamples)
 
virtual const SizeValueTypeGetNumberOfFixedImageSamples () const
 
void ReinitializeSeed ()
 
void ReinitializeSeed (int seed)
 
virtual void SetUseCachingOfBSplineWeights (bool _arg)
 
virtual const bool & GetUseCachingOfBSplineWeights () const
 
virtual void UseCachingOfBSplineWeightsOn ()
 
virtual MultiThreaderTypeGetModifiableThreader ()
 
const TransformPointerGetThreaderTransform ()
 
- Public Member Functions inherited from itk::Object
unsigned long AddObserver (const EventObject &event, Command *)
 
unsigned long AddObserver (const EventObject &event, Command *) 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
 
CommandGetCommand (unsigned long tag)
 
bool GetDebug () const
 
MetaDataDictionaryGetMetaDataDictionary ()
 
const MetaDataDictionaryGetMetaDataDictionary () const
 
virtual ModifiedTimeType 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
 
void Register () const override
 
void RemoveAllObservers ()
 
void RemoveObserver (unsigned long tag)
 
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 void Delete ()
 
virtual int GetReferenceCount () const
 
void Print (std::ostream &os, Indent indent=0) const
 

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 ()
 

Static Public Attributes

static constexpr unsigned int MovingImageDimension = MovingImageType::ImageDimension
 
- Static Public Attributes inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
static constexpr unsigned int FixedImageDimension = TFixedImage::ImageDimension
 
static constexpr unsigned int MovingImageDimension = TMovingImage::ImageDimension
 

Protected Member Functions

 MattesMutualInformationImageToImageMetric ()
 
void PrintSelf (std::ostream &os, Indent indent) const override
 
 ~MattesMutualInformationImageToImageMetric () override=default
 
- Protected Member Functions inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
virtual void ComputeImageDerivatives (const MovingImagePointType &mappedPoint, ImageDerivativesType &gradient, ThreadIdType threadId) const
 
 ImageToImageMetric ()
 
virtual void PreComputeTransformValues ()
 
virtual void SampleFixedImageIndexes (FixedImageSampleContainer &samples) const
 
virtual void SampleFixedImageRegion (FixedImageSampleContainer &samples) const
 
virtual void SampleFullFixedImageRegion (FixedImageSampleContainer &samples) const
 
virtual void TransformPoint (unsigned int sampleNumber, MovingImagePointType &mappedPoint, bool &sampleOk, double &movingImageValue, ThreadIdType threadId) const
 
virtual void TransformPointWithDerivatives (unsigned int sampleNumber, MovingImagePointType &mappedPoint, bool &sampleOk, double &movingImageValue, ImageDerivativesType &movingImageGradient, ThreadIdType threadId) const
 
 ~ImageToImageMetric () override=default
 
void GetValueMultiThreadedInitiate () const
 
void GetValueMultiThreadedPostProcessInitiate () const
 
virtual void GetValueThread (ThreadIdType threadId) const
 
void GetValueAndDerivativeMultiThreadedInitiate () const
 
void GetValueAndDerivativeMultiThreadedPostProcessInitiate () const
 
virtual void GetValueAndDerivativeThread (ThreadIdType threadId) const
 
virtual void SynchronizeTransforms () const
 
- Protected Member Functions inherited from itk::SingleValuedCostFunction
 SingleValuedCostFunction ()=default
 
 ~SingleValuedCostFunction () override
 
- Protected Member Functions inherited from itk::CostFunctionTemplate< TInternalComputationValueType >
 CostFunctionTemplate ()=default
 
 ~CostFunctionTemplate () override=default
 
- Protected Member Functions inherited from itk::Object
 Object ()
 
bool PrintObservers (std::ostream &os, Indent indent) const
 
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 PrintTrailer (std::ostream &os, Indent indent) const
 
virtual ~LightObject ()
 

