Segments structures in an image based on a user supplied edge potential map and user supplied shape model. More...

#include <itkGeodesicActiveContourShapePriorLevelSetImageFilter.h>

Inheritance diagram for itk::GeodesicActiveContourShapePriorLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >:

Collaboration diagram for itk::GeodesicActiveContourShapePriorLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >:

List of all members.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::FeatureImageType	FeatureImageType
typedef GeodesicActiveContourFunctionType::Pointer	GeodesicActiveContourFunctionPointer
typedef GeodesicActiveContourShapePriorLevelSetFunction < OutputImageType, FeatureImageType >	GeodesicActiveContourFunctionType
typedef Superclass::OutputImageType	OutputImageType
typedef Superclass::OutputPixelType	OutputPixelType
typedef SmartPointer< Self >	Pointer
typedef GeodesicActiveContourShapePriorLevelSetImageFilter	Self
typedef ShapePriorSegmentationLevelSetImageFilter < TInputImage, TFeatureImage, TOutputPixelType >	Superclass
typedef Superclass::ValueType	ValueType
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const

void	SetDerivativeSigma (float value)
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
void	GenerateData ()
	GeodesicActiveContourShapePriorLevelSetImageFilter (const Self &)
void	operator= (const Self &)
virtual void	PrintSelf (std::ostream &os, Indent indent) const
Private Attributes
GeodesicActiveContourFunctionPointer	m_GeodesicActiveContourFunction
float	GetDerivativeSigma () const
	~GeodesicActiveContourShapePriorLevelSetImageFilter ()
	GeodesicActiveContourShapePriorLevelSetImageFilter ()

Detailed Description

template<class TInputImage, class TFeatureImage, class TOutputPixelType = float>
class itk::GeodesicActiveContourShapePriorLevelSetImageFilter< TInputImage, TFeatureImage, TOutputPixelType >

Segments structures in an image based on a user supplied edge potential map and user supplied shape model.

IMPORTANT: The SegmentationLevelSetImageFilter class, ShapePriorSegmentationLevelSetImageFilter class and the GeodesicActiveContourShapePrior0LevelSetFunction class contain additional information necessary to gain full understanding of how to use this filter.

OVERVIEW: This class is a level set method segmentation filter. An initial contour is propagated outwards (or inwards) until it ''sticks'' to the shape boundaries. This is done by using a level set speed function based on a user supplied edge potential map and a user supplied shape model.

INPUTS: This filter requires two inputs. The first input is a initial level set. The initial level set is a real image which contains the initial contour/surface as the zero level set. For example, a signed distance function from the initial contour/surface is typically used. Unlike the simpler ShapeDetectionLevelSetImageFilter the initial contour does not have to lie wholly within the shape to be segmented. The intiial contour is allow to overlap the shape boundary. The advection term in the update equation behaves like a doublet and attracts the contour to the boundary. The shape prior term adds robustness by incorporating aprior information about the shape to be segmented. This approach for segmentation follows that of Leventon et al (2000).

: The second input is the feature image. For this filter, this is the edge potential map. General characteristics of an edge potential map is that it has values close to zero in regions near the edges and values close to one inside the shape itself. Typically, the edge potential map is compute from the image gradient, for example:

$g(I) = 1 / ( 1 + | (\nabla * G)(I)| )$

$g(I) = \exp^{-|(\nabla * G)(I)|}$

where $ I $ is image intensity and $(\nabla * G)$ is the derivative of Gaussian operator.

: See SegmentationLevelSetImageFilter and SparseFieldLevelSetImageFilter for more information on Inputs.

PARAMETERS: The PropagationScaling parameter can be used to switch from propagation outwards (POSITIVE scaling parameter) versus propagating inwards (NEGATIVE scaling parameter).

This implementation allows the user to set the weights between the propagation, advection curvature and shape prior term using methods SetPropagationScaling(), SetAdvectionScaling(), SetCurvatureScaling() and SetShapePriorScaling. In general, the larger the CurvatureScaling, the smoother the resulting contour. To follow the implementation in Leventon et al paper, set the PropagationScaling to $\lambda_1 \times c$ , the AdvectionScaling and CurvatureScaling both to $\lambda_1$ and the ShapePriorScaling to $\lambda_2$ .

OUTPUTS: The filter outputs a single, scalar, real-valued image. Negative values in the output image represent the inside of the segmented region and positive values in the image represent the outside of the segmented region. The zero crossings of the image correspond to the position of the propagating front.

: See SparseFieldLevelSetImageFilter and SegmentationLevelSetImageFilter for more information.

REFERENCES

: Leventon, M.E. et al. "Statistical Shape Influence in Geodesic Active Contours", CVPR 2000.

See also:: SegmentationLevelSetImageFilter; ShapePriorSegmentationLevelSetImageFilter; GeodesicActiveContourShapePriorLevelSetFunction; SparseFieldLevelSetImageFilter; ShapeSignedDistanceFunction

Definition at line 113 of file itkGeodesicActiveContourShapePriorLevelSetImageFilter.h.