ITK  5.2.0
Insight Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | List of all members
itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage > Class Template Reference

#include <itkN4BiasFieldCorrectionImageFilter.h>

+ Inheritance diagram for itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >:
+ Collaboration diagram for itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >:

Public Types

using ArrayType = typename BSplineFilterType::ArrayType
 
using BiasFieldControlPointLatticeType = typename BSplineFilterType::PointDataImageType
 
using BSplineFilterType = BSplineScatteredDataPointSetToImageFilter< PointSetType, ScalarImageType >
 
using ConstPointer = SmartPointer< const Self >
 
using InputImageType = TInputImage
 
using MaskImageType = TMaskImage
 
using MaskPixelType = typename MaskImageType::PixelType
 
using OutputImageType = TOutputImage
 
using Pointer = SmartPointer< Self >
 
using PointSetPointer = typename PointSetType::Pointer
 
using PointSetType = PointSet< ScalarType, Self::ImageDimension >
 
using PointType = typename PointSetType::PointType
 
using RealImagePointer = typename RealImageType::Pointer
 
using RealImageType = Image< RealType, ImageDimension >
 
using RealType = float
 
using ScalarImageType = Image< ScalarType, Self::ImageDimension >
 
using ScalarType = Vector< RealType, 1 >
 
using Self = N4BiasFieldCorrectionImageFilter
 
using Superclass = ImageToImageFilter< TInputImage, TOutputImage >
 
using VariableSizeArrayType = Array< unsigned int >
 
- Public Types inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
using ConstPointer = SmartPointer< const Self >
 
using InputImageConstPointer = typename InputImageType::ConstPointer
 
using InputImagePixelType = typename InputImageType::PixelType
 
using InputImagePointer = typename InputImageType::Pointer
 
using InputImageRegionType = typename InputImageType::RegionType
 
using InputImageType = TInputImage
 
using OutputImagePixelType = typename Superclass::OutputImagePixelType
 
using OutputImageRegionType = typename Superclass::OutputImageRegionType
 
using Pointer = SmartPointer< Self >
 
using Self = ImageToImageFilter
 
using Superclass = ImageSource< TOutputImage >
 
- Public Types inherited from itk::ImageSource< TOutputImage >
using ConstPointer = SmartPointer< const Self >
 
using DataObjectIdentifierType = Superclass::DataObjectIdentifierType
 
using DataObjectPointer = DataObject::Pointer
 
using DataObjectPointerArraySizeType = Superclass::DataObjectPointerArraySizeType
 
using OutputImagePixelType = typename OutputImageType::PixelType
 
using OutputImagePointer = typename OutputImageType::Pointer
 
using OutputImageRegionType = typename OutputImageType::RegionType
 
using OutputImageType = TOutputImage
 
using Pointer = SmartPointer< Self >
 
using Self = ImageSource
 
using Superclass = ProcessObject
 
- Public Types inherited from itk::ProcessObject
using ConstPointer = SmartPointer< const Self >
 
using DataObjectIdentifierType = DataObject::DataObjectIdentifierType
 
using DataObjectPointer = DataObject::Pointer
 
using DataObjectPointerArray = std::vector< DataObjectPointer >
 
using DataObjectPointerArraySizeType = DataObjectPointerArray::size_type
 
using MultiThreaderType = MultiThreaderBase
 
using NameArray = std::vector< DataObjectIdentifierType >
 
using Pointer = SmartPointer< Self >
 
using Self = ProcessObject
 
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

virtual ::itk::LightObject::Pointer CreateAnother () const
 
void EnlargeOutputRequestedRegion (DataObject *) override
 
virtual const char * GetNameOfClass () const
 
void SetInput1 (const InputImageType *image)
 
- Public Member Functions inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
const InputImageTypeGetInput () const
 
const InputImageTypeGetInput (unsigned int idx) const
 
void PopBackInput () override
 
void PopFrontInput () override
 
virtual void PushBackInput (const InputImageType *input)
 
virtual void PushFrontInput (const InputImageType *input)
 
virtual void SetInput (const DataObjectIdentifierType &key, DataObject *input)
 
virtual void SetInput (const InputImageType *input)
 
virtual void SetInput (unsigned int, const TInputImage *image)
 
virtual void SetCoordinateTolerance (double _arg)
 
virtual double GetCoordinateTolerance () const
 
virtual void SetDirectionTolerance (double _arg)
 
virtual double GetDirectionTolerance () const
 
- Public Member Functions inherited from itk::ImageSource< TOutputImage >
OutputImageTypeGetOutput ()
 
const OutputImageTypeGetOutput () const
 
OutputImageTypeGetOutput (unsigned int idx)
 
virtual void GraftOutput (DataObject *graft)
 
virtual void GraftOutput (const DataObjectIdentifierType &key, DataObject *graft)
 
virtual void GraftNthOutput (unsigned int idx, DataObject *graft)
 
