Open Inventor Release 2023.2.3
 
Loading...
Searching...
No Matches
SoMultiscaleStructureEnhancementProcessing3d Class Reference

ImageViz SoMultiscaleStructureEnhancementProcessing2d engine More...

#include <ImageViz/Engines/ImageFiltering/TextureFilters/SoMultiscaleStructureEnhancementProcessing3d.h>

+ Inheritance diagram for SoMultiscaleStructureEnhancementProcessing3d:

Public Types

enum  TensorType {
  HESSIAN = 0 ,
  GRADIENT = 1
}
 
enum  Lightness {
  BRIGHT = 0 ,
  DARK = 1
}
 
enum  StructureType {
  ROD = 0 ,
  BALL = 1 ,
  PLANE = 2
}
 
- Public Types inherited from SoImageVizEngine
enum  ComputeMode {
  MODE_2D = 0 ,
  MODE_3D = 1 ,
  MODE_AUTO = 2
}
 Compute Mode This enum specifies whether the main input will be interpreted as a 3D volume or a stack of 2D images for processing. More...
 
enum  Neighborhood3d {
  CONNECTIVITY_6 = 0 ,
  CONNECTIVITY_18 = 1 ,
  CONNECTIVITY_26 = 2
}
 Neighborhood Connectivity 3D. More...
 

Public Member Functions

 SoMultiscaleStructureEnhancementProcessing3d ()
 Constructor.
 
- Public Member Functions inherited from SoImageVizEngine
virtual SoType getTypeId () const
 Returns the type identifier for this specific instance.
 
virtual void startEvaluate ()
 Evaluate engine and dependencies in another thread without blocking the current one.
 
virtual void waitEvaluate ()
 Wait for the end of engine evaluation.
 
virtual void abortEvaluate ()
 Abort current processing as soon as possible.
 
virtual bool isEvaluating ()
 Returns true if the engine evaluation is in progress.
 
- Public Member Functions inherited from SoEngine
virtual int getOutputs (SoEngineOutputList &list) const
 Returns a list of outputs in this engine.
 
SoEngineOutputgetOutput (const SbName &outputName) const
 Returns a reference to the engine output with the given name.
 
SbBool getOutputName (const SoEngineOutput *output, SbName &outputName) const
 Returns (in outputName) the name of the engine output (output).
 
SoEnginecopy () const
 Creates and returns an exact copy of the engine.
 
- Public Member Functions inherited from SoFieldContainer
void setToDefaults ()
 Sets all fields in this object to their default values.
 
SbBool hasDefaultValues () const
 Returns TRUE if all of the object's fields have their default values.
 
SbBool fieldsAreEqual (const SoFieldContainer *fc) const
 Returns TRUE if this object's fields are exactly equal to fc's fields.
 
void copyFieldValues (const SoFieldContainer *fc, SbBool copyConnections=FALSE)
 Copies the contents of fc's fields into this object's fields.
 
SoNONUNICODE SbBool set (const char *fieldDataString)
 Sets one or more fields in this object to the values specified in the given string, which should be a string in the Open Inventor file format.
 
SbBool set (const SbString &fieldDataString)
 Sets one or more fields in this object to the values specified in the given string, which should be a string in the Open Inventor file format.
 
void get (SbString &fieldDataString)
 Returns the values of the fields of this object in the Open Inventor ASCII file format in the given string.
 
virtual int getFields (SoFieldList &list) const
 Appends references to all of this object's fields to resultList, and returns the number of fields appended.
 
virtual int getAllFields (SoFieldList &list) const
 Returns a list of fields, including the eventIn's and eventOut's.
 
virtual SoFieldgetField (const SbName &fieldName) const
 Returns a the field of this object whose name is fieldName.
 
virtual SoFieldgetEventIn (const SbName &fieldName) const
 Returns a the eventIn with the given name.
 
virtual SoFieldgetEventOut (const SbName &fieldName) const
 Returns the eventOut with the given name.
 
