ITK/Release 4/Why Switch to ITKv4

Modularization

• Easier to find what you are looking for.
• Easier to understand how to use the toolkit.
• Build only the parts of the toolkit that you need.
• Extend bridging of the toolkit to other toolkit and libraries.
• Makes it easy to associate and build auxiliary community projects with an External module.
• Find the quality control per module by performing code coverage tests per module.

New Finite Element Registration Framework

• Better conformity with the rest of the toolkit
• Improved IO of objects and results

New Registration Framework

• New unified and fully multi-threaded optimization and registration framework
• Unified framework supports sparse and dense metric computation
• Unified framework supports low and high dimensional mapping
• Improved multi-threaded metrics for rigid, affine and deformable registration
• New metrics support sparse or dense sampling
• Metrics for landmark or label guided registration
• Automatic parameter scale estimation for registration
• Automatic step-size selection for gradient-based registration optimizers
• Composite transforms and composite transform optimization
• Displacement field and diffeomorphic velocity field-based transforms
• Better support for multi-threading in optimizers and metrics
• Additional evolutionary optimizers
• Improved B-Spline registration approach available and bug fixes to old framework
• Accurately transform and reorient covariant tensors and vectors

New LevelSets Segmentation Framework

• Powerful, modular architecture
  • Now you, too, can fully understand how level sets are implemented!
  • Easy to extend and customize
• Simultaneously evolve multiple level sets on an image
• Faster
  • Limit evolution to a domain
  • Three different sparse representations available, Whitaker, Shi, Malcolm
  • Design avoids duplication of calculations in many ways
• Easy conversion from BinaryMask or LabelMap to a level set.

SimpleITK

• Easy to use
  • Procedural Interface Examples:
    • Procedual Gaussian in Python
    • Procedural Gaussian in C++
  • Object Oriented Interface Examples:
    • OOP Gaussian in C++
    • OOP Gaussian in Python
    • OOP Gaussian in Java
    • OOP Gaussian in C#
  • Additional Examples
    • http://www.itk.org/SimpleITKDoxygen/html/examples.html
• Rapid development
• Interactive processing

Software Process

• Fast, distributed, powerful version control: Git
• Better support for making contributions
  • Low barrier to entry
  • Well defined contribution process
  • Use powerful tools, Git branches, Gerrit reviews
  • Get code into the toolkit quicker
  • Get higher quality code in with more reviews and platform testing
• Forget SETI@home, give the aliens a reason to visit by improving ITK with CDash@home!
• Know when/if your bug will be addressed with the scrum process in the JIRA issue tracker
• Flexible management of testing data

WrapITK

• Tight incorporation of the outstanding, formerly third party WrapITK project.
• Numpy integration.

"You can do it!"

• Migration Guide
• ITKv4 Removed or renamed classes|
• The insight-users mailing list is there for you.
• Transition is easier with ITKV3_COMPATIBILITY configuration option.
• Many deprecated classes are still available.
• The list of other improvements and new features are legion, don't miss out!