Private Types

using CubicBSplineDerivativeFunctionType = BSplineDerivativeKernelFunction< 3, PDFValueType >
 
using CubicBSplineFunctionType = BSplineKernelFunction< 3, PDFValueType >
 
using JointPDFDerivativesIndexType = JointPDFDerivativesType::IndexType
 
using JointPDFDerivativesRegionType = JointPDFDerivativesType::RegionType
 
using JointPDFDerivativesSizeType = JointPDFDerivativesType::SizeType
 
using JointPDFDerivativesValueType = JointPDFDerivativesType::PixelType
 
using JointPDFIndexType = JointPDFType::IndexType
 
using JointPDFRegionType = JointPDFType::RegionType
 
using JointPDFSizeType = JointPDFType::SizeType
 
using JointPDFValueType = JointPDFType::PixelType
 
using MarginalPDFType = std::vector< PDFValueType >
 
using PRatioArrayType = Array2D< PRatioType >
 
using PRatioType = PDFValueType
 

Private Member Functions

void ComputeFixedImageParzenWindowIndices (FixedImageSampleContainer &samples)
 
void ComputePDFDerivatives (ThreadIdType threadId, unsigned int sampleNumber, int pdfMovingIndex, const ImageDerivativesType &movingImageGradientValue, PDFValueType cubicBSplineDerivativeValue) const
 
void GetValueAndDerivativeThreadPostProcess (ThreadIdType threadId, bool withinSampleThread) const override
 
void GetValueAndDerivativeThreadPreProcess (ThreadIdType threadId, bool withinSampleThread) const override
 
bool GetValueAndDerivativeThreadProcessSample (ThreadIdType threadId, SizeValueType fixedImageSample, const MovingImagePointType &mappedPoint, double movingImageValue, const ImageDerivativesType &movingImageGradientValue) const override
 
void GetValueThreadPostProcess (ThreadIdType threadId, bool withinSampleThread) const override
 
void GetValueThreadPreProcess (ThreadIdType threadId, bool withinSampleThread) const override
 
bool GetValueThreadProcessSample (ThreadIdType threadId, SizeValueType fixedImageSample, const MovingImagePointType &mappedPoint, double movingImageValue) const override
 
 itkAlignedTypedef (ITK_CACHE_LINE_ALIGNMENT, PaddedMMIMetricPerThreadStruct, AlignedMMIMetricPerThreadStruct)
 
 itkPadStruct (ITK_CACHE_LINE_ALIGNMENT, MMIMetricPerThreadStruct, PaddedMMIMetricPerThreadStruct)
 

Private Attributes

PDFValueType m_FixedImageBinSize { 0.0 }
 
PDFValueType m_FixedImageNormalizedMin { 0.0 }
 
PDFValueType m_FixedImageTrueMax { 0.0 }
 
PDFValueType m_FixedImageTrueMin { 0.0 }
 
bool m_ImplicitDerivativesSecondPass { false }
 
std::unique_ptr< AlignedMMIMetricPerThreadStruct[]> m_MMIMetricPerThreadVariables
 
PDFValueType m_MovingImageBinSize { 0.0 }
 
MarginalPDFType m_MovingImageMarginalPDF
 
PDFValueType m_MovingImageNormalizedMin { 0.0 }
 
PDFValueType m_MovingImageTrueMax { 0.0 }
 
PDFValueType m_MovingImageTrueMin { 0.0 }
 
SizeValueType m_NumberOfHistogramBins { 50 }
 
PRatioArrayType m_PRatioArray
 
bool m_UseExplicitPDFDerivatives { true }
 

Additional Inherited Members

- Protected Types inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
using BooleanArrayType = std::vector< bool >
 
using BSplineInterpolatorType = BSplineInterpolateImageFunction< MovingImageType, CoordinateRepresentationType >
 
using BSplineParametersOffsetType = FixedArray< SizeValueType, FixedImageType::ImageDimension >
 
using BSplineTransformIndexArrayType = typename BSplineTransformType::ParameterIndexArrayType
 
using BSplineTransformIndicesArrayType = Array2D< IndexValueType >
 
using BSplineTransformType = BSplineBaseTransform< CoordinateRepresentationType, FixedImageType::ImageDimension, Self::DeformationSplineOrder >
 
using BSplineTransformWeightsArrayType = Array2D< WeightsValueType >
 
using BSplineTransformWeightsType = typename BSplineTransformType::WeightsType
 
using DerivativeFunctionType = CentralDifferenceImageFunction< MovingImageType, CoordinateRepresentationType >
 
using FixedImageSampleContainer = std::vector< FixedImageSamplePoint >
 
using ImageDerivativesType = CovariantVector< double, Self::MovingImageDimension >
 
using IndexValueType = typename BSplineTransformIndexArrayType::ValueType
 
using MovingImagePointArrayType = std::vector< MovingImagePointType >
 
using WeightsValueType = typename BSplineTransformWeightsType::ValueType
 
- Static Protected Member Functions inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION GetValueMultiThreaded (void *workunitInfoAsVoid)
 