ProcessObject::DataObjectPointer MakeOutput (ProcessObject::DataObjectPointerArraySizeType idx) override
 
ProcessObject::DataObjectPointer MakeOutput (const ProcessObject::DataObjectIdentifierType &) override
 
- Public Member Functions inherited from itk::ProcessObject
virtual void AbortGenerateDataOff ()
 
virtual void AbortGenerateDataOn ()
 
virtual const bool & GetAbortGenerateData () const
 
DataObjectPointerArray GetIndexedInputs ()
 
DataObjectPointerArray GetIndexedOutputs ()
 
NameArray GetInputNames () const
 
DataObjectPointerArray GetInputs ()
 
DataObjectPointerArraySizeType GetNumberOfIndexedInputs () const
 
DataObjectPointerArraySizeType GetNumberOfIndexedOutputs () const
 
DataObjectPointerArraySizeType GetNumberOfInputs () const
 
DataObjectPointerArraySizeType GetNumberOfOutputs () const
 
virtual DataObjectPointerArraySizeType GetNumberOfValidRequiredInputs () const
 
NameArray GetOutputNames () const
 
DataObjectPointerArray GetOutputs ()
 
virtual float GetProgress () const
 
NameArray GetRequiredInputNames () const
 
bool HasInput (const DataObjectIdentifierType &key) const
 
bool HasOutput (const DataObjectIdentifierType &key) const
 
void IncrementProgress (float increment)
 
virtual void PropagateRequestedRegion (DataObject *output)
 
virtual void ResetPipeline ()
 
virtual void SetAbortGenerateData (bool _arg)
 
virtual void Update ()
 
virtual void UpdateLargestPossibleRegion ()
 
virtual void UpdateOutputData (DataObject *output)
 
virtual void UpdateOutputInformation ()
 
void UpdateProgress (float progress)
 
virtual void SetReleaseDataFlag (bool val)
 
virtual bool GetReleaseDataFlag () const
 
void ReleaseDataFlagOn ()
 
void ReleaseDataFlagOff ()
 
virtual void SetReleaseDataBeforeUpdateFlag (bool _arg)
 
virtual const bool & GetReleaseDataBeforeUpdateFlag () const
 
virtual void ReleaseDataBeforeUpdateFlagOn ()
 
virtual void ReleaseDataBeforeUpdateFlagOff ()
 
virtual void SetNumberOfWorkUnits (ThreadIdType _arg)
 
virtual const ThreadIdTypeGetNumberOfWorkUnits () const
 
MultiThreaderTypeGetMultiThreader () const
 
void SetMultiThreader (MultiThreaderType *threader)
 
virtual void PrepareOutputs ()
 
- 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
 
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::ImageToImageFilter< TInputImage, TOutputImage >
static void SetGlobalDefaultDirectionTolerance (double)
 
static double GetGlobalDefaultDirectionTolerance ()
 
static void SetGlobalDefaultCoordinateTolerance (double)
 
static double GetGlobalDefaultCoordinateTolerance ()
 
- 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 ImageDimension = TInputImage::ImageDimension
 
- Static Public Attributes inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
static constexpr unsigned int InputImageDimension = TInputImage::ImageDimension
 
static constexpr unsigned int OutputImageDimension = TOutputImage::ImageDimension
 
- Static Public Attributes inherited from itk::ImageSource< TOutputImage >
static constexpr unsigned int OutputImageDimension = TOutputImage::ImageDimension
 
MaskPixelType m_MaskLabel
 
bool m_UseMaskLabel { false }
 
unsigned int m_NumberOfHistogramBins { 200 }
 
RealType m_WienerFilterNoise { static_cast<RealType>(0.01) }
 
RealType m_BiasFieldFullWidthAtHalfMaximum { static_cast<RealType>(0.15) }
 
VariableSizeArrayType m_MaximumNumberOfIterations
 
unsigned int m_ElapsedIterations { 0 }
 
RealType m_ConvergenceThreshold { static_cast<RealType>(0.001) }
 
RealType m_CurrentConvergenceMeasurement
 
unsigned int m_CurrentLevel { 0 }
 
BiasFieldControlPointLatticeType::Pointer m_LogBiasFieldControlPointLattice
 
unsigned int m_SplineOrder { 3 }
 
ArrayType m_NumberOfControlPoints
 
ArrayType m_NumberOfFittingLevels
 
virtual void SetMaskImage (const MaskImageType *input)
 