SbBool getFieldName (const SoField *field, SbName &fieldName) const
 Returns the name of the given field in the fieldName argument.
 
SbBool enableNotify (SbBool flag)
 Notification at this Field Container is enabled (if flag == TRUE) or disabled (if flag == FALSE).
 
SbBool isNotifyEnabled () const
 Notification is the process of telling interested objects that this object has changed.
 
virtual void setUserData (void *data)
 Sets application data.
 
void * getUserData (void) const
 Gets user application data.
 
- Public Member Functions inherited from SoBase
virtual void touch ()
 Marks an instance as modified, simulating a change to it.
 
virtual SbName getName () const
 Returns the name of an instance.
 
virtual void setName (const SbName &name)
 Sets the name of an instance.
 
void setSynchronizable (const bool b)
 Sets this to be a ScaleViz synchronizable object.
 
bool isSynchronizable () const
 Gets the ScaleViz synchronizable state of this object.
 
- Public Member Functions inherited from SoRefCounter
void ref () const
 Adds a reference to an instance.
 
void unref () const
 Removes a reference from an instance.
 
void unrefNoDelete () const
 unrefNoDelete() should be called when it is desired to decrement the reference count, but not delete the instance if this brings the reference count to zero.
 
int getRefCount () const
 Returns current reference count.
 
void lock () const
 lock this instance.
 
void unlock () const
 unlock this instance.
 
- Public Member Functions inherited from SoTypedObject
SbBool isOfType (const SoType &type) const
 Returns TRUE if this object is of the type specified in type or is derived from that type.
 
template<typename TypedObjectClass >
SbBool isOfType () const
 Returns TRUE if this object is of the type of class TypedObjectClass or is derived from that class.
 

Public Attributes

SoSFImageDataAdapter inImage
 Input image.
 
SoSFEnum tensorType
 Defines whether the command will use the gradient tensor or the hessian matrix.
 
SoSFVec2f standardDeviationRange
 Standard deviation of the Gaussian kernel at the minimum and maximum scale.
 
SoSFFloat standardDeviationStep
 Standard deviation step.
 
SoSFEnum lightness
 The lightness type of structures to enhance.
 
SoSFEnum structureType
 Shape of structures to extract.
 
SoImageVizEngineOutput< SoSFImageDataAdapter, SoImageDataAdapter * > outImage
 Output image.
 
- Public Attributes inherited from SoImageVizEngine
SbEventHandler< EventArg & > onBegin
 Event raised when the processing begins.
 
SbEventHandler< EventArg & > onEnd
 Event raised when processing ends and the result is available.
 
SbEventHandler< EventArg & > onProgress
 Event raised while processing is running.
 

Additional Inherited Members

- Static Public Member Functions inherited from SoImageVizEngine
static SoType getClassTypeId ()
 Returns the type identifier for this class.
 
- Static Public Member Functions inherited from SoEngine
static SoType getClassTypeId ()
 Returns the type identifier for the SoEngine class.
 
static SoEnginegetByName (const SbName &name)
 Looks up engine(s) by name.
 
static int getByName (const SbName &name, SoEngineList &list)
 Looks up engine(s) by name.
 
- Static Public Member Functions inherited from SoFieldContainer
static SoType getClassTypeId ()
 Returns the type of this class.
 
- Static Public Member Functions inherited from SoBase
static SoType getClassTypeId ()
 Returns type identifier for this class.
 
- Static Public Member Functions inherited from SoTypedObject
static SoType getClassTypeId ()
 Returns the type identifier for this class.
 

Detailed Description

ImageViz SoMultiscaleStructureEnhancementProcessing2d engine

Overview

    The purpose of this algorithm is to enhance structures of interest from an image using a multi scale analysis. The result of this algorithm is a score image that can be used with the goal of segmenting the input image.