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION GetValueMultiThreadedPostProcess (void *workunitInfoAsVoid)
 
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION GetValueAndDerivativeMultiThreaded (void *workunitInfoAsVoid)
 
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION GetValueAndDerivativeMultiThreadedPostProcess (void *workunitInfoAsVoid)
 
- Protected Attributes inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
BSplineInterpolatorType::Pointer m_BSplineInterpolator
 
BSplineParametersOffsetType m_BSplineParametersOffset
 
MovingImagePointArrayType m_BSplinePreTransformPointsArray
 
BSplineTransformType::Pointer m_BSplineTransform
 
BSplineTransformIndexArrayType m_BSplineTransformIndices
 
BSplineTransformIndicesArrayType m_BSplineTransformIndicesArray
 
BSplineTransformWeightsType m_BSplineTransformWeights
 
BSplineTransformWeightsArrayType m_BSplineTransformWeightsArray
 
bool m_ComputeGradient { true }
 
DerivativeFunctionType::Pointer m_DerivativeCalculator
 
FixedImageConstPointer m_FixedImage
 
FixedImageIndexContainer m_FixedImageIndexes
 
FixedImageMaskConstPointer m_FixedImageMask
 
FixedImageSampleContainer m_FixedImageSamples
 
FixedImagePixelType m_FixedImageSamplesIntensityThreshold
 
GradientImagePointer m_GradientImage
 
InterpolatorPointer m_Interpolator
 
bool m_InterpolatorIsBSpline { false }
 
MovingImageConstPointer m_MovingImage
 
MovingImageMaskConstPointer m_MovingImageMask
 
SizeValueType m_NumberOfFixedImageSamples { 50000 }
 
SizeValueType m_NumberOfParameters { 0 }
 
SizeValueType m_NumberOfPixelsCounted { 0 }
 
ThreadIdType m_NumberOfWorkUnits { 1 }
 
SizeValueType m_NumBSplineWeights { 0 }
 
int m_RandomSeed
 
bool m_ReseedIterator { false }
 
std::unique_ptr< BSplineTransformIndexArrayType[]> m_ThreaderBSplineTransformIndices
 
std::unique_ptr< BSplineTransformWeightsType[]> m_ThreaderBSplineTransformWeights
 
std::unique_ptr< TransformPointer[]> m_ThreaderTransform
 
TransformPointer m_Transform
 
bool m_TransformIsBSpline { false }
 
bool m_UseAllPixels { false }
 
bool m_UseCachingOfBSplineWeights { true }
 
bool m_UseFixedImageIndexes { false }
 
bool m_UseFixedImageSamplesIntensityThreshold { false }
 
bool m_UseSequentialSampling { false }
 
BooleanArrayType m_WithinBSplineSupportRegionArray
 
MultiThreaderType::Pointer m_Threader
 
std::unique_ptr< ConstantPointerWrapperm_ConstSelfWrapper
 
std::unique_ptr< unsigned int[]> m_ThreaderNumberOfMovingImageSamples
 
bool m_WithinThreadPreProcess { false }
 
bool m_WithinThreadPostProcess { false }
 
- Protected Attributes inherited from itk::LightObject
std::atomic< int > m_ReferenceCount
 
- Static Protected Attributes inherited from itk::ImageToImageMetric< TFixedImage, TMovingImage >
static constexpr unsigned int DeformationSplineOrder = 3
 

Detailed Description

template<typename TFixedImage, typename TMovingImage>
class itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >

Computes the mutual information between two images to be registered using the method of Mattes et al.

MattesMutualInformationImageToImageMetric computes the mutual information between a fixed and moving image to be registered.

This class is templated over the FixedImage type and the MovingImage type.

The fixed and moving images are set via methods SetFixedImage() and SetMovingImage(). This metric makes use of user specified Transform and Interpolator. The Transform is used to map points from the fixed image to the moving image domain. The Interpolator is used to evaluate the image intensity at user specified geometric points in the moving image. The Transform and Interpolator are set via methods SetTransform() and SetInterpolator().

If a BSplineInterpolationFunction is used, this class obtain image derivatives from the BSpline interpolator. Otherwise, image derivatives are computed using central differencing.

