#include <itkMultiLabelSTAPLEImageFilter.h>
This filter performs a pixelwise combination of an arbitrary number of input images, where each of them represents a segmentation of the same scene (i.e., image).
The labelings in the images are weighted relative to each other based on their "performance" as estimated by an expectation-maximization algorithm. In the process, a ground truth segmentation is estimated, and the estimated performances of the individual segmentations are relative to this estimated ground truth.
The algorithm is based on the binary STAPLE algorithm by Warfield et al. as published originally in [137].
The multi-label algorithm implemented here is described in detail in [93].
Input volumes must all contain the same size RequestedRegions. Not all input images must contain all possible labels, but all label values must have the same meaning in all images.
The filter can optionally be provided with estimates for the a priori class probabilities through the SetPriorProbabilities function. If no estimate is provided, one is automatically generated by analyzing the relative frequencies of the labels in the input images.
By default, the label used for undecided pixels is the maximum label value used in the input images plus one. Since it is possible for an image with 8 bit pixel values to use all 256 possible label values, it is permissible to combine 8 bit (i.e., byte) images into a 16 bit (i.e., short) output image.
In addition to the combined image, the estimated confusion matrices for each of the input segmentations can be obtained through the GetConfusionMatrix member function.
A termination threshold for the EM iteration can be defined by calling SetTerminationUpdateThreshold. The iteration terminates once no single parameter of any confusion matrix changes by less than this threshold. Alternatively, a maximum number of iterations can be specified by calling SetMaximumNumberOfIterations. The algorithm may still terminate after a smaller number of iterations if the termination threshold criterion is satisfied.
Definition at line 110 of file itkMultiLabelSTAPLEImageFilter.h.
Static Public Member Functions | |
static Pointer | New () |
![]() | |
static double | GetGlobalDefaultCoordinateTolerance () |
static double | GetGlobalDefaultCoordinateTolerance () |
static double | GetGlobalDefaultDirectionTolerance () |
static double | GetGlobalDefaultDirectionTolerance () |
static void | SetGlobalDefaultCoordinateTolerance (double) |
static void | SetGlobalDefaultCoordinateTolerance (double) |
static void | SetGlobalDefaultDirectionTolerance (double) |
static void | SetGlobalDefaultDirectionTolerance (double) |
![]() | |
static bool | GetGlobalWarningDisplay () |
static void | GlobalWarningDisplayOff () |
static void | GlobalWarningDisplayOn () |
static Pointer | New () |
static void | SetGlobalWarningDisplay (bool val) |
![]() | |
static void | BreakOnError () |
static Pointer | New () |
Static Public Attributes | |
static constexpr unsigned int | ImageDimension = TOutputImage::ImageDimension |
![]() | |
static constexpr unsigned int | InputImageDimension |
static constexpr unsigned int | InputImageDimension |
static constexpr unsigned int | OutputImageDimension |
static constexpr unsigned int | OutputImageDimension |
![]() | |
static constexpr unsigned int | OutputImageDimension |
Private Member Functions | |
void | AllocateConfusionMatrixArray () |
void | InitializeConfusionMatrixArrayFromVoting () |
void | InitializePriorProbabilities () |
Private Attributes | |
std::vector< ConfusionMatrixType > | m_ConfusionMatrixArray {} |
unsigned int | m_ElapsedNumberOfIterations { 0u } |
bool | m_HasLabelForUndecidedPixels { false } |
bool | m_HasMaximumNumberOfIterations { false } |
bool | m_HasPriorProbabilities { false } |
OutputPixelType | m_LabelForUndecidedPixels {} |
unsigned int | m_MaximumNumberOfIterations { 0 } |
PriorProbabilitiesType | m_PriorProbabilities {} |
TWeights | m_TerminationUpdateThreshold {} |
vcl_size_t | m_TotalLabelCount { 0 } |
std::vector< ConfusionMatrixType > | m_UpdatedConfusionMatrixArray {} |
Additional Inherited Members | |
![]() | |
using | InputToOutputRegionCopierType |
using | OutputToInputRegionCopierType |
![]() | |
static const ImageRegionSplitterBase * | GetGlobalDefaultSplitter () |
static ITK_THREAD_RETURN_FUNCTION_CALL_CONVENTION | ThreaderCallback (void *arg) |
![]() | |
template<typename TSourceObject> | |
static void | MakeRequiredOutputs (TSourceObject &sourceObject, const DataObjectPointerArraySizeType numberOfRequiredOutputs) |
static constexpr float | progressFixedToFloat (uint32_t fixed) |
static uint32_t | progressFloatToFixed (float f) |
![]() | |
bool | m_DynamicMultiThreading |
![]() | |
TimeStamp | m_OutputInformationMTime {} |
bool | m_Updating {} |
![]() | |
std::atomic< int > | m_ReferenceCount {} |
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::ConfusionMatrixType = Array2D<WeightsType> |
Definition at line 151 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::ConstPointer = SmartPointer<const Self> |
Definition at line 119 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::InputConstIteratorType = ImageRegionConstIterator<TInputImage> |
Iterator types.