void SetInput2 (const MaskImageType *mask)
 
virtual const MaskImageTypeGetMaskImage () const
 
virtual void SetMaskLabel (MaskPixelType _arg)
 
virtual MaskPixelType GetMaskLabel () const
 
virtual void SetUseMaskLabel (bool _arg)
 
virtual bool GetUseMaskLabel () const
 
virtual void UseMaskLabelOn ()
 
virtual void UseMaskLabelOff ()
 
virtual void SetConfidenceImage (const RealImageType *input)
 
void SetInput3 (const RealImageType *image)
 
virtual const RealImageTypeGetConfidenceImage () const
 
virtual void SetNumberOfHistogramBins (unsigned int _arg)
 
virtual unsigned int GetNumberOfHistogramBins () const
 
virtual void SetWienerFilterNoise (RealType _arg)
 
virtual RealType GetWienerFilterNoise () const
 
virtual void SetBiasFieldFullWidthAtHalfMaximum (RealType _arg)
 
virtual RealType GetBiasFieldFullWidthAtHalfMaximum () const
 
virtual void SetSplineOrder (unsigned int _arg)
 
virtual unsigned int GetSplineOrder () const
 
virtual void SetNumberOfControlPoints (ArrayType _arg)
 
virtual ArrayType GetNumberOfControlPoints () const
 
virtual void SetNumberOfFittingLevels (ArrayType _arg)
 
void SetNumberOfFittingLevels (unsigned int n)
 
virtual ArrayType GetNumberOfFittingLevels () const
 
virtual void SetMaximumNumberOfIterations (VariableSizeArrayType _arg)
 
virtual VariableSizeArrayType GetMaximumNumberOfIterations () const
 
virtual void SetConvergenceThreshold (RealType _arg)
 
virtual RealType GetConvergenceThreshold () const
 
virtual const BiasFieldControlPointLatticeTypeGetLogBiasFieldControlPointLattice () const
 
virtual unsigned int GetElapsedIterations () const
 
virtual RealType GetCurrentConvergenceMeasurement () const
 
virtual unsigned int GetCurrentLevel () const
 
RealImagePointer ReconstructBiasField (const BiasFieldControlPointLatticeType *)
 
 N4BiasFieldCorrectionImageFilter ()
 
 ~N4BiasFieldCorrectionImageFilter () override=default
 
void PrintSelf (std::ostream &os, Indent indent) const override
 
void GenerateData () override
 
void SharpenImage (const RealImageType *unsharpenedImage, RealImageType *sharpenedImage) const
 
RealImagePointer UpdateBiasFieldEstimate (RealImageType *, std::vcl_size_t)
 
RealType CalculateConvergenceMeasurement (const RealImageType *, const RealImageType *) const
 

Additional Inherited Members

- Protected Types inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
using InputToOutputRegionCopierType = ImageToImageFilterDetail::ImageRegionCopier< Self::OutputImageDimension, Self::InputImageDimension >
 
using OutputToInputRegionCopierType = ImageToImageFilterDetail::ImageRegionCopier< Self::InputImageDimension, Self::OutputImageDimension >
 
- Protected Member Functions inherited from itk::ImageToImageFilter< TInputImage, TOutputImage >
 ImageToImageFilter ()
 
 ~ImageToImageFilter () override=default
 
void VerifyInputInformation () ITKv5_CONST override
 
void GenerateInputRequestedRegion () override
 
virtual void CallCopyOutputRegionToInputRegion (InputImageRegionType &destRegion, const OutputImageRegionType &srcRegion)
 
virtual void CallCopyInputRegionToOutputRegion (OutputImageRegionType &destRegion, const InputImageRegionType &srcRegion)
 
void PushBackInput (const DataObject *input) override
 
void PushFrontInput (const DataObject *input) override
 
- Protected Member Functions inherited from itk::ImageSource< TOutputImage >
 ImageSource ()
 
 ~ImageSource () override=default
 
void ClassicMultiThread (ThreadFunctionType callbackFunction)
 
virtual void ThreadedGenerateData (const OutputImageRegionType &region, ThreadIdType threadId)
 
virtual void DynamicThreadedGenerateData (const OutputImageRegionType &outputRegionForThread)
 
virtual void AllocateOutputs ()
 
virtual void BeforeThreadedGenerateData ()
 
virtual void AfterThreadedGenerateData ()
 
virtual const ImageRegionSplitterBaseGetImageRegionSplitter () const
 
virtual unsigned int SplitRequestedRegion (unsigned int i, unsigned int pieces, OutputImageRegionType &splitRegion)
 
virtual bool GetDynamicMultiThreading () const
 
virtual void SetDynamicMultiThreading (bool _arg)
 
virtual void DynamicMultiThreadingOn ()
 
virtual void DynamicMultiThreadingOff ()
 