Warning
This metric assumes that the moving image has already been connected to the interpolator outside of this class.

The method GetValue() computes of the mutual information while method GetValueAndDerivative() computes both the mutual information and its derivatives with respect to the transform parameters.

The calculations are based on the method of Mattes et al [1,2] where the probability density distribution are estimated using Parzen histograms. Since the fixed image PDF does not contribute to the derivatives, it does not need to be smooth. Hence, a zero order (box car) BSpline kernel is used for the fixed image intensity PDF. On the other hand, to ensure smoothness a third order BSpline kernel is used for the moving image intensity PDF.

On Initialize(), the FixedImage is uniformly sampled within the FixedImageRegion. The number of samples used can be set via SetNumberOfSpatialSamples(). Typically, the number of spatial samples used should increase with the image size.

The option UseAllPixelOn() disables the random sampling and uses all the pixels of the FixedImageRegion in order to estimate the joint intensity PDF.

During each call of GetValue(), GetDerivatives(), GetValueAndDerivatives(), marginal and joint intensity PDF's values are estimated at discrete position or bins. The number of bins used can be set via SetNumberOfHistogramBins(). To handle data with arbitrary magnitude and dynamic range, the image intensity is scale such that any contribution to the histogram will fall into a valid bin.

One the PDF's have been constructed, the mutual information is obtained by doubling summing over the discrete PDF values.

Notes:

  1. This class returns the negative mutual information value.

References: [1] "Nonrigid multimodality image registration" D. Mattes, D. R. Haynor, H. Vesselle, T. Lewellen and W. Eubank Medical Imaging 2001: Image Processing, 2001, pp. 1609-1620. [2] "PET-CT Image Registration in the Chest Using Free-form Deformations" D. Mattes, D. R. Haynor, H. Vesselle, T. Lewellen and W. Eubank IEEE Transactions in Medical Imaging. Vol.22, No.1, January 2003. pp.120-128. [3] "Optimization of Mutual Information for MultiResolution Image Registration" P. Thevenaz and M. Unser IEEE Transactions in Image Processing, 9(12) December 2000.

ITK Sphinx Examples:
Examples
Examples/RegistrationITKv4/DeformableRegistration13.cxx, Examples/RegistrationITKv4/DeformableRegistration14.cxx, Examples/RegistrationITKv4/DeformableRegistration15.cxx, Examples/RegistrationITKv4/ImageRegistration16.cxx, Examples/RegistrationITKv4/MultiResImageRegistration2.cxx, Examples/RegistrationITKv4/MultiResImageRegistration3.cxx, and SphinxExamples/src/Registration/Common/WatchRegistration/Code.cxx.

Definition at line 117 of file itkMattesMutualInformationImageToImageMetric.h.

Member Typedef Documentation

◆ ConstPointer

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::ConstPointer = SmartPointer<const Self>

◆ CubicBSplineDerivativeFunctionType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::CubicBSplineDerivativeFunctionType = BSplineDerivativeKernelFunction<3, PDFValueType>
private

◆ CubicBSplineFunctionType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::CubicBSplineFunctionType = BSplineKernelFunction<3, PDFValueType>
private

Typedefs for BSpline kernel and derivative functions.

Definition at line 282 of file itkMattesMutualInformationImageToImageMetric.h.

◆ JointPDFDerivativesIndexType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFDerivativesIndexType = JointPDFDerivativesType::IndexType
private

◆ JointPDFDerivativesRegionType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFDerivativesRegionType = JointPDFDerivativesType::RegionType
private

◆ JointPDFDerivativesSizeType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFDerivativesSizeType = JointPDFDerivativesType::SizeType
private

◆ JointPDFDerivativesType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFDerivativesType = Image<PDFValueType, 3>

◆ JointPDFDerivativesValueType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFDerivativesValueType = JointPDFDerivativesType::PixelType
private

◆ JointPDFIndexType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFIndexType = JointPDFType::IndexType
private

◆ JointPDFRegionType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFRegionType = JointPDFType::RegionType
private

◆ JointPDFSizeType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFSizeType = JointPDFType::SizeType
private

◆ JointPDFType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFType = Image<PDFValueType, 2>

Typedef for the joint PDF and PDF derivatives are stored as ITK Images.

Definition at line 230 of file itkMattesMutualInformationImageToImageMetric.h.