Definition at line 146 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::InputImagePointer = typename InputImageType::Pointer |
Definition at line 139 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::InputImageType = TInputImage |
Image type alias support
Definition at line 137 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::InputPixelType = typename TInputImage::PixelType |
Definition at line 130 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::OutputImagePointer = typename OutputImageType::Pointer |
Definition at line 140 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::ImageSource< TOutputImage >::OutputImageRegionType |
Definition at line 125 of file itkImageSource.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::OutputImageType = TOutputImage |
Definition at line 138 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::OutputIteratorType = ImageRegionIterator<TOutputImage> |
Definition at line 147 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::OutputPixelType = typename TOutputImage::PixelType |
Extract some information from the image types. Dimensionality of the two images is assumed to be the same.
Definition at line 129 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::Pointer = SmartPointer<Self> |
Definition at line 118 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::PriorProbabilitiesType = Array<WeightsType> |
Definition at line 152 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::Self = MultiLabelSTAPLEImageFilter |
Standard class type aliases.
Definition at line 116 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::Superclass = ImageToImageFilter<TInputImage, TOutputImage> |
Definition at line 117 of file itkMultiLabelSTAPLEImageFilter.h.
using itk::MultiLabelSTAPLEImageFilter< TInputImage, TOutputImage, TWeights >::WeightsType = TWeights |
Confusion matrix type alias.
Definition at line 150 of file itkMultiLabelSTAPLEImageFilter.h.
|
inlineprotected |
Definition at line 276 of file itkMultiLabelSTAPLEImageFilter.h.
References m_LabelForUndecidedPixels, and m_TerminationUpdateThreshold.
Referenced by GetNameOfClass().
|
overrideprotecteddefault |
|
private |
|
protected |
Determine maximum value among all input images' pixels
|
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::LightObject.
|
overrideprotectedvirtual |
Give the process object a chance to indicate that it will produce more output than it was requested to produce. For example, many imaging filters must compute the entire output at once or can only produce output in complete slices. Such filters cannot handle smaller requested regions. These filters must provide an implementation of this method, setting the output requested region to the size they will produce. By default, a process object does not modify the size of the output requested region.
Reimplemented from itk::ProcessObject.
|
overrideprotectedvirtual |
A version of GenerateData() specific for image processing filters. This implementation will split the processing across multiple threads. The buffer is allocated by this method. Then the BeforeThreadedGenerateData() method is called (if provided). Then, a series of threads are spawned each calling DynamicThreadedGenerateData(). After all the threads have completed processing, the AfterThreadedGenerateData() method is called (if provided). If an image processing filter cannot be threaded, the filter should provide an implementation of GenerateData(). That implementation is responsible for allocating the output buffer. If a filter can be threaded, it should NOT provide a GenerateData() method but should provide a DynamicThreadedGenerateData() instead.
Reimplemented from itk::ImageSource< TInputImage >.
|
overrideprotectedvirtual |
What is the input requested region that is required to produce the output requested region? The base assumption for image processing filters is that the input requested region can be set to match the output requested region. If a filter requires more input (for instance a filter that uses neighborhoods needs more input than output to avoid introducing artificial boundary conditions) or less input (for instance a magnify filter) will have to override this method. In doing so, it should call its superclass' implementation as its first step. Note that imaging filters operate differently than the classes to this point in the class hierarchy. Up till now, the base assumption has been that the largest possible region will be requested of the input.