    The SoMultiscaleStructureEnhancement filters compute a score between 0 and 1 for each pixel, 1 representing a good matching with a structure model and 0 a background pixel. This provides a powerful technique for automatically identifying structures such as blood vessels. The score can be computed either on an Hessian matrix to detect ridge structures or on a Gradient tensor for object edges and corners. The structure models available are:

    • Balls (circular structures with Hessian in 2D, spherical in 3D, object corners with Gradient tensor)
    • Rods (linear structures)
    • Plates (only available in 3D)

    The principle of the algorithm can be summarized as follows :

    • A set of tensor fields is extracted from the image by filtering the image at different scales.
    • A score image is extracted from each tensor field by analyzing the eigenvalues of tensors.
    • The final score is obtained by selecting the maximum of all score images.

    The following publication describes this algorithm when applied to detect Rod structures with the Hessian matrix: A.F.Frangi, W.J.Niessen, K.L.Vincken, M.A.Viergever, "Multiscale vessel enhancement filtering", Lecture Notes in Computer Science(MICCAI), vol. 1496, pp. 130-137, 1998.

Tensor Extraction

    2 modes are available for computing the tensor field; the GRADIENT mode and the HESSIAN mode. The first one is based on the gradient tensor the second one on the hessian matrix.

GRADIENT mode

    In the GRADIENT mode, the gradient tensor is extracted. This tensor also referred to as structure tensor or second order moment matrix, is a matrix derived from the gradient of the image. This matrix summarizes the predominant directions of the gradient around the voxel of interest.

    $
 S_w(p) =
     \left( \begin{array}{cc}
     \int w(r) (I_x(p - r)) ^ 2\, d r & \int w(r) I_x(p - r)I_y(p - r)\, d r \\
     \int w(r) I_x(p - r)I_y(p - r)\, d r  & \int w(r) (I_y(p - r)) ^ 2\, d r
     \end{array}  \right)
 $

    Where $w(r)$ is a gaussian kernel controlling the scale of analysis.

HESSIAN mode

    In this mode, the tensor field is based on the extraction of the hessian matrix of the image. This hessian matrix is computed by filtering the image with the derivative of a gaussian kernel.The standard deviation of the kernel controls the scale of analysis.

Feature extraction

    The parameter structureType controls the type of structure that is extracted from the tensor field(ROD/BALL/PLANE). The computation is based on eigen values $\lambda_{1}$, $\lambda_{2}$ and $\lambda_{3}$ where $\mid \lambda_{1} \mid \geq \mid \lambda_{2} \mid \geq \mid \lambda_{3} \mid $.

    Let first introduce

    $ \mathcal{R}_b = \frac{ \lambda_1 }{ \sqrt{ \lambda_2 \lambda_3 } } $, and

    $ \mathcal{R}_a = \frac{ \lambda_2 }{ \lambda_3 } $

    The first ratio attains its maximum for blob-like structure. The second ratio distinguishes plate-like and line-like structures.

    The score for StructureType3D::ROD corresponds to :

    $
    \text{score}_{\text{ROD}} = (1-\exp(-\frac{\mathcal{R}_a^2}{2\alpha^2}))\exp(-\frac{\mathcal{R}_b^2}{2\beta^2})(1-\exp(-\frac{S^2}{2c^2})) 
 $

    The score for StructureType3D::BALL is computed as follow :

    $
    \text{score}_{\text{BALL}} = (1-\exp(-\frac{\mathcal{R}_a^2}{2\alpha^2}))(1-\exp(-\frac{\mathcal{R}_b^2}{2\beta^2}))(1-\exp(-\frac{S^2}{2c^2}))
 $

    The score for StructureType3D::PLANE is computed as follow :

    $
    \text{score}_{\text{PLANE}} = \exp(-\frac{\mathcal{R}_a^2}{2\alpha^2})\exp(-\frac{\mathcal{R}_b^2}{2\beta^2})(1-\exp(-\frac{S^2}{2c^2}))
 $

    where $S$ is the tensor norm $ S = \sqrt{\sum \lambda_i^2} $, $ \alpha $ is a threshold which controls the flatness sensitivity, $ \beta $ is a threshold which controls the blobness sensitivity, and $ c $ is a sensitivity threshold which controls the noise influence. $c = \text{noiseCutoff} \times S_{max}$ with $S_{max}$ the maximum Hessian norm in the image.

