de.unihalle.informatik.MiToBo.apps.cells2D

Class CellBoundaryExtractor2D

java.lang.Object

de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.MiToBo.core.operator.MTBOperator

de.unihalle.informatik.MiToBo.apps.cells2D.CellBoundaryExtractor2D

All Implemented Interfaces:

de.unihalle.informatik.Alida.datatypes.ALDConfigurationValidator, de.unihalle.informatik.Alida.operator.events.ALDOperatorExecutionProgressEventListener, EventListener

@ALDAOperator(genericExecutionMode=ALL,
              level=APPLICATION,
              allowBatchMode=false)
public class CellBoundaryExtractor2D
extends MTBOperator

Operator for segmenting cell boundaries in microtubuli experiments.

This operator basically applies a vesselness filter to extract boundaries of cells in microtubuli experiments. As tubular and vessel-like structures not only appear along the cell boundaries the results require (manual) post-processing including gap closing, removing false detections, skeleton extraction and spine removal.

Author:

Birgit Moeller

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CellBoundaryExtractor2D.BorderBackgroundContrast Border color.
static class	CellBoundaryExtractor2D.OperationMode Operation mode of the operator.

Nested classes/interfaces inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.Alida.operator.ALDOperator.HidingMode, de.unihalle.informatik.Alida.operator.ALDOperator.HistoryConstructionMode

Field Summary

Fields

Modifier and Type	Field and Description
private MTBImageByte	binFilteredImg Intermediate result: binarized vesselness image after filtering.
private MTBImageByte	binVesselImg Intermediate result: binarized vesselness image.
CellBoundaryExtractor2D.BorderBackgroundContrast	borderContrast Border to background relation.
private int	boundaryChannel Channel of input image containing stained cell boundaries.
private MTBRegion2DSet	cellContours Set of extracted regions.
private MTBImage	cellLabelImg Label image of extracted cell regions.
private int	height Height of the input image.
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString	inDir Input directory where to find the images to process in batch mode.
private MTBImage	inImg Input grayscale image/stack to process.
private MTBImageByte	initialSkelImg Intermediate result: initial contour skeleton.
private int	maximalCellSize Threshold for the maximal admissible cell size.
private int	minimalCellSize Threshold for the minimal admissible cell size.
private static String	operatorID Identifier string for this operator class.
CellBoundaryExtractor2D.OperationMode	operatorMode Mode of operation of the operator.
private MTBImageByte	resultBinFilteredImg Filtered binary vesselness image.
private MTBImageByte	resultBinVesselImg Binarized vesselness image.
private MTBRegion2DSet	resultCellContours ROI set of detected cell regions.
private MTBImage	resultCellLabelImg Label image of detected cell regions.
private MTBImageByte	resultInitialSkeletonImg Initial skeleton image.
private MTBImageByte	resultSkelImg Skeleton image (of cell boundaries).
private MTBImageByte	resultVesselImg Result of applying the vesselness filter to the input image.
private boolean	showAdditionalResultImages Flag to enable/disable showing additional and intermediate result images.
private MTBImageByte	skelImg Intermediate result: final contour skeleton.
private MTBImageByte	vesselImg Intermediate result: vesselness image.
private int	width Width of the input image.

Fields inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

completeDAG, name, operatorExecutionEventlistenerList, portHashAccess, verbose, versionProvider

Constructor Summary

Constructors

Constructor and Description
CellBoundaryExtractor2D() Default constructor.

Method Summary

Modifier and Type	Method and Description
private MTBImageByte	applyVesselnessFilter(MTBImage img) Gaussian smoothing and vesselness enhancement filtering.
private MTBImageByte	closeGapsNativeLinks(MTBImageByte inSkelImg) Close gaps by native linkage.
private MTBImageByte	enhanceBoundaries(MTBImage img) Enhance cell boundaries by applying a vesselness enhancement filter.
static Vector<Point2D.Double>	findEndpoints(MTBImageByte img) Detect end-points in binary image.
protected void	operate()
private void	postProcessImage(MTBImage img) Post-process the vesselness filter result.
private void	processImage(MTBImage im) Main image analysis routine.
private void	switchOpModeParameters() Callback routine to change operator mode parameters.