◆ JointPDFValueType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::JointPDFValueType = JointPDFType::PixelType
private

◆ MarginalPDFType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::MarginalPDFType = std::vector<PDFValueType>
private

The moving image marginal PDF.

Definition at line 338 of file itkMattesMutualInformationImageToImageMetric.h.

◆ OffsetValueType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::OffsetValueType = typename FixedImageType::OffsetValueType

◆ PDFValueType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::PDFValueType = double

The marginal PDFs are stored as std::vector.

Definition at line 226 of file itkMattesMutualInformationImageToImageMetric.h.

◆ Pointer

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::Pointer = SmartPointer<Self>

◆ PRatioArrayType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::PRatioArrayType = Array2D<PRatioType>
private

◆ PRatioType

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::PRatioType = PDFValueType
private

Helper array for storing the values of the JointPDF ratios.

Definition at line 332 of file itkMattesMutualInformationImageToImageMetric.h.

◆ Self

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::Self = MattesMutualInformationImageToImageMetric

Standard class type aliases.

Definition at line 124 of file itkMattesMutualInformationImageToImageMetric.h.

◆ Superclass

template<typename TFixedImage , typename TMovingImage >
using itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::Superclass = ImageToImageMetric<TFixedImage, TMovingImage>

Constructor & Destructor Documentation

◆ MattesMutualInformationImageToImageMetric()

template<typename TFixedImage , typename TMovingImage >
itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::MattesMutualInformationImageToImageMetric ( )
protected

◆ ~MattesMutualInformationImageToImageMetric()

template<typename TFixedImage , typename TMovingImage >
itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::~MattesMutualInformationImageToImageMetric ( )
overrideprotecteddefault

Member Function Documentation

◆ ComputeFixedImageParzenWindowIndices()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::ComputeFixedImageParzenWindowIndices ( FixedImageSampleContainer samples)
private

Precompute fixed image parzen window indices.

◆ ComputePDFDerivatives()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::ComputePDFDerivatives ( ThreadIdType  threadId,
unsigned int  sampleNumber,
int  pdfMovingIndex,
const ImageDerivativesType movingImageGradientValue,
PDFValueType  cubicBSplineDerivativeValue 
) const
private

Compute PDF derivative contribution for each parameter.

◆ GetDerivative()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetDerivative ( const ParametersType parameters,
DerivativeType derivative 
) const
overridevirtual

Get the derivatives of the match measure.

Implements itk::SingleValuedCostFunction.

◆ GetJointPDF()

template<typename TFixedImage , typename TMovingImage >
const JointPDFType::Pointer itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetJointPDF ( ) const
inline

Get the internal JointPDF image that was used in creating the metric value.

Definition at line 238 of file itkMattesMutualInformationImageToImageMetric.h.

◆ GetJointPDFDerivatives()

template<typename TFixedImage , typename TMovingImage >
const JointPDFDerivativesType::Pointer itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetJointPDFDerivatives ( ) const
inline

Get the internal JointPDFDeriviative image that was used in creating the metric derivative value. This is only created when UseExplicitPDFDerivatives is ON, and derivatives are requested.

Definition at line 255 of file itkMattesMutualInformationImageToImageMetric.h.

◆ GetNameOfClass()

template<typename TFixedImage , typename TMovingImage >
virtual const char* itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetNameOfClass ( ) const
virtual

Run-time type information (and related methods).

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetNumberOfHistogramBins()

template<typename TFixedImage , typename TMovingImage >
virtual const SizeValueType& itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetNumberOfHistogramBins ( ) const
virtual

Number of bins to used in the histogram. According to Mattes et al the optimum value is 50. The minimum value is 5 due to the padding required by the Parzen windowing with a cubic-BSpline kernel. Note that even if the metric is used on binary images, the number of bins should at least be equal to five.

◆ GetUseExplicitPDFDerivatives()

template<typename TFixedImage , typename TMovingImage >
virtual const bool& itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetUseExplicitPDFDerivatives ( ) const
virtual

This variable selects the method to be used for computing the Metric derivatives with respect to the Transform parameters. Two modes of computation are available. The choice between one and the other is a trade-off between computation speed and memory allocations. The two modes are described in detail below:

UseExplicitPDFDerivatives = True will compute the Metric derivative by first calculating the derivatives of each one of the Joint PDF bins with respect to each one of the Transform parameters and then accumulating these contributions in the final metric derivative array by using a bin-specific weight. The memory required for storing the intermediate derivatives is a 3D array of floating point values with size equals to the product of (number of histogram bins)^2 times number of transform parameters. This method is well suited for Transform with a small number of parameters.