- Protected Member Functions inherited from itk::ProcessObject
 ProcessObject ()
 
 ~ProcessObject () override
 
DataObjectGetInput (const DataObjectIdentifierType &key)
 
const DataObjectGetInput (const DataObjectIdentifierType &key) const
 
DataObjectGetInput (DataObjectPointerArraySizeType idx)
 
const DataObjectGetInput (DataObjectPointerArraySizeType idx) const
 
virtual void SetInput (const DataObjectIdentifierType &key, DataObject *input)
 
virtual void SetNthInput (DataObjectPointerArraySizeType idx, DataObject *input)
 
virtual void AddInput (DataObject *input)
 
virtual void RemoveInput (const DataObjectIdentifierType &key)
 
virtual void RemoveInput (DataObjectPointerArraySizeType)
 
DataObjectGetPrimaryInput ()
 
const DataObjectGetPrimaryInput () const
 
virtual void SetPrimaryInputName (const DataObjectIdentifierType &key)
 
virtual const char * GetPrimaryInputName () const
 
virtual void SetPrimaryInput (DataObject *object)
 
void SetNumberOfIndexedInputs (DataObjectPointerArraySizeType num)
 
virtual void SetNumberOfRequiredInputs (DataObjectPointerArraySizeType)
 
virtual const DataObjectPointerArraySizeTypeGetNumberOfRequiredInputs () const
 
bool RemoveRequiredInputName (const DataObjectIdentifierType &)
 
bool IsRequiredInputName (const DataObjectIdentifierType &) const
 
void SetRequiredInputNames (const NameArray &)
 
bool AddRequiredInputName (const DataObjectIdentifierType &)
 
bool AddRequiredInputName (const DataObjectIdentifierType &, DataObjectPointerArraySizeType idx)
 
void AddOptionalInputName (const DataObjectIdentifierType &)
 
void AddOptionalInputName (const DataObjectIdentifierType &, DataObjectPointerArraySizeType idx)
 
DataObjectGetOutput (const DataObjectIdentifierType &key)
 
const DataObjectGetOutput (const DataObjectIdentifierType &key) const
 
virtual void SetPrimaryOutputName (const DataObjectIdentifierType &key)
 
virtual const char * GetPrimaryOutputName () const
 
DataObjectGetOutput (DataObjectPointerArraySizeType i)
 
const DataObjectGetOutput (DataObjectPointerArraySizeType i) const
 
virtual void SetOutput (const DataObjectIdentifierType &name, DataObject *output)
 
virtual void RemoveOutput (const DataObjectIdentifierType &key)
 
DataObjectGetPrimaryOutput ()
 
const DataObjectGetPrimaryOutput () const
 
virtual void SetPrimaryOutput (DataObject *object)
 
virtual void SetNthOutput (DataObjectPointerArraySizeType idx, DataObject *output)
 
virtual void AddOutput (DataObject *output)
 
virtual void RemoveOutput (DataObjectPointerArraySizeType idx)
 
virtual void SetNumberOfRequiredOutputs (DataObjectPointerArraySizeType _arg)
 
virtual const DataObjectPointerArraySizeTypeGetNumberOfRequiredOutputs () const
 
void SetNumberOfIndexedOutputs (DataObjectPointerArraySizeType num)
 
DataObjectIdentifierType MakeNameFromInputIndex (DataObjectPointerArraySizeType idx) const
 
DataObjectIdentifierType MakeNameFromOutputIndex (DataObjectPointerArraySizeType idx) const
 
DataObjectPointerArraySizeType MakeIndexFromInputName (const DataObjectIdentifierType &name) const
 
DataObjectPointerArraySizeType MakeIndexFromOutputName (const DataObjectIdentifierType &name) const
 
bool IsIndexedInputName (const DataObjectIdentifierType &) const
 
bool IsIndexedOutputName (const DataObjectIdentifierType &) const
 
virtual void VerifyPreconditions () ITKv5_CONST
 
virtual void GenerateOutputRequestedRegion (DataObject *output)
 
virtual void GenerateOutputInformation ()
 
virtual void PropagateResetPipeline ()
 
virtual void ReleaseInputs ()
 
virtual void CacheInputReleaseDataFlags ()
 
virtual void RestoreInputReleaseDataFlags ()
 
virtual bool GetThreaderUpdateProgress () const
 
virtual void ThreaderUpdateProgressOn ()
 
virtual void ThreaderUpdateProgressOff ()
 
virtual void SetThreaderUpdateProgress (bool arg)
 