Methods inherited from class de.unihalle.informatik.MiToBo.core.operator.MTBOperator

readResolve

Methods inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

addOperatorExecutionProgressEventListener, addParameter, addParameter, addParameterUnconditioned, fieldContained, fireOperatorExecutionProgressEvent, getALDPortHashAccessKey, getConstructionMode, getDocumentation, getHidingMode, getInactiveParameterNames, getInInoutNames, getInInoutNames, getInNames, getInOutNames, getMissingRequiredInputs, getName, getNumParameters, getOutInoutNames, getOutNames, getParameter, getParameterDescriptor, getParameterDescriptorUnconditioned, getParameterNames, getParameterUnconditioned, getSupplementalNames, getVerbose, getVersion, handleOperatorExecutionProgressEvent, hasInOutParameters, hasParameter, isAnnotatedParameter, isConfigured, print, print, print, printInterface, printInterface, readHistory, reinitializeParameterDescriptors, removeOperatorExecutionProgressEventListener, removeParameter, runOp, runOp, runOp, setConstructionMode, setConstructionMode, setConstructionMode, setHidingMode, setName, setParameter, setParameterUnconditioned, setVerbose, toStringVerbose, unconfiguredItems, validate, validateCustom, validateGeneric, writeHistory, writeHistory, writeHistory

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

operatorID

private static final String operatorID

Identifier string for this operator class.

See Also:

Constant Field Values

operatorMode

@Parameter(label="Operation Mode",
           required=true,
           direction=IN,
           dataIOOrder=-5,
           description="Operation mode of the operator.",
           callback="switchOpModeParameters",
           paramModificationMode=MODIFIES_INTERFACE)
public CellBoundaryExtractor2D.OperationMode operatorMode

Mode of operation of the operator.

inDir

@Parameter(label="Input Directory",
           required=true,
           direction=IN,
           description="Input directory.",
           dataIOOrder=-3)
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString inDir

Input directory where to find the images to process in batch mode.

inImg

@Parameter(label="Input Image",
           required=true,
           direction=IN,
           description="Input image.",
           dataIOOrder=-3)
private transient MTBImage inImg

Input grayscale image/stack to process.

boundaryChannel

@Parameter(label="Cell Boundary Channel",
           required=true,
           direction=IN,
           dataIOOrder=-2,
           description="Boundary Channel, e.g., 1, 2 and so on.")
private int boundaryChannel

Channel of input image containing stained cell boundaries.

borderContrast

@Parameter(label="Border Contrast",
           required=true,
           direction=IN,
           dataIOOrder=3,
           description="Contrast of cell boundaries wrt to background.")
public CellBoundaryExtractor2D.BorderBackgroundContrast borderContrast

Border to background relation.

minimalCellSize

@Parameter(label="Minimal Size of Cells",
           required=true,
           direction=IN,
           dataIOOrder=4,
           description="Cells smaller than this threshold are discarded.")
private int minimalCellSize

Threshold for the minimal admissible cell size.

Cell regions falling below this threshold are ignored.

maximalCellSize

@Parameter(label="Maximal Size of Cells",
           required=true,
           direction=IN,
           dataIOOrder=5,
           description="Cells larger than this threshold are discarded.")
private int maximalCellSize

Threshold for the maximal admissible cell size.

Cell regions lying above this threshold are ignored.

showAdditionalResultImages

@Parameter(label="Show/save additional results?",
           required=false,
           supplemental=true,
           direction=IN,
           dataIOOrder=-1,
           mode=STANDARD,
           description="Enable/disable showing/saving additional results.")
private boolean showAdditionalResultImages

Flag to enable/disable showing additional and intermediate result images.

resultCellLabelImg

@Parameter(label="Label Image of Detected Cell Regions",
           dataIOOrder=0,
           direction=OUT,
           description="Label image of detected cell regions.")
private transient MTBImage resultCellLabelImg

Label image of detected cell regions.

resultCellContours

@Parameter(label="Detected Cell Region Contours",
           dataIOOrder=1,
           direction=OUT,
           description="Cell region contours in ImageJ ROI format.")
private transient MTBRegion2DSet resultCellContours

ROI set of detected cell regions.

