SimpleITK
itk::simple::STAPLEImageFilter Class Reference

The STAPLE filter implements the Simultaneous Truth and Performance Level Estimation algorithm for generating ground truth volumes from a set of binary expert segmentations. More...

#include <sitkSTAPLEImageFilter.h>

Inheritance diagram for itk::simple::STAPLEImageFilter:
Collaboration diagram for itk::simple::STAPLEImageFilter:

## Public Types

using PixelIDTypeList = IntegerPixelIDTypeList

using Self = STAPLEImageFilter

Public Types inherited from itk::simple::ImageFilter
using Self = ImageFilter

Public Types inherited from itk::simple::ProcessObject
using Self = ProcessObject

## Public Member Functions

Image Execute (const Image &image1)

Image Execute (const Image &image1, const Image &image2)

Image Execute (const Image &image1, const Image &image2, const Image &image3)

Image Execute (const Image &image1, const Image &image2, const Image &image3, const Image &image4)

Image Execute (const Image &image1, const Image &image2, const Image &image3, const Image &image4, const Image &image5)

Image Execute (const std::vector< Image > &images)

double GetConfidenceWeight () const

uint32_t GetElapsedIterations () const

double GetForegroundValue () const

unsigned int GetMaximumIterations () const

std::string GetName () const

std::vector< double > GetSensitivity () const

std::vector< double > GetSpecificity () const
After the filter is updated, this method returns the Specificity (true negative fraction, q) value for the i-th expert input volume. More...

SelfSetConfidenceWeight (double ConfidenceWeight)

SelfSetForegroundValue (double ForegroundValue)

SelfSetMaximumIterations (unsigned int MaximumIterations)

STAPLEImageFilter ()

std::string ToString () const

virtual ~STAPLEImageFilter ()

Public Member Functions inherited from itk::simple::ImageFilter
ImageFilter ()

virtual ~ImageFilter ()=0

Public Member Functions inherited from itk::simple::ProcessObject
virtual void Abort ()

virtual int AddCommand (itk::simple::EventEnum event, const std::function< void()> &func)
Directly add a callback to observe an event. More...

virtual int AddCommand (itk::simple::EventEnum event, itk::simple::Command &cmd)
Add a Command Object to observer the event. More...

virtual float GetProgress () const
An Active Measurement of the progress of execution. More...

virtual bool HasCommand (itk::simple::EventEnum event) const
Query of this object has any registered commands for event. More...

ProcessObject ()

virtual void RemoveAllCommands ()
Remove all registered commands. More...

virtual ~ProcessObject ()

virtual void DebugOn ()

virtual void DebugOff ()

virtual bool GetDebug () const

virtual void SetDebug (bool debugFlag)

virtual void SetNumberOfThreads (unsigned int n)

virtual unsigned int GetNumberOfThreads () const

virtual void SetNumberOfWorkUnits (unsigned int n)

virtual unsigned int GetNumberOfWorkUnits () const

## Private Types

using MemberFunctionType = Image(Self::*)(const std::vector< Image > &)

## Private Member Functions

template<class TImageType >
Image ExecuteInternal (const std::vector< Image > &images)

## Private Attributes

double m_ConfidenceWeight {1.0}

uint32_t m_ElapsedIterations {0}

double m_ForegroundValue {1.0}

unsigned int m_MaximumIterations {std::numeric_limits<unsigned int>::max()}

std::unique_ptr< detail::MemberFunctionFactory< MemberFunctionType > > m_MemberFactory

std::vector< double > m_Sensitivity {std::vector<double>()}

std::vector< double > m_Specificity {std::vector<double>()}

## Friends

Static Public Member Functions inherited from itk::simple::ProcessObject
static bool GetGlobalDefaultDebug ()

static void GlobalDefaultDebugOff ()

static void GlobalDefaultDebugOn ()

static void SetGlobalDefaultDebug (bool debugFlag)

static void GlobalWarningDisplayOn ()

static void GlobalWarningDisplayOff ()

static void SetGlobalWarningDisplay (bool flag)

static bool GetGlobalWarningDisplay ()

static double GetGlobalDefaultCoordinateTolerance ()
Access the global tolerance to determine congruent spaces. More...

static void SetGlobalDefaultCoordinateTolerance (double)
Access the global tolerance to determine congruent spaces. More...

static double GetGlobalDefaultDirectionTolerance ()
Access the global tolerance to determine congruent spaces. More...

static void SetGlobalDefaultDirectionTolerance (double)
Access the global tolerance to determine congruent spaces. More...

