ImFusion C++ SDK 4.5.0
ImFusion::Cranial::VesselSegmentationAlgorithm Class Reference

#include <CranialPlugin/include/ImFusion/Cranial/VesselSegmentationAlgorithm.h>

Algorithm for segmenting vessels in brain MR-T1C, ToF-MRA or CTA scans (from v4 onward). More...

Inheritance diagram for ImFusion::Cranial::VesselSegmentationAlgorithm:

Detailed Description

Algorithm for segmenting vessels in brain MR-T1C, ToF-MRA or CTA scans (from v4 onward).

Warning: when using a version lower or equal than 3, the algorithm is expected to only work properly on MR-T1C scans. Initial model predictions can be refined with 3 possible refinement algorithms (all 3 can be used at the same time):

  • Hessian refinement: Increases the amount of detection, useful when some small vessels are missing
  • Graph refinement: Visually smooth the predicted vessel tree by locally averaging estimated vessel diameters
  • Mesh refinement: Visually smooth the predicted vessel tree and remove small disconnected components Note: This algorithm is experimental.

Public Member Functions

 VesselSegmentationAlgorithm (SharedImageSet &input, AnatomicalStructureCollection *asc=nullptr)
 Constructor. If asc is not null, segmentation results will be written to it.
SharedImageSetinput () const
void setInputImage (SharedImageSet &newInput)
AnatomicalStructureCollectionasc () const
const SharedImageSetvesselMap () const
 Returns a non-owning pointer to the generated vessel map, or nullptr if the algorithm was not successful or if the output was already fetched via takeOutput().
Public Member Functions inherited from ImFusion::Algorithm
 Algorithm ()
 Default constructor will registers a single "compute" action that calls compute() and returns status().
virtual void setProgress (Progress *progress)
 Sets a Progress interface the algorithm can use to notify observers about its computing progress.
Progressprogress () const
 Returns the progress interface if set.
virtual int status () const
 Indicates the status of the last call to compute().
const FactoryInfofactoryInfo () const
 Returns the record describing how this Algorithm was instantiated by the AlgorithmFactory.
void setFactoryInfo (const FactoryInfo &value)
 Sets the record describing how this Algorithm was instantiated by the AlgorithmFactory.
Status runAction (const std::string &id)
 Run the action with name id if it exists.
const std::vector< Action > & actions ()
 Get a mapping from Action id to Action as registered in this algorithm.
Public Member Functions inherited from ImFusion::Configurable
virtual void configureDefaults ()
 Retrieve the properties of this object, replaces values with their defaults and sets it again.
void registerParameter (ParameterBase *param)
 Register the given Parameter or SubProperty, so that it will be configured during configure()/configuration().
void unregisterParameter (const ParameterBase *param)
 Remove the given Parameter or SubProperty from the list of registered parameters.
 Configurable (const Configurable &rhs)
 Configurable (Configurable &&rhs) noexcept
Configurable & operator= (const Configurable &)
Configurable & operator= (Configurable &&) noexcept
Public Member Functions inherited from ImFusion::SignalReceiver
 SignalReceiver ()=default
 Default constructor.
 SignalReceiver (const SignalReceiver &other)
 Copy constructor, does not copy any existing signal connections from other.
SignalReceiveroperator= (SignalReceiver rhs)
 Assignment operator, disconnects all existing connections, does not copy any existing signal connections from rhs.
virtual ~SignalReceiver ()
 Virtual destructor disconnects from all connected signals.

Public Attributes

Parameter< std::stringp_modelSet = {"modelSet", Models::Latest::ModelSetName, this}
 Model set for all models (vessel segmentation and internal sub-models).
Parameter< std::stringp_modelSetVersion = {"modelSetVersion", Models::Latest::ModelSetVersion, this}
 Model set version used for all models.
Parameter< bool > p_useBrainMask = {"useBrainMask", true, this}
 If enabled, performs a brain segmentation to remove detections outside the brain.
Parameter< bool > p_keepLargestComponent = {"keepLargestComponent", false, this}
 If enabled, removes all components but the largest one.
Parameter< bool > p_refinePredictions = {"refinePredictions", false, this}
 If enabled, exposes the individual refinement method toggles (Hessian / graph / mesh).
Parameter< bool > p_hessianRefinement = {"hessianRefinement", false, this}
 If enabled, augments the soft-probability map with multi-scale Hessian tubularity responses before binarisation, recovering small vessels missed by the model.
Parameter< std::vector< double > > p_hessianRefinementScales = {"hessianRefinementScales", std::vector<double>{1.}, this}
 If hessianRefinement enabled, specifies the scales (in mm) at which the Hessian refinement is performed.
Parameter< float > p_hessianRefinementThreshold = {"hessianRefinementThreshold", -2.5, this}
 If hessianRefinement is enabled, uses this threshold to detect additional vessels If at least 2 eigen values of the hessian are below that threshold, the structure is considered as tubular at the given location.
Parameter< float > p_vesselBinarizationThreshold = {"vesselBinarizationThreshold", 0.5f, this}
 Threshold applied to the continuous vessel probability map (p(fg) plus additive Hessian responses) to produce the binary segmentation.
Parameter< bool > p_graphRefinement = {"graphRefinement", false, this}
 If enabled, performs a round trip to and from graph centerline to smooth the predictions.
Parameter< bool > p_meshRefinement = {"meshRefinement", false, this}
 If enabled, performs a round trip to and from mesh with an intermediate mesh processing (cleaning) step.
Parameter< float > p_meshRefinementCleanThreshold = {"meshRefinementCleanThreshold", 5, this}
 If meshRefinement is enabled, defines the minimum connected component surface area (in mm^2) to be kept.
Public Attributes inherited from ImFusion::Algorithm
Signal signalOutputChanged
 Signal should be emitted by Algorithms when their output/result has changed.
Signal signalParametersChanged
 Signal should be emitted by Algorithms when their parameter configuration has changed.
Public Attributes inherited from ImFusion::Configurable
Signal signalParametersChanged
 Emitted whenever one of the registered Parameters' or SubPropertys' signalValueChanged signal was emitted.
void configure (const Properties *p) override
 Configure this object instance by de-serializing the given Properties.
void configuration (Properties *p) const override
 Serialize the current object configuration into the given Properties object.
void compute () override
 Execute the algorithm.
bool survivesDataDeletion (const Data *) const override
 Indicates whether the algorithm can handle (partial) deletion of the specified data, by default this checks whether the data is in the input list.
OwningDataList takeOutput () override
 Returns (1) the label map, (2) the AnatomicalStructureCollection if it has been created by the algorithm.
static bool createCompatible (const DataList &data, Algorithm **a=0)
 Standard methods for the Algorithm interface.