- Protected Member Functions inherited from itk::Object
 Object ()
 
 ~Object () override
 
bool PrintObservers (std::ostream &os, Indent indent) const
 
virtual void SetTimeStamp (const TimeStamp &timeStamp)
 
- 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 ()
 
- Static Protected Member Functions inherited from itk::ImageSource< TOutputImage >
static const ImageRegionSplitterBaseGetGlobalDefaultSplitter ()
 
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION ThreaderCallback (void *arg)
 
- Static Protected Member Functions inherited from itk::ProcessObject
static constexpr float progressFixedToFloat (uint32_t fixed)
 
static uint32_t progressFloatToFixed (float f)
 
- Protected Attributes inherited from itk::ImageSource< TOutputImage >
bool m_DynamicMultiThreading
 
- Protected Attributes inherited from itk::ProcessObject
bool m_Updating
 
TimeStamp m_OutputInformationMTime
 
- Protected Attributes inherited from itk::LightObject
std::atomic< int > m_ReferenceCount
 

Detailed Description

template<typename TInputImage, typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
class itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >

Implementation of the N4 bias field correction algorithm.

The nonparametric nonuniform intensity normalization (N3) algorithm, as introduced by Sled et al. in 1998 is a method for correcting nonuniformity associated with MR images. The algorithm assumes a simple parametric model (Gaussian) for the bias field and does not require tissue class segmentation. In addition, there are only a couple of parameters to tune with the default values performing quite well. N3 has been publicly available as a set of perl scripts (http://www.bic.mni.mcgill.ca/ServicesSoftwareAdvancedImageProcessingTools/HomePage)

The N4 algorithm, encapsulated with this class, is a variation of the original N3 algorithm with the additional benefits of an improved B-spline fitting routine which allows for multiple resolutions to be used during the correction process. We also modify the iterative update component of algorithm such that the residual bias field is continually updated

Notes for the user:

  1. Since much of the image manipulation is done in the log space of the intensities, input images with negative and small values (< 1) can produce poor results.
  2. The original authors recommend performing the bias field correction on a downsampled version of the original image.
  3. A binary mask or a weighted image can be supplied. If a binary mask is specified, those voxels in the input image which correspond to the voxels in the mask image are used to estimate the bias field. If a UseMaskLabel value is set to false (the default), all non-zero voxels in the MaskImage will be masked; otherwise only voxels in the MaskImage that match the MaskLabel will be used. If a confidence image is specified, the input voxels are weighted in the b-spline fitting routine according to the confidence voxel values.
  4. The filter returns the corrected image. If the bias field is wanted, one can reconstruct it using the class itkBSplineControlPointImageFilter. See the IJ article and the test file for an example.
  5. The 'Z' parameter in Sled's 1998 paper is the square root of the class variable 'm_WienerFilterNoise'.

The basic algorithm iterates between sharpening the intensity histogram of the corrected input image and spatially smoothing those results with a B-spline scalar field estimate of the bias field.

Author
Nicholas J. Tustison

Contributed by Nicholas J. Tustison, James C. Gee in the Insight Journal paper: https://www.insight-journal.org/browse/publication/640

REFERENCE

J.G. Sled, A.P. Zijdenbos and A.C. Evans. "A Nonparametric Method for Automatic Correction of Intensity Nonuniformity in Data" IEEE Transactions on Medical Imaging, Vol 17, No 1. Feb 1998.

N.J. Tustison, B.B. Avants, P.A. Cook, Y. Zheng, A. Egan, P.A. Yushkevich, and J.C. Gee. "N4ITK: Improved N3 Bias Correction" IEEE Transactions on Medical Imaging, 29(6):1310-1320, June 2010.

Definition at line 96 of file itkN4BiasFieldCorrectionImageFilter.h.

Member Typedef Documentation

◆ ArrayType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ArrayType = typename BSplineFilterType::ArrayType

Definition at line 137 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ BiasFieldControlPointLatticeType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::BiasFieldControlPointLatticeType = typename BSplineFilterType::PointDataImageType

Definition at line 136 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ BSplineFilterType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::BSplineFilterType = BSplineScatteredDataPointSetToImageFilter<PointSetType, ScalarImageType>

B-sline filter type alias

Definition at line 135 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ ConstPointer

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ConstPointer = SmartPointer<const Self>

Definition at line 105 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ InputImageType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::InputImageType = TInputImage

Some convenient type alias.