Set/Get the default threader used for process objects. More...

Set/Get the default threader used for process objects. More...

static void SetGlobalDefaultNumberOfThreads (unsigned int n)

Set/Get the default threader used for process objects. More...

Protected Member Functions inherited from itk::simple::ImageFilter
void CheckImageMatchingDimension (const Image &image1, const Image &image2, const std::string &image2Name)

void CheckImageMatchingPixelType (const Image &image1, const Image &image2, const std::string &image2Name)

void CheckImageMatchingSize (const Image &image1, const Image &image2, const std::string &image2Name)

Protected Member Functions inherited from itk::simple::ProcessObject
virtual unsigned long AddITKObserver (const itk::EventObject &, itk::Command *)

virtual itk::ProcessObjectGetActiveProcess ()

virtual void OnActiveProcessDelete ()

virtual void onCommandDelete (const itk::simple::Command *cmd) noexcept

virtual void PreUpdate (itk::ProcessObject *p)

virtual void RemoveITKObserver (EventCommand &e)

Protected Member Functions inherited from itk::simple::NonCopyable
NonCopyable ()=default

NonCopyable (const NonCopyable &)=delete

NonCopyableoperator= (const NonCopyable &)=delete

Static Protected Member Functions inherited from itk::simple::ImageFilter
template<class TImageType >
static void FixNonZeroIndex (TImageType *img)

Static Protected Member Functions inherited from itk::simple::ProcessObject
template<class TImageType >
static TImageType::ConstPointer CastImageToITK (const Image &img)

template<class TPixelType , unsigned int VImageDimension, unsigned int VLength, template< typename, unsigned int > class TVector>
static Image CastITKToImage (itk::Image< TVector< TPixelType, VLength >, VImageDimension > *img)

template<unsigned int VImageDimension, unsigned int VLength, template< unsigned int > class TVector>
static Image CastITKToImage (itk::Image< TVector< VLength >, VImageDimension > *img)

template<class TImageType >
static Image CastITKToImage (TImageType *img)

static const itk::EventObjectGetITKEventObject (EventEnum e)

template<typename T >
static std::ostream & ToStringHelper (std::ostream &os, const T &v)

static std::ostream & ToStringHelper (std::ostream &os, const char &v)

static std::ostream & ToStringHelper (std::ostream &os, const signed char &v)

static std::ostream & ToStringHelper (std::ostream &os, const unsigned char &v)

## Detailed Description

The STAPLE filter implements the Simultaneous Truth and Performance Level Estimation algorithm for generating ground truth volumes from a set of binary expert segmentations.

The STAPLE algorithm treats segmentation as a pixelwise classification, which leads to an averaging scheme that accounts for systematic biases in the behavior of experts in order to generate a fuzzy ground truth volume and simultaneous accuracy assessment of each expert. The ground truth volumes produced by this filter are floating point volumes of values between zero and one that indicate probability of each pixel being in the object targeted by the segmentation.

The STAPLE algorithm is described in

S. Warfield, K. Zou, W. Wells, "Validation of image segmentation and expert quality with an expectation-maximization algorithm" in MICCAI 2002: Fifth International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer-Verlag, Heidelberg, Germany, 2002, pp. 298-306

INPUTS
Input volumes to the STAPLE filter must be binary segmentations of an image, that is, there must be a single foreground value that represents positively classified pixels (pixels that are considered to belong inside the segmentation). Any number of background pixel values may be present in the input images. You can, for example, input volumes with many different labels as long as the structure you are interested in creating ground truth for is consistently labeled among all input volumes. Pixel type of the input volumes does not matter. Specify the label value for positively classified pixels using SetForegroundValue. All other labels will be considered to be negatively classified pixels (background).

Input volumes must all contain the same size RequestedRegions.

OUTPUTS
The STAPLE filter produces a single output volume with a range of floating point values from zero to one. IT IS VERY IMPORTANT TO INSTANTIATE THIS FILTER WITH A FLOATING POINT OUTPUT TYPE (floats or doubles). You may threshold the output above some probability threshold if you wish to produce a binary ground truth.
PARAMETERS
The STAPLE algorithm requires a number of inputs. You may specify any number of input volumes using the SetInput(i, p_i) method, where i ranges from zero to N-1, N is the total number of input segmentations, and p_i is the SmartPointer to the i-th segmentation.

