#include <ImFusion/US/BoneSegmentationBaseAlgorithm.h>

Performs bone segmentation on ultrasound images using a machine learning model. More...

Inheritance diagram for ImFusion::US::BoneSegmentationBaseAlgorithm:

Detailed Description

Performs bone segmentation on ultrasound images using a machine learning model.

This class provides a concrete implementation of a segmentation pipeline tailored to bone detection in ultrasound images. It integrates machine learning predictions, detection via connected component analysis, and tracking using intensity/gradient-based scanline evaluation.

The algorithm can optionally compare its predictions to labeled ground truth data, computing confidence scores, precision, and recall. It also supports writing detailed evaluation metrics to a configurable statistics file.

A wide range of parameters can be adjusted via the Properties interface, including the model path, segmentation thresholds, smoothing factors, scanline step, and margin widths. These settings allow the algorithm to be adapted to varying image characteristics and use cases.

Additionally, a custom path to the prediction model can be set via the Properties interface.

While the class includes a legacyDetection() method with an empty implementation intended for extension in derived classes, it is not declared as a pure virtual function. Therefore, the class remains fully instantiable and is not abstract.

Note: This is the base class for BoneSegmentationAlgorithm.

Classes
struct	PredictionMap
struct	DetectionResult

Public Member Functions
	BoneSegmentationBaseAlgorithm (SharedImageSet images, SharedImageSet labels=nullptr)
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.
OwningDataList	takeOutput () override
	Return any new Data that was created by the Algorithm during the last call to compute().
virtual bool	useDefaultAlgorithmController () const
	If you need to use a different controller in a derived class, set this to false.
virtual void	init ()
	Initialize the algorithm.
virtual void	reset ()
	Clears current output.
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.
Progress *	progress () const
	Returns the progress interface if set.
virtual int	status () const
	Indicates the status of the last call to compute().
virtual bool	survivesDataDeletion (const Data *) const
	Indicates whether the algorithm can handle (partial) deletion of the specified data, by default this checks whether the data is in the input list.
const FactoryInfo &	factoryInfo () 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

Static Public Member Functions
static bool	createCompatible (const DataList &data, Algorithm **a=0)
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
virtual void	updatePrediction ()
	Update prediction using current features.
virtual void	detection ()
	Run detection using ML prediction.
virtual void	legacyDetection ()
	Run legacy algorithm for bone detection.
virtual void	tracking ()
	Run tracking using last detection.
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 Attributes
SharedImage *	m_curImage
std::unique_ptr< SharedImageSet >	m_outImages
std::unique_ptr< ImageResamplingAlgorithm >	m_resamplingAlgo
std::string	m_statsFile
Protected Attributes inherited from ImFusion::Algorithm
std::string	m_name
	Algorithm name.
Progress *	m_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< Action >	m_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< Param >	m_params
	List of all registered Parameter and SubProperty instances.

Input
SharedImageSet *	m_images
SharedImageSet *	m_labels

Results
std::shared_ptr< SharedImage >	m_probabilityMap
	Probability map.
std::vector< vec3 >	m_detectedBone
	Detection result.
std::vector< vec3 >	m_segmentedBone
	Segmentation result.
float	m_curConfidenceScore
std::vector< double >	m_curBoneClassification

General Parameters
bool	m_useLegacyAlgorithm
	Use previous algorithm.
double	m_workingResolution
	Spacing for the working images.
int	m_frameStep
	Step between predicted frames.
int	m_nbSplinePoints
	Number of control points in the final spline.

Parameters for automatic detection
std::string	m_predictionModelPath
std::unique_ptr< ML::MachineLearningModel >	m_predictionModel
float	m_detectionProbabilityThreshold
	Threshold on random forest probability for detection heuristic.
float	m_detectionDepthPenalization

Parameters for automatic segmentation
double	m_marginAroundDetection
	Margin around detection for the mask in mm.
double	m_maskSmoothingScale
	Scale for the laplacian in mm.
double	m_marginAroundPrevious
	Margin around previous segmentation for the mask in mm.
float	m_segmentationThreshold
	Threshold for segmentation extraction.
float	m_segmentationGradientFactor
double	m_segmentationOffset
int	m_segmentationSmoothHalfSize
float	m_removeSidePercent
	Total percent of the points to be removed from the sides of each bone (0 1).
double	m_qualityThreshold
	Frames having lower tracking quality than this threshold are ignored.
bool	m_medianQualityThreshold
	If true, median tracking quality of all frames is used as the threshold.

Methods for getting members or results
const std::vector< vec3 > &	detectedBone () const
const std::vector< vec3 > &	segmentedBone () const
float	confidenceScore () const
PredictionMap	computePredictionMap (const SharedImage &curImage) const
DetectionResult	computeDetectedBone (const SharedImage &probabilityMap) const
std::vector< vec3 >	computeSegmentedBone (const SharedImage &curImage, const std::vector< vec3 > &detectedBone) const

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...
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.

Member Function Documentation

◆ configure()

void ImFusion::US::BoneSegmentationBaseAlgorithm::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::US::BoneSegmentationBaseAlgorithm::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::US::BoneSegmentationBaseAlgorithm::compute ( )

overridevirtual

Execute the algorithm.

Implements ImFusion::Algorithm.

◆ takeOutput()

OwningDataList ImFusion::US::BoneSegmentationBaseAlgorithm::takeOutput ( )

overridevirtual

Return any new Data that was created by the Algorithm during the last call to compute().

The default implementation will return an empty list.

Note: Since ownership of the data is transferred, you can call this method only once between calls to compute().

Reimplemented from ImFusion::Algorithm.

◆ init()

virtual void ImFusion::US::BoneSegmentationBaseAlgorithm::init ( )

virtual

Initialize the algorithm.

Load the machine learning model from the configured path, if it has not been loaded previously. If loading fails, a message will be logged.

Reimplemented in ImFusion::US::BoneSegmentationAlgorithm.

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

ImFusion/US/BoneSegmentationBaseAlgorithm.h

Detailed Description

Classes

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Input

Results

General Parameters

Parameters for automatic detection

Parameters for automatic segmentation

Methods for getting members or results

Additional Inherited Members

Member Function Documentation

◆ configure()

◆ configuration()

◆ compute()

◆ takeOutput()

◆ init()