Definition at line 117 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ MaskImageType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::MaskImageType = TMaskImage

Definition at line 119 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ MaskPixelType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::MaskPixelType = typename MaskImageType::PixelType

Definition at line 120 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ OutputImageType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::OutputImageType = TOutputImage

Definition at line 118 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ Pointer

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::Pointer = SmartPointer<Self>

Definition at line 104 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ PointSetPointer

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::PointSetPointer = typename PointSetType::Pointer

Definition at line 131 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ PointSetType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::PointSetType = PointSet<ScalarType, Self::ImageDimension>

Definition at line 129 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ PointType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::PointType = typename PointSetType::PointType

Definition at line 132 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ RealImagePointer

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::RealImagePointer = typename RealImageType::Pointer

Definition at line 124 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ RealImageType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::RealImageType = Image<RealType, ImageDimension>

Definition at line 123 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ RealType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::RealType = float

Definition at line 122 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ ScalarImageType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ScalarImageType = Image<ScalarType, Self::ImageDimension>

Definition at line 130 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ ScalarType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ScalarType = Vector<RealType, 1>

B-spline smoothing filter argument type alias

Definition at line 128 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ Self

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::Self = N4BiasFieldCorrectionImageFilter

Standard class type aliases.

Definition at line 102 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ Superclass

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::Superclass = ImageToImageFilter<TInputImage, TOutputImage>

Definition at line 103 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ VariableSizeArrayType

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
using itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::VariableSizeArrayType = Array<unsigned int>

Definition at line 125 of file itkN4BiasFieldCorrectionImageFilter.h.

Constructor & Destructor Documentation

◆ N4BiasFieldCorrectionImageFilter()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::N4BiasFieldCorrectionImageFilter ( )
protected

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

◆ ~N4BiasFieldCorrectionImageFilter()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::~N4BiasFieldCorrectionImageFilter ( )
overrideprotecteddefault

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Member Function Documentation

◆ CalculateConvergenceMeasurement()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::CalculateConvergenceMeasurement ( const RealImageType ,
const RealImageType  
) const
private

Convergence is determined by the coefficient of variation of the difference image between the current bias field estimate and the previous estimate.

◆ CreateAnother()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual::itk::LightObject::Pointer itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::CreateAnother ( ) const
virtual

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.

Reimplemented from itk::Object.

◆ EnlargeOutputRequestedRegion()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::EnlargeOutputRequestedRegion ( DataObject )
overridevirtual

Ensures that this filter can compute the entire output at once.

Reimplemented from itk::ProcessObject.

◆ GenerateData()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GenerateData ( )
overrideprotectedvirtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Reimplemented from itk::ImageSource< TOutputImage >.

◆ GetBiasFieldFullWidthAtHalfMaximum()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetBiasFieldFullWidthAtHalfMaximum ( ) const
virtual

Get the full width at half maximum parameter characterizing the width of the Gaussian deconvolution. Default = 0.15.

◆ GetConfidenceImage()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual const RealImageType* itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetConfidenceImage ( ) const
virtual

Get confidence image function. If a confidence image is specified, estimation of the bias field weights the contribution of each voxel according the value of the corresponding voxel in the confidence image. For example, when estimating the bias field using brain , one can use a soft segmentation of the white matter as the confidence image instead of using a hard segmentation of the white matter as the mask image (as has been done in the literature) as an alternative strategy to estimating the bias field.

◆ GetConvergenceThreshold()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetConvergenceThreshold ( ) const
virtual

Get the convergence threshold. Convergence is determined by the coefficient of variation of the difference image between the current bias field estimate and the previous estimate. If this value is less than the specified threshold, the algorithm proceeds to the next fitting level or terminates if it is at the last level.

◆ GetCurrentConvergenceMeasurement()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetCurrentConvergenceMeasurement ( ) const
virtual

Get the current convergence measurement. This is a helper function for reporting observations.

◆ GetCurrentLevel()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetCurrentLevel ( ) const
virtual

Get the current fitting level. This is a helper function for reporting observations.

◆ GetElapsedIterations()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetElapsedIterations ( ) const
virtual

Get the number of elapsed iterations. This is a helper function for reporting observations.

◆ GetLogBiasFieldControlPointLattice()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual const BiasFieldControlPointLatticeType* itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetLogBiasFieldControlPointLattice ( ) const
virtual

Typically, a reduced size image is used as input to the N4 filter using something like itkShrinkImageFilter. Since the output is a corrected version of the input, the user will probably want to apply the bias field correction to the full resolution image. This can be done by using the LogBiasFieldControlPointLattice to reconstruct the bias field at the full image resolution (using the class BSplineControlPointImageFilter).