The SetConfidenceWeight parameter is a modifier for the prior probability that any pixel would be classified as inside the target object. This implementation of the STAPLE algorithm automatically calculates prior positive classification probability as the average fraction of the image volume filled by the target object in each input segmentation. The ConfidenceWeight parameter allows for scaling the of this default prior probability: if g_t is the prior probability that a pixel would be classified inside the target object, then g_t is set to g_t * ConfidenceWeight before iterating on the solution. In general ConfidenceWeight should be left to the default of 1.0.

You must provide a foreground value using SetForegroundValue that the STAPLE algorithm will use to identify positively classified pixels in the the input images. All other values in the image will be treated as background values. For example, if your input segmentations consist of 1's everywhere inside the segmented region, then use SetForegroundValue(1).

The STAPLE algorithm is an iterative E-M algorithm and will converge on a solution after some number of iterations that cannot be known a priori. After updating the filter, the total elapsed iterations taken to converge on the solution can be queried through GetElapsedIterations() . You may also specify a MaximumNumberOfIterations, after which the algorithm will stop iterating regardless of whether or not it has converged. This implementation of the STAPLE algorithm will find the solution to within seven digits of precision unless it is stopped early.

Once updated, the Sensitivity (true positive fraction, q) and Specificity (true negative fraction, q) for each expert input volume can be queried using GetSensitivity(i) and GetSpecificity(i), where i is the i-th input volume.

REQUIRED PARAMETERS
The only required parameters for this filter are the ForegroundValue and the input volumes. All other parameters may be safely left to their default values. Please see the paper cited above for more information on the STAPLE algorithm and its parameters. A proper understanding of the algorithm is important for interpreting the results that it produces.
EVENTS
This filter invokes IterationEvent() at each iteration of the E-M algorithm. Setting the AbortGenerateData() flag will cause the algorithm to halt after the current iteration and produce results just as if it had converged. The algorithm makes no attempt to report its progress since the number of iterations needed cannot be known in advance.
itk::simple::STAPLE for the procedural interface

Definition at line 77 of file sitkSTAPLEImageFilter.h.

## ◆ MemberFunctionType

 using itk::simple::STAPLEImageFilter::MemberFunctionType = Image (Self::*)( const std::vector & )
private

Setup for member function dispatching

Definition at line 172 of file sitkSTAPLEImageFilter.h.

## ◆ PixelIDTypeList

Define the pixels types supported by this filter

Definition at line 92 of file sitkSTAPLEImageFilter.h.

## ◆ Self

Definition at line 81 of file sitkSTAPLEImageFilter.h.

## ◆ ~STAPLEImageFilter()

 virtual itk::simple::STAPLEImageFilter::~STAPLEImageFilter ( )
virtual

Destructor

## ◆ STAPLEImageFilter()

 itk::simple::STAPLEImageFilter::STAPLEImageFilter ( )

Default Constructor that takes no arguments and initializes default parameters

## ◆ Execute() [1/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const Image & image1 )

## ◆ Execute() [2/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const Image & image1, const Image & image2 )

## ◆ Execute() [3/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const Image & image1, const Image & image2, const Image & image3 )

## ◆ Execute() [4/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const Image & image1, const Image & image2, const Image & image3, const Image & image4 )

## ◆ Execute() [5/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const Image & image1, const Image & image2, const Image & image3, const Image & image4, const Image & image5 )

## ◆ Execute() [6/6]

 Image itk::simple::STAPLEImageFilter::Execute ( const std::vector< Image > & images )

Execute the filter on the input images

## ◆ ExecuteInternal()

template<class TImageType >
 Image itk::simple::STAPLEImageFilter::ExecuteInternal ( const std::vector< Image > & images )
private

## ◆ GetConfidenceWeight()

 double itk::simple::STAPLEImageFilter::GetConfidenceWeight ( ) const
inline

Scales the estimated prior probability that a pixel will be inside the targeted object of segmentation. The default prior probability g_t is calculated automatically as the average fraction of positively classified pixels to the total size of the volume (across all input volumes). ConfidenceWeight will scale this default value as g_t = g_t * ConfidenceWeight. In general, ConfidenceWeight should be left to the default of 1.0.

Definition at line 105 of file sitkSTAPLEImageFilter.h.

## ◆ GetElapsedIterations()

 uint32_t itk::simple::STAPLEImageFilter::GetElapsedIterations ( ) const
inline

Get the number of elapsed iterations of the iterative E-M algorithm.

This is a measurement. Its value is updated in the Execute methods, so the value will only be valid after an execution.

Definition at line 132 of file sitkSTAPLEImageFilter.h.

## ◆ GetForegroundValue()

 double itk::simple::STAPLEImageFilter::GetForegroundValue ( ) const
inline

Set get the binary ON value of the input image.

