Using ManagedITK with C

1
Using ManagedITK with C(.Net)

• Reporter ???

2
What is ITK

• National Library of Medicine(?????????) Insight
  Segmentation and Registration Toolkit (ITK).
• Image processing
• Image Read/Write?Smoothing filters?Edge
  detection...
• Segmentation
• Region growing?Watershed?Level set?Feature
  extraction...
• Registration
• To determine the spatial transform that maps
  points from one image to homologous points on a
  object in the second image.
• Open-source.
• Developed by six principal organizations.
• http//www.itk.org/index.htm

3
What is ITK

• No Graphical User Interface (GUI)
• No Visualization
• Implemented in C
• ITK is cross-platform, using the CMake build
  environment to manage the compilation process.

4
ITK Tutorials

• http//www.itk.org/HTML/Tutorials.htm
• Getting Started I Introduction to ITK. (HTML).
• Getting Started II Using ITK with VTK.
• Getting Started III ITK Architecture.
• Getting Started IV ITK and GUIs (FLTK,QT).
• Getting Started V Integrating ITK in your
  Application.

5
What is ManagedITK

• The Insight Journal
• http//insight-journal.org/midas/handle.php?handle
  1926/501
• ManagedITK generates wrappers around ITK for .NET
  languages.
• Supported languages include C, C/CLI, VB.NET,
  IronPython4, F5, Chrome (Object Pascal)6, and
  other languages which target the .NET CLR.
• Windows Platform Only
• Object Browser and Auto-complete

6
Using ManagedITK

• Download and unzip
• ManagedITK-bin-Win32-3.6.0.1.zip
• Ensure the .NET Framework 2.0 is installed on
  your system.
• Install the Microsoft Visual C 2005
  Redistributable Package.
• vc_redist_x86.exe

7
Using ManagedITK

• Open Visual Studio
• Select Objects browser
• Edit Custom Component Set

8
Using ManagedITK

• Add Reference
• Source Code
• using itk

9
Documents and Examples

• Documents
• ItkSoftwareGuide-2.4.0.pdf
• ManagedITK-3.6.0.2.pdf
• Examples
• ManagedITK-src-3.6.0.2.zip
• Others
• http//www.itk.org/HTML/Documentation.htm

10
ITK Data Representation

• PointSet
• a basic class intended to represent geometry in
  the form of a set of points in n-dimensional
  space.
• Mesh
• The class is intended to represent shapes in
  space.
• Path
• This class will typically be used for
  representing in a concise way the output of an
  image segmentation algorithm in 2D.
• Image
• ITK supports images with any pixel type and any
  spatial dimension.
• TreeContainer

11
Data Representation - Image

• We must decide with what type to represent the
  pixels and what the dimension of the image will
  be.
• Type UC(unsigned char)?F(float)?SS(signed short)
• A region is a subset of the image and indicates a
  portion of the image that may be processed by
  other classes in the system.
• A region is defined by two classes the itkIndex
  and itkSize.
• Index(int) The origin of the region within the
  image.
• Size The size of the region.
• Spacing?Origin(double)

12
Data Representation - Image
13
Example - Allocate

• // Create an image using an explicit type
• // Note "UC2" stands for itkImagelt unsigned
  char, 2 gt
• itkImageBase image itkImage_UC2.New()
• // Region
• itkSize size new itkSize(128, 128)
• itkIndex index new itkIndex(0, 0)
• itkImageRegion region new itkImageRegion(size,
  index)
• // Set the information
• image.SetRegions(region)
• image.Allocate()
• image.Spacing new itkSpacing(1.0, 1.0)
• image.Origin new itkPoint(0.0, 0.0)
• // Test a pixel value
• itkPixel pixel image.GetPixel(index)

14
Iterators

• To use an ImageRegionIterator to iterate over the
  each pixel.
• // Create iterators to walk the input image
• itkImageRegionConstIterator_IUC2 inputIt
• inputIt new itkImageRegionConstIterator_IUC2(in
  put, region)
• // Walk the images using the iterators
• foreach (itkPixel pixel in inputIt) ...

... for(int y0 y lt size1 y) for(int x0
x lt size0 x) itkIndex index new
itkIndex(x, y) itkPixel p image.GetPixel(inde
x) ... ...
15
RescaleIntensityImageFilter

• The RescaleIntensityImageFilter linearly scales
  the pixel values in such a way that the minimum
  and maximum values of the input are mapped to
  minimum and maximum values provided by the user.
• using FilterType itkRescaleIntensityImageFilter
  
• // Apply the Rescale Intensity filter
• FilterType f f.New(inputImage_UC,
  outputImage_F)
• f.SetInput(input)
• f.OutputMinimum 000.0F
• f.OutputMaximum 255.0F
• f.Update()
• f.GetOutput(output)

16
Displaying itkImages

• System.Drawing.Bitmap
• The System.Drawing namespace is a managed wrapper
  around the Windows GDI library.
• MSDN
• BITMAP http//msdn2.microsoft.com/en-us/library/sy
  stem.drawing.bitmap(VS.80).aspx
• Working with Images, Bitmaps, Icons, and
  Metafiles http//msdn2.microsoft.com/en-us/library
  /a343dky2(VS.80).aspx
• The source code can be found in the file
• ManagedITK-3.6.0.2 /Examples/Images/itk.Examples.I
  mages.FormBitmap1.c

17

• AForge.NET
• http//code.google.com/p/aforge/
• AForge.NET is a C framework designed for
  developers and researchers in the fields of
  Computer Vision and Artificial Intelligence -
  image processing, neural networks, genetic
  algorithms, machine learning, etc.
• MATITK
• http//matitk.cs.sfu.ca/usageguide
• With the help of MATITK, biomedical image
  computing researchers familiar with MATLAB can
  harness the power of ITK algorithms while
  avoiding learning C and dealing with low-level
  programming issues.