This implementation of GenerateInputRequestedRegion() only processes the inputs that are a subclass of the ImageBase<InputImageDimension>. If an input is another type of DataObject (including an Image of a different dimension), they are skipped by this method. The subclasses of ImageToImageFilter are responsible for providing an implementation of GenerateInputRequestedRegion() when there are multiple inputs of different types.
Reimplemented from itk::ImageToImageFilter< TInputImage, TInputImage >.
|
inline |
Get confusion matrix for the i-th input segmentation.
Definition at line 270 of file itkMultiLabelSTAPLEImageFilter.h.
References m_ConfusionMatrixArray.
|
virtual |
Get the number of elapsed iterations of the iterative E-M algorithm.
|
virtual |
True if LabelForUndecidedPixels has been manually set.
|
virtual |
True if the MaximumNumberOfIterations has been manually set.
|
virtual |
True if PriorProbabilities has been manually set.
|
virtual |
Get label value used for undecided pixels.
After updating the filter, this function returns the actual label value used for undecided pixels in the current output. Note that this value is overwritten when SetLabelForUndecidedPixels is called and the new value only becomes effective upon the next filter update.
|
virtual |
Set maximum number of iterations.
|
overridevirtual |
Reimplemented from itk::ImageToImageFilter< TInputImage, TInputImage >.
References MultiLabelSTAPLEImageFilter().
|
virtual |
Get prior class probabilities.
After updating the filter, this function returns the actual prior class probabilities. If these were not previously set by a call to SetPriorProbabilities, then they are estimated from the input segmentations and the result is available through this function.
|
virtual |
Set termination threshold based on confusion matrix parameter updates.
|
private |
|
private |
|
static |
Method for creation through the object factory.
|
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::ImageToImageFilter< TInputImage, TInputImage >.
|
inline |
Set label value for undecided pixels.
Definition at line 194 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasLabelForUndecidedPixels, m_LabelForUndecidedPixels, and itk::Object::Modified().
|
inline |
Set maximum number of iterations.
Definition at line 160 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasMaximumNumberOfIterations, m_MaximumNumberOfIterations, and itk::Object::Modified().
|
inline |
Set manual estimates for the a priori class probabilities.
The size of the array must be greater than the value of the largest label. The index into the array corresponds to the label value in the segmented image for the class.
Definition at line 234 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasPriorProbabilities, m_PriorProbabilities, and itk::Object::Modified().
|
virtual |
Set termination threshold based on confusion matrix parameter updates.
|
inline |
Unset label value for undecided pixels and turn on automatic selection.
Definition at line 217 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasLabelForUndecidedPixels, and itk::Object::Modified().
|
inline |
Unset the maximum number of iterations, and rely on the TerminationUpdateThreshold.
Definition at line 175 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasMaximumNumberOfIterations, and itk::Object::Modified().
|
inline |
Unset prior class probabilities and turn on automatic estimation.
Definition at line 257 of file itkMultiLabelSTAPLEImageFilter.h.
References m_HasPriorProbabilities, and itk::Object::Modified().
|
staticconstexpr |
Extract some information from the image types. Dimensionality of the two images is assumed to be the same.
Definition at line 134 of file itkMultiLabelSTAPLEImageFilter.h.
|
private |
Definition at line 312 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by GetConfusionMatrix().
|
private |
Definition at line 322 of file itkMultiLabelSTAPLEImageFilter.h.
|
private |
Definition at line 304 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by SetLabelForUndecidedPixels(), and UnsetLabelForUndecidedPixels().
|
private |
Definition at line 320 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by SetMaximumNumberOfIterations(), and UnsetMaximumNumberOfIterations().
|
private |
Definition at line 306 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by SetPriorProbabilities(), and UnsetPriorProbabilities().
|
private |
Definition at line 303 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by MultiLabelSTAPLEImageFilter(), and SetLabelForUndecidedPixels().
|
private |
Definition at line 321 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by SetMaximumNumberOfIterations().
|
private |
Definition at line 307 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by SetPriorProbabilities().
|
private |
Definition at line 324 of file itkMultiLabelSTAPLEImageFilter.h.
Referenced by MultiLabelSTAPLEImageFilter().
|
private |
Definition at line 301 of file itkMultiLabelSTAPLEImageFilter.h.
|
private |
Definition at line 313 of file itkMultiLabelSTAPLEImageFilter.h.