resultVesselImg

@Parameter(label="Vessels",
           dataIOOrder=2,
           direction=OUT,
           description="Result image of vesselness enhancement filter.")
private transient MTBImageByte resultVesselImg

Result of applying the vesselness filter to the input image.

resultBinVesselImg

@Parameter(label="Binarized Vesselness Image",
           dataIOOrder=4,
           direction=OUT,
           description="Binarized vesselness image.")
private transient MTBImageByte resultBinVesselImg

Binarized vesselness image.

resultBinFilteredImg

@Parameter(label="Filtered Binary Vesselness Image",
           dataIOOrder=5,
           direction=OUT,
           description="Filtered binary vesselness image.")
private transient MTBImageByte resultBinFilteredImg

Filtered binary vesselness image.

resultInitialSkeletonImg

@Parameter(label="Initial skeleton image before post-processing.",
           dataIOOrder=6,
           direction=OUT,
           description="Initial skeleton image.")
private transient MTBImageByte resultInitialSkeletonImg

Initial skeleton image.

resultSkelImg

@Parameter(label="Skeleton Image",
           dataIOOrder=7,
           direction=OUT,
           description="Skeleton image.")
private transient MTBImageByte resultSkelImg

Skeleton image (of cell boundaries).

width

private transient int width

Width of the input image.

height

private transient int height

Height of the input image.

cellLabelImg

private transient MTBImage cellLabelImg

Label image of extracted cell regions.

cellContours

private transient MTBRegion2DSet cellContours

Set of extracted regions.

vesselImg

private transient MTBImageByte vesselImg

Intermediate result: vesselness image.

binVesselImg

private transient MTBImageByte binVesselImg

Intermediate result: binarized vesselness image.

binFilteredImg

private transient MTBImageByte binFilteredImg

Intermediate result: binarized vesselness image after filtering.

initialSkelImg

private transient MTBImageByte initialSkelImg

Intermediate result: initial contour skeleton.

skelImg

private transient MTBImageByte skelImg

Intermediate result: final contour skeleton.

Constructor Detail

CellBoundaryExtractor2D

public CellBoundaryExtractor2D()
                        throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Default constructor.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException - Thrown if construction fails.

Method Detail

switchOpModeParameters

private void switchOpModeParameters()

Callback routine to change operator mode parameters.

operate

protected void operate()
                throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                       de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Specified by:

operate in class de.unihalle.informatik.Alida.operator.ALDOperator

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

processImage

private void processImage(MTBImage im)
                   throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                          de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Main image analysis routine.

Parameters:

im - Image (stack) to process.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException - Thrown in case of failure.

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException - Thrown in case of failure.

enhanceBoundaries

private MTBImageByte enhanceBoundaries(MTBImage img)
                                throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                                       de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Enhance cell boundaries by applying a vesselness enhancement filter.

Parameters:

img - Input grayscale image to process.

Returns:

Gray-scale image with region boundaries enhanced.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException - Thrown in case of failure.

de.unihalle.informatik.Alida.exceptions.ALDOperatorException - Thrown in case of failure.

applyVesselnessFilter

private MTBImageByte applyVesselnessFilter(MTBImage img)
                                    throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                                           de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Gaussian smoothing and vesselness enhancement filtering.

Parameters:

img - Image to process.

Returns:

Filtered image.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException - Thrown in case of processing failure.

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException - Thrown in case of problems with processing history.

postProcessImage

private void postProcessImage(MTBImage img)
                       throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                              de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Post-process the vesselness filter result.

Parameters:

img - Image to process.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException - Thrown in case of failure.

de.unihalle.informatik.Alida.exceptions.ALDOperatorException - Thrown in case of failure.

closeGapsNativeLinks

private MTBImageByte closeGapsNativeLinks(MTBImageByte inSkelImg)

Close gaps by native linkage.

Parameters:

inSkelImg - Skeleton image.

Returns:

Skeleton image with closed gaps.

findEndpoints

public static Vector<Point2D.Double> findEndpoints(MTBImageByte img)

Detect end-points in binary image.

Parameters:

img - Input image.

Returns:

Set of end-points.