◆ GetMaskImage()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual const MaskImageType* itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetMaskImage ( ) const
virtual

Get mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

◆ GetMaskLabel()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual MaskPixelType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetMaskLabel ( ) const
virtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

◆ GetMaximumNumberOfIterations()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual VariableSizeArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetMaximumNumberOfIterations ( ) const
virtual

Get the maximum number of iterations specified at each fitting level. Default = 50.

◆ GetNameOfClass()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual const char* itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetNameOfClass ( ) const
virtual

Runtime information support.

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.

◆ GetNumberOfControlPoints()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual ArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetNumberOfControlPoints ( ) const
virtual

Get the control point grid size defining the B-spline estimate of the scalar bias field. In each dimension, the B-spline mesh size is equal to the number of control points in that dimension minus the spline order. Default = 4 control points in each dimension for a mesh size of 1 in each dimension.

◆ GetNumberOfFittingLevels()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual ArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetNumberOfFittingLevels ( ) const
virtual

Get the number of fitting levels. One of the contributions of N4 is the introduction of a multi-scale approach to fitting. This allows one to specify a B-spline mesh size for initial fitting followed by a doubling of the mesh resolution for each subsequent fitting level. Default = 1 level.

◆ GetNumberOfHistogramBins()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetNumberOfHistogramBins ( ) const
virtual

Get number of bins defining the log input intensity histogram. Default = 200.

◆ GetSplineOrder()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetSplineOrder ( ) const
virtual

Get the spline order defining the bias field estimate. Default = 3.

◆ GetUseMaskLabel()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual bool itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetUseMaskLabel ( ) const
virtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

◆ GetWienerFilterNoise()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::GetWienerFilterNoise ( ) const
virtual

Get the noise estimate defining the Wiener filter. Default = 0.01.

◆ New()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
static Pointer itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::New ( )
static

Standard New method.

◆ PrintSelf()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const
overrideprotectedvirtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.

◆ ReconstructBiasField()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealImagePointer itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ReconstructBiasField ( const BiasFieldControlPointLatticeType )

Reconstruct bias field given the control point lattice.

◆ SetBiasFieldFullWidthAtHalfMaximum()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetBiasFieldFullWidthAtHalfMaximum ( RealType  _arg)
virtual

Set the full width at half maximum parameter characterizing the width of the Gaussian deconvolution. Default = 0.15.

◆ SetConfidenceImage()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetConfidenceImage ( const RealImageType input)
virtual

Set confidence image function. If a confidence image is specified, estimation of the bias field weights the contribution of each voxel according the value of the corresponding voxel in the confidence image. For example, when estimating the bias field using brain , one can use a soft segmentation of the white matter as the confidence image instead of using a hard segmentation of the white matter as the mask image (as has been done in the literature) as an alternative strategy to estimating the bias field.

Referenced by itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetInput3().

◆ SetConvergenceThreshold()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetConvergenceThreshold ( RealType  _arg)
virtual

Set the convergence threshold. Convergence is determined by the coefficient of variation of the difference image between the current bias field estimate and the previous estimate. If this value is less than the specified threshold, the algorithm proceeds to the next fitting level or terminates if it is at the last level.

◆ SetInput1()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetInput1 ( const InputImageType image)
inline

The image expected for input for bias correction.

Definition at line 147 of file itkN4BiasFieldCorrectionImageFilter.h.

References itk::ImageToImageFilter< TInputImage, TOutputImage >::SetInput().

◆ SetInput2()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetInput2 ( const MaskImageType mask)
inline

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 159 of file itkN4BiasFieldCorrectionImageFilter.h.

References itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetMaskImage().

◆ SetInput3()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetInput3 ( const RealImageType image)
inline

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 204 of file itkN4BiasFieldCorrectionImageFilter.h.

References itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetConfidenceImage().

◆ SetMaskImage()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetMaskImage ( const MaskImageType input)
virtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Referenced by itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetInput2().

◆ SetMaskLabel()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetMaskLabel ( MaskPixelType  _arg)
virtual

Set/Get mask label value. If a binary mask image is specified and if UseMaskValue is true, only those input image voxels corresponding with mask image values equal to MaskLabel are used in estimating the bias field. If a MaskImage is specified and UseMaskLabel is false, all input image voxels corresponding to non-zero voxels in the MaskImage are used in estimating the bias field. Default = 1.

◆ SetMaximumNumberOfIterations()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetMaximumNumberOfIterations ( VariableSizeArrayType  _arg)
virtual

Set the maximum number of iterations specified at each fitting level. Default = 50.