Additional Inherited Members

Public Types inherited from ImFusion::Algorithm
enum  Status {
  Unknown = -1 , Success = 0 , Error = 1 , InvalidInput ,
  IncompleteInput , OutOfMemoryHost , OutOfMemoryGPU , UnsupportedGPU ,
  UnknownAction , AbortedByUser , User = 1000
}
 Status codes. More...
Static Public Member Functions inherited from ImFusion::Algorithm
static bool createCompatible (const DataList &data, Algorithm **a=nullptr)
 Factory function to check algorithm compatibility with input data and optionally instantiate it.
Protected Member Functions inherited from ImFusion::Algorithm
void loadDefaults ()
void registerAction (const std::string &id, const std::string &guiName, const std::function< Algorithm::Status(void)> &action)
 Register an action to be run via runAction.
template<typename D>
void registerAction (const std::string &id, const std::string &guiName, Algorithm::Status(D::*action)(void))
 Template version of runAction that can be used with a pointer to a member function.
void registerAction (const Action &action)
 Register an action.
Protected Member Functions inherited from ImFusion::SignalReceiver
void disconnectAll ()
 Disconnects all existing connections.
Protected Attributes inherited from ImFusion::Algorithm
std::string m_name
 Algorithm name.
Progressm_progress = nullptr
 Non-owing pointer to a progress interface. May be a nullptr.
FactoryInfo m_factoryInfo = {}
 Record describing how this algorithm was instantiated by the AlgorithmFactory.
int m_status = Status::Unknown
 Algorithm status after last call to compute().
std::vector< Actionm_actions
 Map of key given by the id of the action, of the available actions of this algorithm.
Protected Attributes inherited from ImFusion::Configurable
std::vector< Paramm_params
 List of all registered Parameter and SubProperty instances.

Member Function Documentation

◆ configure()

void ImFusion::Cranial::VesselSegmentationAlgorithm::configure ( const Properties * p)
overridevirtual

Configure this object instance by de-serializing the given Properties.

The default implementation will do so automatically for all registered Parameter and SubProperty instances.

See also
configuration() for the inverse functionality

Reimplemented from ImFusion::Configurable.

◆ configuration()

void ImFusion::Cranial::VesselSegmentationAlgorithm::configuration ( Properties * p) const
overridevirtual

Serialize the current object configuration into the given Properties object.

The default implementation will do so automatically for all registered Parameter and SubProperty instances.

See also
configure() for the inverse functionality

Reimplemented from ImFusion::Configurable.

◆ compute()

void ImFusion::Cranial::VesselSegmentationAlgorithm::compute ( )
overridevirtual

Execute the algorithm.

Implements ImFusion::Algorithm.

◆ survivesDataDeletion()

bool ImFusion::Cranial::VesselSegmentationAlgorithm::survivesDataDeletion ( const Data * ) const
overridevirtual

Indicates whether the algorithm can handle (partial) deletion of the specified data, by default this checks whether the data is in the input list.

Reimplemented from ImFusion::Algorithm.

◆ takeOutput()

OwningDataList ImFusion::Cranial::VesselSegmentationAlgorithm::takeOutput ( )
overridevirtual

Returns (1) the label map, (2) the AnatomicalStructureCollection if it has been created by the algorithm.

Reimplemented from ImFusion::Algorithm.

Member Data Documentation

◆ p_modelSetVersion

Parameter<std::string> ImFusion::Cranial::VesselSegmentationAlgorithm::p_modelSetVersion = {"modelSetVersion", Models::Latest::ModelSetVersion, this}

Model set version used for all models.

Changing this resets any parameters defined in the selected version's metadata to their version-specific defaults.

◆ p_refinePredictions

Parameter<bool> ImFusion::Cranial::VesselSegmentationAlgorithm::p_refinePredictions = {"refinePredictions", false, this}

If enabled, exposes the individual refinement method toggles (Hessian / graph / mesh).

At least one refinement method must also be enabled for any refinement to take effect.

◆ p_vesselBinarizationThreshold

Parameter<float> ImFusion::Cranial::VesselSegmentationAlgorithm::p_vesselBinarizationThreshold = {"vesselBinarizationThreshold", 0.5f, this}

Threshold applied to the continuous vessel probability map (p(fg) plus additive Hessian responses) to produce the binary segmentation.

Lower values yield more liberal (oversegmented) results, which can be useful when erasing is easier than drawing vessels.


The documentation for this class was generated from the following file:
  • CranialPlugin/include/ImFusion/Cranial/VesselSegmentationAlgorithm.h
Search Tab / S to search, Esc to close