UseExplicitPDFDerivatives = False will compute the Metric derivative by first computing the weights for each one of the Joint PDF bins and caching them into an array. Then it will revisit each one of the PDF bins for computing its weighted contribution to the full derivative array. In this method an extra 2D array is used for storing the weights of each one of the PDF bins. This is an array of floating point values with size equals to (number of histogram bins)^2. This method is well suited for Transforms with a large number of parameters, such as, BSplineTransforms.

◆ GetValue()

template<typename TFixedImage , typename TMovingImage >
MeasureType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValue ( const ParametersType parameters) const
overridevirtual

Get the value.

Implements itk::SingleValuedCostFunction.

◆ GetValueAndDerivative()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueAndDerivative ( const ParametersType parameters,
MeasureType value,
DerivativeType derivative 
) const
overridevirtual

Get the value and derivatives for single valued optimizers.

Reimplemented from itk::SingleValuedCostFunction.

◆ GetValueAndDerivativeThreadPostProcess()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueAndDerivativeThreadPostProcess ( ThreadIdType  ,
bool   
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetValueAndDerivativeThreadPreProcess()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueAndDerivativeThreadPreProcess ( ThreadIdType  ,
bool   
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetValueAndDerivativeThreadProcessSample()

template<typename TFixedImage , typename TMovingImage >
bool itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueAndDerivativeThreadProcessSample ( ThreadIdType  ,
SizeValueType  ,
const MovingImagePointType ,
double  ,
const ImageDerivativesType  
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetValueThreadPostProcess()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueThreadPostProcess ( ThreadIdType  ,
bool   
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetValueThreadPreProcess()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueThreadPreProcess ( ThreadIdType  ,
bool   
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ GetValueThreadProcessSample()

template<typename TFixedImage , typename TMovingImage >
bool itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::GetValueThreadProcessSample ( ThreadIdType  ,
SizeValueType  ,
const MovingImagePointType ,
double   
) const
overrideprivatevirtual

Synchronizes the threader transforms with the transform member variable.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ Initialize()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::Initialize ( )
overridevirtual

Initialize the Metric by (1) making sure that all the components are present and plugged together correctly, (2) uniformly select NumberOfSpatialSamples within the FixedImageRegion, and (3) allocate memory for pdf data structures.

Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ itkAlignedTypedef()

template<typename TFixedImage , typename TMovingImage >
itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::itkAlignedTypedef ( ITK_CACHE_LINE_ALIGNMENT  ,
PaddedMMIMetricPerThreadStruct  ,
AlignedMMIMetricPerThreadStruct   
)
private

◆ itkPadStruct()

template<typename TFixedImage , typename TMovingImage >
itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::itkPadStruct ( ITK_CACHE_LINE_ALIGNMENT  ,
MMIMetricPerThreadStruct  ,
PaddedMMIMetricPerThreadStruct   
)
private

◆ New()

template<typename TFixedImage , typename TMovingImage >
static Pointer itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::New ( )
static

Method for creation through the object factory.

◆ PrintSelf()

template<typename TFixedImage , typename TMovingImage >
void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::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::ImageToImageMetric< TFixedImage, TMovingImage >.

◆ SetNumberOfHistogramBins()

template<typename TFixedImage , typename TMovingImage >
virtual void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::SetNumberOfHistogramBins ( SizeValueType  _arg)
virtual

Number of bins to used in the histogram. According to Mattes et al the optimum value is 50. The minimum value is 5 due to the padding required by the Parzen windowing with a cubic-BSpline kernel. Note that even if the metric is used on binary images, the number of bins should at least be equal to five.

◆ SetUseExplicitPDFDerivatives()

template<typename TFixedImage , typename TMovingImage >
virtual void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::SetUseExplicitPDFDerivatives ( bool  _arg)
virtual

This variable selects the method to be used for computing the Metric derivatives with respect to the Transform parameters. Two modes of computation are available. The choice between one and the other is a trade-off between computation speed and memory allocations. The two modes are described in detail below:

UseExplicitPDFDerivatives = True will compute the Metric derivative by first calculating the derivatives of each one of the Joint PDF bins with respect to each one of the Transform parameters and then accumulating these contributions in the final metric derivative array by using a bin-specific weight. The memory required for storing the intermediate derivatives is a 3D array of floating point values with size equals to the product of (number of histogram bins)^2 times number of transform parameters. This method is well suited for Transform with a small number of parameters.

