#include <ImFusion/US/UltrasoundConeCalibrationAlgorithm.h>

Algorithm that automatically computes ultrasound calibration using two or more ultrasound sweeps covering a cone phantom. More...

Inheritance diagram for ImFusion::US::UltrasoundConeCalibrationAlgorithm:

Detailed Description

Algorithm that automatically computes ultrasound calibration using two or more ultrasound sweeps covering a cone phantom.

The sweeps must be taken with a "Cone Phantom" as described in the paper "PRO-TIP: Phantom for RObust automatic ultrasound calibration by TIP detection" (Ronchetti et al. 2022).

The algorithm proceeds in the following steps:

Cone Segmentation: For each sweep, the cones are segmented in each frame using a machine learning model.
Cone Tracking: Detected cones are tracked across frames to form cone tracks. Stored using TrackedCone.
Tip Detection: For each tracked cone, the tip (highest point) is identified using a smoothed height profile.
Tip Matching: Detected tips are matched between sweeps based on their height, forming candidate correspondences.
Calibration Estimation: RANSAC is used to robustly estimate the calibration matrix from the matched tips, rejecting outliers.
Image-based Refinement: The calibration is refined using image-based optimization to maximize similarity between sweeps.
See also
UltrasoundCalibration

Classes
class	TrackedCone
	Represents a cone detected in an ultrasound sweep across multiple frames. More...
struct	Tip
	Represents a detected cone tip. More...
struct	EstimatedCalibration
	Represents an estimated calibration result. More...
struct	Fiducials
	Represents fiducial points used for calibration. More...
struct	Matches
	Represents matches between cone tips from different sweeps. More...

Public Member Functions
	UltrasoundConeCalibrationAlgorithm (std::vector< UltrasoundSweep * > sweeps)
void	compute () override
	Execute the algorithm.
mat4	originalCalibration () const
	Returns the original calibration matrix.
int	detectTips (int sweepIndex)
	Detects cone tips in a given sweep.
std::vector< TrackedCone >	detectCones (SharedImageSet *segmentation, int sweepIndex)
	Given a segmentation, detects cones and merges the detections into tracks.
bool	setSegmentations (std::vector< SharedImageSet * > segmentations)
	Sets segmentations to be used instead of the ones produced by the ML model.
Public Member Functions inherited from ImFusion::Algorithm
	Algorithm ()
	Default constructor will registers a single "compute" action that calls compute() and returns status().
virtual OwningDataList	takeOutput ()
	Return any new Data that was created by the Algorithm during the last call to compute().
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	configure (const Properties *p)
	Configure this object instance by de-serializing the given Properties.
virtual void	configuration (Properties *p) const
	Serialize the current object configuration into the given Properties object.
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=nullptr)
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.

Public Attributes
std::vector< Tip >	m_tips
	Detected tips from ultrasound sweeps.
std::vector< TrackedCone >	m_cones
	Tracked cones detected across multiple frames.
std::vector< EstimatedCalibration >	m_calibrations
	Calibrations estimated by RANSAC.
Matches	m_matches
	Matches between cone tips from different sweeps.
std::unordered_map< std::string, std::unordered_map< std::string, Fiducials > >	m_fiducials
Parameter< std::string >	p_modelPath = {"modelPath", "Models/ConesCalibration.yaml", *this}
	Path to the ML model.
Parameter< double >	p_phantomScale = {"phantomScale", 1.0, *this}
	Relative scale of the physical phantom compared the default model.
Parameter< double >	p_heightEps = {"heightEps", 3.0, *this}
	Maximum height difference for matching tips in mm.
Parameter< int >	p_imageFrames = {"imageFrames", 30, *this}
	Number of frames used for image-based refinement.
Parameter< int >	p_imageBasedRepeats = {"imageBasedRepeats", 2, *this}
	Number of times the image-based refinement is repeated.
Parameter< int >	p_smoothing = {"smoothing", 5, *this}
	Smoothing parameter for tip detection.
Parameter< int >	p_minFrames = {"minFrames", 10, *this}
	Minimum number of frames for accepting a cone track.
Parameter< double >	p_eps = {"eps", 10.0, *this}
	RANSAC epsilon parameter.
Parameter< int >	p_ransacIterations = {"ransacIterations", 50000, *this}
	Number of RANSAC iterations.
Parameter< int >	p_ransacKeepBest = {"ransacKeepBest", 5, *this}
	Number of best candidates to keep in RANSAC.
Parameter< double >	p_optimizationThreshold = {"optimizationThreshold", 10, *this}
	Threshold for early discard in RANSAC.
Parameter< bool >	p_debugMode = {"debugMode", false, *this}
	Debug mode flag.
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.

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...
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 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.

Member Function Documentation

◆ compute()

void ImFusion::US::UltrasoundConeCalibrationAlgorithm::compute ( )

overridevirtual

Execute the algorithm.

Implements ImFusion::Algorithm.

◆ detectTips()

int ImFusion::US::UltrasoundConeCalibrationAlgorithm::detectTips ( int sweepIndex )

Detects cone tips in a given sweep.

Parameters

sweepIndex Index of the sweep.

Returns: Number of detected tips.

◆ detectCones()

std::vector< TrackedCone > ImFusion::US::UltrasoundConeCalibrationAlgorithm::detectCones	(	SharedImageSet *	segmentation,
		int	sweepIndex )

Given a segmentation, detects cones and merges the detections into tracks.

Parameters

segmentation	Segmentation image set.
sweepIndex	Index of the sweep.

Returns: List of detected cones.

◆ setSegmentations()

bool ImFusion::US::UltrasoundConeCalibrationAlgorithm::setSegmentations ( std::vector< SharedImageSet * > segmentations )

Sets segmentations to be used instead of the ones produced by the ML model.

Parameters

segmentations List of segmentations.

Returns: True if compatible, false otherwise.

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

ImFusion/US/UltrasoundConeCalibrationAlgorithm.h

Detailed Description

Classes

Public Member Functions

Static Public Member Functions

Public Attributes

Additional Inherited Members

Member Function Documentation

◆ compute()

◆ detectTips()

◆ detectCones()

◆ setSegmentations()