    In the HESSIAN mode, the lightness parameter limits the feature extraction to dark or bright objects by analyzing the sign of eigenvalues. This parameter is ignored in GRADIENT mode where tensors are positive definite matrices.

SEE ALSO

SoMultiscaleStructureEnhancementProcessing2d.

FILE FORMAT/DEFAULT

    MultiscaleStructureEnhancementProcessing3d {
    inImage NULL
    tensorType HESSIAN
    standardDeviationRange 1.0f 3.0f
    standardDeviationStep 1.0f
    lightness BRIGHT
    structureType ROD
    }


Library references: structureenhancementfilter3d

Definition at line 158 of file SoMultiscaleStructureEnhancementProcessing3d.h.

Member Enumeration Documentation

◆ Lightness

Enumerator
BRIGHT 

Extracts bright structures from dark background.

DARK 

Extracts dark structures from bright background.

Definition at line 198 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ StructureType

Enumerator
ROD 

Extracts tubular structures.

BALL 

Extracts blob-like structures.

PLANE 

Extracts plate-like structures.

Definition at line 217 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ TensorType

Enumerator
HESSIAN 

Extracts the Hessian matrix.

GRADIENT 

Extracts the gradient tensor.

Definition at line 173 of file SoMultiscaleStructureEnhancementProcessing3d.h.

Constructor & Destructor Documentation

◆ SoMultiscaleStructureEnhancementProcessing3d()

SoMultiscaleStructureEnhancementProcessing3d::SoMultiscaleStructureEnhancementProcessing3d ( )

Constructor.

Member Data Documentation

◆ inImage

SoSFImageDataAdapter SoMultiscaleStructureEnhancementProcessing3d::inImage

Input image.

Type of the image can be integer or floating. Default value is NULL. Supported types include: grayscale image.

Definition at line 168 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ lightness

SoSFEnum SoMultiscaleStructureEnhancementProcessing3d::lightness

The lightness type of structures to enhance.

Use enum Lightness. Default is BRIGHT

Definition at line 212 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ outImage

SoImageVizEngineOutput<SoSFImageDataAdapter,SoImageDataAdapter*> SoMultiscaleStructureEnhancementProcessing3d::outImage

Output image.

Type of the output image is forced to float. Default value is NULL. Supported types include: grayscale image.

Definition at line 238 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ standardDeviationRange

SoSFVec2f SoMultiscaleStructureEnhancementProcessing3d::standardDeviationRange

Standard deviation of the Gaussian kernel at the minimum and maximum scale.

Default value is SbVec2f(1.0f,3.0f).

Definition at line 190 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ standardDeviationStep

SoSFFloat SoMultiscaleStructureEnhancementProcessing3d::standardDeviationStep

Standard deviation step.

Structures will be detected from min to max standard deviation at a pitch of this value. Default value is 1.0f.

Definition at line 193 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ structureType

SoSFEnum SoMultiscaleStructureEnhancementProcessing3d::structureType

Shape of structures to extract.

Use enum StructureType. Default is ROD

Definition at line 235 of file SoMultiscaleStructureEnhancementProcessing3d.h.

◆ tensorType

SoSFEnum SoMultiscaleStructureEnhancementProcessing3d::tensorType

Defines whether the command will use the gradient tensor or the hessian matrix.

Use enum TensorType. Default is HESSIAN

Definition at line 187 of file SoMultiscaleStructureEnhancementProcessing3d.h.


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