UseExplicitPDFDerivatives = False will compute the Metric derivative by first computing the weights for each one of the Joint PDF bins and caching them into an array. Then it will revisit each one of the PDF bins for computing its weighted contribution to the full derivative array. In this method an extra 2D array is used for storing the weights of each one of the PDF bins. This is an array of floating point values with size equals to (number of histogram bins)^2. This method is well suited for Transforms with a large number of parameters, such as, BSplineTransforms.

◆ UseExplicitPDFDerivativesOn()

template<typename TFixedImage , typename TMovingImage >
virtual void itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::UseExplicitPDFDerivativesOn ( )
virtual

This variable selects the method to be used for computing the Metric derivatives with respect to the Transform parameters. Two modes of computation are available. The choice between one and the other is a trade-off between computation speed and memory allocations. The two modes are described in detail below:

UseExplicitPDFDerivatives = True will compute the Metric derivative by first calculating the derivatives of each one of the Joint PDF bins with respect to each one of the Transform parameters and then accumulating these contributions in the final metric derivative array by using a bin-specific weight. The memory required for storing the intermediate derivatives is a 3D array of floating point values with size equals to the product of (number of histogram bins)^2 times number of transform parameters. This method is well suited for Transform with a small number of parameters.

UseExplicitPDFDerivatives = False will compute the Metric derivative by first computing the weights for each one of the Joint PDF bins and caching them into an array. Then it will revisit each one of the PDF bins for computing its weighted contribution to the full derivative array. In this method an extra 2D array is used for storing the weights of each one of the PDF bins. This is an array of floating point values with size equals to (number of histogram bins)^2. This method is well suited for Transforms with a large number of parameters, such as, BSplineTransforms.

Member Data Documentation

◆ m_FixedImageBinSize

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_FixedImageBinSize { 0.0 }
private

◆ m_FixedImageNormalizedMin

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_FixedImageNormalizedMin { 0.0 }
private

◆ m_FixedImageTrueMax

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_FixedImageTrueMax { 0.0 }
private

◆ m_FixedImageTrueMin

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_FixedImageTrueMin { 0.0 }
private

◆ m_ImplicitDerivativesSecondPass

template<typename TFixedImage , typename TMovingImage >
bool itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_ImplicitDerivativesSecondPass { false }
mutableprivate

◆ m_MMIMetricPerThreadVariables

template<typename TFixedImage , typename TMovingImage >
std::unique_ptr<AlignedMMIMetricPerThreadStruct[]> itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MMIMetricPerThreadVariables
private

◆ m_MovingImageBinSize

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MovingImageBinSize { 0.0 }
private

◆ m_MovingImageMarginalPDF

template<typename TFixedImage , typename TMovingImage >
MarginalPDFType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MovingImageMarginalPDF
mutableprivate

◆ m_MovingImageNormalizedMin

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MovingImageNormalizedMin { 0.0 }
private

◆ m_MovingImageTrueMax

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MovingImageTrueMax { 0.0 }
private

◆ m_MovingImageTrueMin

template<typename TFixedImage , typename TMovingImage >
PDFValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_MovingImageTrueMin { 0.0 }
private

◆ m_NumberOfHistogramBins

template<typename TFixedImage , typename TMovingImage >
SizeValueType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_NumberOfHistogramBins { 50 }
private

Variables to define the marginal and joint histograms.

Definition at line 321 of file itkMattesMutualInformationImageToImageMetric.h.

◆ m_PRatioArray

template<typename TFixedImage , typename TMovingImage >
PRatioArrayType itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_PRatioArray
mutableprivate

◆ m_UseExplicitPDFDerivatives

template<typename TFixedImage , typename TMovingImage >
bool itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::m_UseExplicitPDFDerivatives { true }
private

◆ MovingImageDimension

template<typename TFixedImage , typename TMovingImage >
constexpr unsigned int itk::MattesMutualInformationImageToImageMetric< TFixedImage, TMovingImage >::MovingImageDimension = MovingImageType::ImageDimension
staticconstexpr

The moving image dimension.

Definition at line 160 of file itkMattesMutualInformationImageToImageMetric.h.


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