USE

1
USE

• Xinwei Xue
• 11/07/02
• SCI Institute

2
OUTLINE

• Overview
• Software Architecture
• Major Functionalities
• Applications
• Write your applications
• Download Compile

3
What is ITK

• C Library for Medical Image Segmentation
  Registration
• Open Source
• Cross Platform Linux, Irix, Windows, Sun, etc.
• Wrapped with Interpreted Languages
• e.g. Tcl, Python, Java, etc.

4
Goals

• Support the Visible Human Project.
• Establish a foundation for future research.
• Create a repository of fundamental algorithms.
• Develop a platform for advanced product
  development.
• Create conventions for future work.
• Grow a self-sustaining community of software
  users and developers.

5
ITK Architecture

• Data Flow Architecture
• Update Request Triggers Processing

Application
Data Storage
Update
Source
Process Object
Process Object
Sink
Data Object
Data Object
Data Object
6
Architectural Features

• Reference counting (smart pointers)
• Object Factory (plug-in support)
• ObjectTypePointer myObject
  ObjectTypeNew()
• Event callbacks (command/observer)
• Portable multi-threading
• GenerateData()
• ThreadedGenerateData()

7
Architectural Features

• Generic Programming
• Compile-time oriented
• Employs C Templates
• Iterators
• Image Iterators
• Neighborhood Iterators
• Slice Iterators
• Concept of Regions
• Typedef

Largest Possible Region
Buffered Region
Requested Region
8
Major Funcationalities

• Segmentation
• Registration
• PDE Solver
• Image Enhancement
• Feature Detection
• Image Transformations
• Other

9
Segmentation Tools

• Similarity-Based Segmentation
• Statistical Pattern Classification
• Supervised (Gaussian)
  and Unsupervised (Kmeans)
• Fuzzy Connectedness
• Region-Based Segmentation
• Watersheds
• Voronoi
• Model-Based Segmentation
• Level-set Based Segmentation
  Threshold, Laplacian
• Deformable Mesh
• Balloon Force
• Hybrid Segmentation
• Fuzzy connectedness voronoi

10
Registration Tools

MultiResolutionRegistrationFramework
ImageRegistrationFramework
PDEBasedRegistration
FEMBasedRegistration
11
Components
Registration Method
FixedImage
MovingImage
12
Components

• Optimizers
• Gradient Descent
• Regular Step Gradient Descent
• Conjugate Gradient
• Levenberg-Marquardt

• Metrics
• Mutual Information
• Mean Squares
• Normalized Correlation
• Pattern Intensity

• Transform
• Translation
• Scale
• Rotation
• Rigid3D
• Rigid2D
• Affine
• Splines TPS, EBS, VS

• Interpolators
• Nearest neighbor
• Linear
• BSpline

13

PDE Solver Framework
Finite Difference Function
Finite Difference Solver

Level Set
Sparse
Dense
Diffusion
Narrow Band
Segment.
Aniso. Diff
Diffusion
Curv. Limited
Other Functions
Other Solvers
14
PDE Filter Structure

Solver Object
Input Image
Output Image (Filtered)
Function Object
Parameters
15
Image Enhancement
Morphology Filter
Gaussian Filters
Erode/Dilate Filters
Image Enhancemnet
Anisotropic Diffusion
Binary Filters
Curvature Diffusion
Other Filters
Curvature MinMax Flow
16
Low Level Feature Detection
Sobel Edge Detection

Gradient
Thresholding
Feature Detection
Laplacian
Canny Edges
Zero- Crossing
Other Filters
Laplacian of Gaussian
17
ITK Applications
18
Watershed Segmentation
19
Interactive Segmentation
20
Multi Field MRI Results
21
Start Using ITK

• Image Class
• Related to Image Class
• Region, Size, Index, etc.
• ImageToImageFilterlt TInputImage, TOutputImagegt
• Image Region Iterator
• Neighborhood Neighborhood Iterators
• NeighborhoodIterator
  SmartNeighborhoodIterator
• RandomAccessNeighhoodIterator
• Neighborhood Operators
• DerivativeOperator, GaussisnOperator,
  LaplacianOperator, etc.
• Image IO PNG, Raw,VOL,VTK, Dicom, Meta formate
  supported

22

Neighborhood

• Templeted over neighorhood radius, image, and
  image region to be processed.