Definition at line 115 of file sitkSTAPLEImageFilter.h.

## ◆ GetMaximumIterations()

 unsigned int itk::simple::STAPLEImageFilter::GetMaximumIterations ( ) const
inline

Set/Get the maximum number of iterations after which the STAPLE algorithm will be considered to have converged. In general this SHOULD NOT be set and the algorithm should be allowed to converge on its own.

Definition at line 125 of file sitkSTAPLEImageFilter.h.

## ◆ GetName()

 std::string itk::simple::STAPLEImageFilter::GetName ( ) const
inlinevirtual

Name of this class

Implements itk::simple::ProcessObject.

Definition at line 152 of file sitkSTAPLEImageFilter.h.

## ◆ GetSensitivity()

 std::vector itk::simple::STAPLEImageFilter::GetSensitivity ( ) const
inline

After the filter is updated, this method returns a std::vector<double> of all Sensitivity (true positive fraction, p) values for the expert input volumes.

This is a measurement. Its value is updated in the Execute methods, so the value will only be valid after an execution.

Definition at line 140 of file sitkSTAPLEImageFilter.h.

## ◆ GetSpecificity()

 std::vector itk::simple::STAPLEImageFilter::GetSpecificity ( ) const
inline

After the filter is updated, this method returns the Specificity (true negative fraction, q) value for the i-th expert input volume.

This is a measurement. Its value is updated in the Execute methods, so the value will only be valid after an execution.

Definition at line 148 of file sitkSTAPLEImageFilter.h.

## ◆ SetConfidenceWeight()

 Self& itk::simple::STAPLEImageFilter::SetConfidenceWeight ( double ConfidenceWeight )
inline

Scales the estimated prior probability that a pixel will be inside the targeted object of segmentation. The default prior probability g_t is calculated automatically as the average fraction of positively classified pixels to the total size of the volume (across all input volumes). ConfidenceWeight will scale this default value as g_t = g_t * ConfidenceWeight. In general, ConfidenceWeight should be left to the default of 1.0.

Definition at line 100 of file sitkSTAPLEImageFilter.h.

## ◆ SetForegroundValue()

 Self& itk::simple::STAPLEImageFilter::SetForegroundValue ( double ForegroundValue )
inline

Set get the binary ON value of the input image.

Definition at line 110 of file sitkSTAPLEImageFilter.h.

## ◆ SetMaximumIterations()

 Self& itk::simple::STAPLEImageFilter::SetMaximumIterations ( unsigned int MaximumIterations )
inline

Set/Get the maximum number of iterations after which the STAPLE algorithm will be considered to have converged. In general this SHOULD NOT be set and the algorithm should be allowed to converge on its own.

Definition at line 120 of file sitkSTAPLEImageFilter.h.

## ◆ ToString()

 std::string itk::simple::STAPLEImageFilter::ToString ( ) const
virtual

Print ourselves out

Reimplemented from itk::simple::ProcessObject.

## Friends And Related Function Documentation

friend

Definition at line 177 of file sitkSTAPLEImageFilter.h.

## ◆ m_ConfidenceWeight

 double itk::simple::STAPLEImageFilter::m_ConfidenceWeight {1.0}
private

Definition at line 182 of file sitkSTAPLEImageFilter.h.

## ◆ m_ElapsedIterations

 uint32_t itk::simple::STAPLEImageFilter::m_ElapsedIterations {0}
private

Definition at line 189 of file sitkSTAPLEImageFilter.h.

## ◆ m_ForegroundValue

 double itk::simple::STAPLEImageFilter::m_ForegroundValue {1.0}
private

Definition at line 184 of file sitkSTAPLEImageFilter.h.

## ◆ m_MaximumIterations

 unsigned int itk::simple::STAPLEImageFilter::m_MaximumIterations {std::numeric_limits::max()}
private

Definition at line 186 of file sitkSTAPLEImageFilter.h.

## ◆ m_MemberFactory

 std::unique_ptr > itk::simple::STAPLEImageFilter::m_MemberFactory
private

Definition at line 179 of file sitkSTAPLEImageFilter.h.

## ◆ m_Sensitivity

 std::vector itk::simple::STAPLEImageFilter::m_Sensitivity {std::vector()}
private

Definition at line 191 of file sitkSTAPLEImageFilter.h.

## ◆ m_Specificity

 std::vector itk::simple::STAPLEImageFilter::m_Specificity {std::vector()}
private

Definition at line 193 of file sitkSTAPLEImageFilter.h.

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