◆ SetNumberOfControlPoints()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfControlPoints ( ArrayType  _arg)
virtual

Set the control point grid size defining the B-spline estimate of the scalar bias field. In each dimension, the B-spline mesh size is equal to the number of control points in that dimension minus the spline order. Default = 4 control points in each dimension for a mesh size of 1 in each dimension.

◆ SetNumberOfFittingLevels() [1/2]

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfFittingLevels ( ArrayType  _arg)
virtual

Set the number of fitting levels. One of the contributions of N4 is the introduction of a multi-scale approach to fitting. This allows one to specify a B-spline mesh size for initial fitting followed by a doubling of the mesh resolution for each subsequent fitting level. Default = 1 level.

Referenced by itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfFittingLevels().

◆ SetNumberOfFittingLevels() [2/2]

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfFittingLevels ( unsigned int  n)
inline

Set the number of fitting levels. One of the contributions of N4 is the introduction of a multi-scale approach to fitting. This allows one to specify a B-spline mesh size for initial fitting followed by a doubling of the mesh resolution for each subsequent fitting level. Default = 1 level.

Definition at line 306 of file itkN4BiasFieldCorrectionImageFilter.h.

References itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfFittingLevels().

◆ SetNumberOfHistogramBins()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetNumberOfHistogramBins ( unsigned int  _arg)
virtual

Set number of bins defining the log input intensity histogram. Default = 200.

◆ SetSplineOrder()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetSplineOrder ( unsigned int  _arg)
virtual

Set the spline order defining the bias field estimate. Default = 3.

◆ SetUseMaskLabel()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetUseMaskLabel ( bool  _arg)
virtual

Use a mask label for identifying mask functionality. See SetMaskLabel. Defaults to false.

◆ SetWienerFilterNoise()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SetWienerFilterNoise ( RealType  _arg)
virtual

Set the noise estimate defining the Wiener filter. Default = 0.01.

◆ SharpenImage()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::SharpenImage ( const RealImageType unsharpenedImage,
RealImageType sharpenedImage 
) const
private

Sharpen the intensity histogram of the current estimate of the corrected image and map those results to a new estimate of the unsmoothed corrected image.

◆ UpdateBiasFieldEstimate()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealImagePointer itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::UpdateBiasFieldEstimate ( RealImageType ,
std::vcl_size_t   
)
private

Given the unsmoothed estimate of the bias field, this function smooths the estimate and adds the resulting control point values to the total bias field estimate.

◆ UseMaskLabelOff()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::UseMaskLabelOff ( )
virtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

◆ UseMaskLabelOn()

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
virtual void itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::UseMaskLabelOn ( )
virtual

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Member Data Documentation

◆ ImageDimension

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
constexpr unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::ImageDimension = TInputImage::ImageDimension
staticconstexpr

ImageDimension constants

Definition at line 114 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_BiasFieldFullWidthAtHalfMaximum

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_BiasFieldFullWidthAtHalfMaximum { static_cast<RealType>(0.15) }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 435 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_ConvergenceThreshold

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_ConvergenceThreshold { static_cast<RealType>(0.001) }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 441 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_CurrentConvergenceMeasurement

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_CurrentConvergenceMeasurement
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 442 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_CurrentLevel

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_CurrentLevel { 0 }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 443 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_ElapsedIterations

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_ElapsedIterations { 0 }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 440 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_LogBiasFieldControlPointLattice

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
BiasFieldControlPointLatticeType::Pointer itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_LogBiasFieldControlPointLattice
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 447 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_MaskLabel

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
MaskPixelType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_MaskLabel
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 428 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_MaximumNumberOfIterations

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
VariableSizeArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_MaximumNumberOfIterations
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 439 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_NumberOfControlPoints

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
ArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_NumberOfControlPoints
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 450 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_NumberOfFittingLevels

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
ArrayType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_NumberOfFittingLevels
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 451 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_NumberOfHistogramBins

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_NumberOfHistogramBins { 200 }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 433 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_SplineOrder

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
unsigned int itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_SplineOrder { 3 }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 449 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_UseMaskLabel

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
bool itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_UseMaskLabel { false }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 429 of file itkN4BiasFieldCorrectionImageFilter.h.

◆ m_WienerFilterNoise

template<typename TInputImage , typename TMaskImage = Image<unsigned char, TInputImage::ImageDimension>, class TOutputImage = TInputImage>
RealType itk::N4BiasFieldCorrectionImageFilter< TInputImage, TMaskImage, TOutputImage >::m_WienerFilterNoise { static_cast<RealType>(0.01) }
private

Set mask image function. If a binary mask image is specified, only those input image voxels inside the mask image values are used in estimating the bias field.

Definition at line 434 of file itkN4BiasFieldCorrectionImageFilter.h.


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