1
0
2
Radius 1
4
3
5
7
6
8
7
6
8
4
3
5
1
0
2
23
Image Declaration Allocation

• typedef itkImageltfloat, 2gt ImageType
• typedef typename ImageTypeRegionType
  RegionType
• typedef typename ImageTypeSizeType
  SizeType
• typedef typename ImageTypeIndexType
  IndexType
• //Creates an image pointer
• ImageTypePointer image
• //Allocating memory for a image
• RegionType region
• SizeType size
• IndexType index
• size0 256 size1 256
• index0 0 index1 0
• region.SetSize(size)
• region.SetIndex(index)
• image-gtSetRegions(region)
• image-gtAllocate( )

24
Neighhood Iterators Example

• itkNeighborhoodInnerProductltImageTypegt IP
• itkDerivativeOperatorltImageTypegt operator
• operator-gtSetOrder(1)
• operator-gtSetDirection(0)
• operator-gtCreateDirectional()
• itkNeighborhoodIteratorltImageTypegt
  iterator(operator-gtGetRadius(), myImage,
  myImage-gtGetRequestedRegion())
• iterator.SetToBegin()
• while ( ! iterator.IsAtEnd() )
• stdcout ltlt "Derivative at index " ltlt
  iterator.GetIndex() ltlt is ltlt IP(iterator,
  operator) ltlt stdendl
• iterator

25
Sample Code Fragment For Read/Write

• typedef itkImageltunsigned int, 3gt
  ImageType
• typedef itkImageFileReaderlt ImageType gt
  FileSourceType
• typedef itkPNGImageIO
  PNGReaderType
• typedef itkImageFileWriterlt ImageType gt
  FileSinkType
• typedef itkPNGImageIO
  PNGWriterType
• //read
• FileSourceTypePointer fileSource
  FileSourceTypeNew()
• fileSource-gtSetFileName( inputFileName )
• PNGReaderTypePointer pngReader
  PNGReaderTypeNew()
• pngReader-gtSetNumberOfDimensions( 3 )
• fileSource-gtSetImageIO( pngReader )
• //write
• FileSinkTypePointer fileSink
  FileSinkTypeNew()
• PNGWriterTypePointer pngWriter
  PNGWriterTypeNew()
• fileSink-gtSetImageIO( pngWriter )
• fileSink-gtSetFilePrefix( outputFileName )
• fileSink-gtSetInput( fileSource-gtGetOutput() )
• fileSink-gtUpdate( )

26
Calling An Image Filter
include "itkImage.h" include "itkImageFileReader
.h" include "itkGradientMagnitudeImageFilter.h"
int main( int argc, char argv ) typedef
itkImageltunsigned short,2gt ImageType
typedef itkImageFileReaderltImageTypegt
ReaderType typedef itkGradientMagnitudeImageF
ilterlt ImageType,
ImageTypegt FilterType typedef
itkPNGImageIO PNGReaderType
PNGReaderTypePointer pngReader
PNGReaderTypeNew() ReaderTypePointer
reader ReaderTypeNew() FilterTypePointer
filter FilterTypeNew() reader-gtSetFileName(
argv1 ) reader-gtSetImageIO(
filter-gtSetInput( reader-gtGetOutput() )
filter-gtUpdate() return 0

27
Get ITK
Depending your building options, you may need
other tools to do a complete build.
28
Configure Compile ITK

• mkdir build
• cd build
• ccmake ../Insight
• Make
• See http//www.itk.org/HTML/BuildOptions.htm
• For More Building Options.

29
Configure ITK
30
(No Transcript)
31
(No Transcript)
32
Writing myProject.cxx
include "itkImage.h" include "itkImageFileReader
.h" include "itkGradientMagnitudeImageFilter.h"
int main( int argc, char argv ) typedef
itkImageltunsigned short,2gt ImageType
typedef itkImageFileReaderltImageTypegt
ReaderType typedef itkGradientMagnitudeImageF
ilterlt ImageType,ImageTypegt
FilterType typedef itkPNGImageIO
PNGReaderType
PNGReaderTypePointer pngReader
PNGReaderTypeNew() ReaderTypePointer
reader ReaderTypeNew() FilterTypePointer
filter FilterTypeNew()
reader-gtSetFileName( argv1 )
reader-gtSetImageIO( filter-gtSetInput(
reader-gtGetOutput() ) filter-gtUpdate()
return 0
33
Meet Problems?

• Join the ITK users email list
• http//www.itk.org/HTML/MailingLists.htm
• Very Helpful!!!

34
Reference

• www.itk.org
• Presentations of ITK Meetings

35

• Thank you!