Package gov.nih.mipav.model.algorithms

Class AlgorithmCellTrackingAGVF

java.lang.Object

java.lang.Thread

gov.nih.mipav.model.algorithms.AlgorithmBase

gov.nih.mipav.model.algorithms.AlgorithmAGVF

gov.nih.mipav.model.algorithms.AlgorithmCellTrackingAGVF

All Implemented Interfaces:

AlgorithmInterface, ActionListener, WindowListener, Runnable, EventListener

public class AlgorithmCellTrackingAGVF
extends AlgorithmAGVF

Active Contour class optimized for Cell Tacking, based on the following paper:

"Active Contours for Cell Tracking", by Nilanjan Ray and Scott T. Acton. 5th IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI'02), 2002.

Most functionality is inherited from AlgorithmAGVF, the runSnake function is optimized with the following constraints for cell-tracking:

1). Constrained Gradient Vector Flow: using a Dirichlet boundary condition, the gradient inside the initial user-defined snake is set to a user-defined velocity vector.

2). Shape-size constraint: the shape and size of the snake is constrained to be circular with a user-defined cell radius.

3). Implicit Resampling: the points along the snake curve are minimized such that they maintain an equal distance between points.

The gradient vector flow is calculated for each frame in the image sequence. Once the GVF is calculated, the points inside the initial snake (either the user-defined snake for frame 0, or the snake for the previous frame) are set to the velocity vector. runSnake then minimizes the shape-size and resampling constraints for the new GVF, based on the user-defined constraint contributions (see the Lambda member variable). The output snake is used as the initial guess for the next frame in the image sequence.

See Also:

• AlgorithmAGVF
• GenerateGaussian

Nested Class Summary

Nested classes/interfaces inherited from class java.lang.Thread

Thread.Builder, Thread.State, Thread.UncaughtExceptionHandler

Field Summary

Fields

Modifier and Type	Field	Description
private float[]	m_afX	Previous snake results (X-position):.
private float[]	m_afY	Previous snake results (Y-position):.
private boolean	m_bDilate	whether or not to dilate the cell contour before solving for the cell on the next frame (dilation helps capture cells that are moving fast).
private boolean	m_bUseVelocity	boolean when true, use the velocity vector:.
private float	m_fDilationFactor	Amount to dilate the cell (multiple of the cell radius).
private float	m_fK	expected cell radius:.
private float	m_fLambda1	Constraint factor for the cell shape:.
private float	m_fLambda2	Constraint factor for the cell size:.
private float	m_fLambda3	Constraint factor for sampling:.
private float	m_fTolerance	tolerance factor for snake evolution:.
private Jama.Matrix	m_kC	Cos matrix: = cos( 2*pi*i/n).
private Jama.Matrix	m_kG	G Matrix, equation 19:.
private Jama.Matrix	m_kH	H Matrix, equation 19:.
private Polygon	m_kPreviousSnake	Previous snake polygon:.
private Jama.Matrix	m_kQ	Q Matrix, equation 24 (inverse calculated once per image sequence on the inital frame):.
private Jama.Matrix	m_kS	Sin matrix: = sin( 2*pi*i/n).
private WildMagic.LibFoundation.Mathematics.Vector2f	m_kVelocity	Velocity vector (either the initial user-defined guess, or the calculated velocity (new snake center - previous snake center):.

Fields inherited from class gov.nih.mipav.model.algorithms.AlgorithmAGVF

boundaryIterations, extents, xDim, yDim, zDim

Fields inherited from class gov.nih.mipav.model.algorithms.AlgorithmBase

destFlag, destImage, image25D, mask, maxProgressValue, minProgressValue, multiThreadingEnabled, nthreads, progress, progressModulus, progressStep, runningInSeparateThread, separable, srcImage, threadStopped

Fields inherited from class java.lang.Thread

MAX_PRIORITY, MIN_PRIORITY, NORM_PRIORITY

Constructor Summary

Constructors

Constructor	Description
AlgorithmCellTrackingAGVF(ModelImage resultImage, ModelImage srcImg, float[] sigmas, int gvfIterations, int boundaryIterations, float k, float smoothness, VOI srcVOI, boolean do25D, float radiusConstraint, float shapeConstraint, float sizeConstraint, float resamplingConstraint, boolean bDilate, float fDilation, float fDx, float fDy)	Creates a new AlgorithmCellTrackingAGVF object.

Method Summary

Modifier and Type	Method	Description
void	finalize()	Prepares this class for destruction.
private void	initSnakeConstants(int iNPoints)	Initializes the H, G, and Q matrices once per image sequence on the first frame.
protected void	runSnake(float[] xPoints, float[] yPoints, float[] u, float[] v, Polygon resultGon)	Actual function that evolves the boundary.

Methods inherited from class gov.nih.mipav.model.algorithms.AlgorithmAGVF

algorithmPerformed, cleanLine, cleanup, getBilinear, getResultVOI, runAlgorithm, runSnake, setPropagation

Methods inherited from class gov.nih.mipav.model.algorithms.AlgorithmBase

actionPerformed, addListener, addProgressChangeListener, calculateImageSize, calculatePrincipleAxis, computeElapsedTime, computeElapsedTime, convertIntoFloat, delinkProgressToAlgorithm, delinkProgressToAlgorithmMulti, displayError, errorCleanUp, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, generateProgressValues, getDestImage, getElapsedTime, getMask, getMaxProgressValue, getMinProgressValue, getNumberOfThreads, getProgress, getProgressChangeListener, getProgressChangeListeners, getProgressModulus, getProgressStep, getProgressValues, getSrcImage, isCompleted, isImage25D, isMultiThreadingEnabled, isRunningInSeparateThread, isThreadStopped, linkProgressToAlgorithm, linkProgressToAlgorithm, makeProgress, notifyListeners, removeListener, removeProgressChangeListener, run, setCompleted, setImage25D, setMask, setMaxProgressValue, setMinProgressValue, setMultiThreadingEnabled, setNumberOfThreads, setProgress, setProgressModulus, setProgressStep, setProgressValues, setProgressValues, setRunningInSeparateThread, setSrcImage, setStartTime, setThreadStopped, startMethod, windowActivated, windowClosed, windowClosing, windowDeactivated, windowDeiconified, windowIconified, windowOpened

Methods inherited from class java.lang.Thread

activeCount, checkAccess, clone, countStackFrames, currentThread, dumpStack, enumerate, getAllStackTraces, getContextClassLoader, getDefaultUncaughtExceptionHandler, getId, getName, getPriority, getStackTrace, getState, getThreadGroup, getUncaughtExceptionHandler, holdsLock, interrupt, interrupted, isAlive, isDaemon, isInterrupted, isVirtual, join, join, join, join, ofPlatform, ofVirtual, onSpinWait, resume, setContextClassLoader, setDaemon, setDefaultUncaughtExceptionHandler, setName, setPriority, setUncaughtExceptionHandler, sleep, sleep, sleep, start, startVirtualThread, stop, suspend, threadId, toString, yield

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Details

m_afX

private float[] m_afX

Previous snake results (X-position):.

m_afY

private float[] m_afY

Previous snake results (Y-position):.

m_bDilate

private boolean m_bDilate

whether or not to dilate the cell contour before solving for the cell on the next frame (dilation helps capture cells that are moving fast).

m_bUseVelocity

private boolean m_bUseVelocity

boolean when true, use the velocity vector:.

m_fDilationFactor

private float m_fDilationFactor

Amount to dilate the cell (multiple of the cell radius).

m_fK

private float m_fK

expected cell radius:.

m_fLambda1

private float m_fLambda1

Constraint factor for the cell shape:.

m_fLambda2

private float m_fLambda2

Constraint factor for the cell size:.

m_fLambda3

private float m_fLambda3

Constraint factor for sampling:.

m_fTolerance

private float m_fTolerance

tolerance factor for snake evolution:.

m_kC

private Jama.Matrix m_kC

Cos matrix: = cos( 2*pi*i/n).

m_kG

private Jama.Matrix m_kG

G Matrix, equation 19:.

m_kH

private Jama.Matrix m_kH

H Matrix, equation 19:.

m_kPreviousSnake

private Polygon m_kPreviousSnake

Previous snake polygon:.

m_kQ

private Jama.Matrix m_kQ

Q Matrix, equation 24 (inverse calculated once per image sequence on the inital frame):.

m_kS

private Jama.Matrix m_kS

Sin matrix: = sin( 2*pi*i/n).

m_kVelocity

private WildMagic.LibFoundation.Mathematics.Vector2f m_kVelocity

Velocity vector (either the initial user-defined guess, or the calculated velocity (new snake center - previous snake center):.

Constructor Details

AlgorithmCellTrackingAGVF

public AlgorithmCellTrackingAGVF(ModelImage resultImage,
 ModelImage srcImg,
 float[] sigmas,
 int gvfIterations,
 int boundaryIterations,
 float k,
 float smoothness,
 VOI srcVOI,
 boolean do25D,
 float radiusConstraint,
 float shapeConstraint,
 float sizeConstraint,
 float resamplingConstraint,
 boolean bDilate,
 float fDilation,
 float fDx,
 float fDy)

Creates a new AlgorithmCellTrackingAGVF object.

Parameters:

resultImage - image of GVF field magnitude

srcImg - 2D or 3D source image

sigmas - describe the scale of the gaussian in each dimension

gvfIterations - iterations in calculating GVF field

boundaryIterations - iterations in calculating boundary

k - GVF constant

smoothness - factor for smoothing points on contour (see AlgorithmAGVF)

srcVOI - VOI that is to be evolved

do25D - only applies to 3D, if true do slice by slice

radiusConstraint - The user-defined cell radius

shapeConstraint - The contribution of the shape constraint in the minimization

sizeConstraint - The contribution of the size constraint in the minimization

resamplingConstraint - The contribution of the resampling constraint in the minimization

bDilate - Whether to dilate the cell radius before optimizing

fDilation - dilation factor (multiple of the cell radius)

fDx - The initial cell velocity (x-component)

fDy - The initial cell velocity (y-component)

Method Details

finalize

public void finalize()

Prepares this class for destruction.

Overrides:

finalize in class AlgorithmAGVF

runSnake

protected void runSnake(float[] xPoints,
 float[] yPoints,
 float[] u,
 float[] v,
 Polygon resultGon)

Actual function that evolves the boundary.

Overrides:

runSnake in class AlgorithmAGVF

Parameters:

xPoints - x coordinates that describe the contour

yPoints - y coordinates that describe the contour

u - x component of the GVF

v - y component of the GVF

resultGon - resultant polygon

initSnakeConstants

private void initSnakeConstants(int iNPoints)

Initializes the H, G, and Q matrices once per image sequence on the first frame. The matrix inverse only has to be computed once.

Parameters:

iNPoints - the number of points in the initial VOI (snake)