Projects / ITK


The National Library of Medicine Insight Segmentation and Registration Toolkit (ITK) is a software system to support the Visible Human Project. Segmentation is the process of identifying and classifying data found in a digitally sampled representation. Registration is the task of aligning or developing correspondences between data. For example, in the medical environment, a CT scan may be aligned with an MRI scan in order to combine the information contained in both.

Operating Systems

Recent releases

  •  28 Jul 2012 03:50

    Release Notes: ITK now supports the latest GCC 4.7.0, as well as Visual Studio 10 without requiring any workarounds. The team also added GPU modules for Finite Difference, Smoothing, Thresholding, and Registration. The new patch-based denoising filter improves noise reduction by calculating and applying parameters locally, thus accommodating noise variations within an image. The infrastructure to support Remote Modules was added along with a new physics-based non-rigid registration technique.

    •  29 Mar 2012 02:24

      Release Notes: This release adds modularization, a simplified accessibility layer, new frameworks for registration and level setting, a refactored finite element framework, video processing support, updated DICOM support, improved support for large microscopy images above 4 GB, better VTK Bridge and WrapITK support, a new deconvolution filtering module, and a new TimeVaryingBSplineVelocityFieldTransform. It has been migrated to GIT.

      •  30 Mar 2011 06:35

        Release Notes: Numerous bugfixes and code speedups were made.

        •  04 May 2010 15:46

          Release Notes: There are improvements in the implementation of mathematical traits, particularly for fast rounding. Classes for managing internationalization of strings have been added. The version of the NrrdIO library in Utilities has been updated. Shadowing warnings reported by gcc have been fixed. Recently added classes were included in the Wrapping. There is improved support for Symmetric Tensor operations. Behavior of the Object Factories has been improved, and testing for Discrete Gaussian derivative filters has been improved.

          •  20 Jul 2009 21:51

            Release Notes: Numerous enhancements.


            Project Spotlight


            A Fluent OpenStack client API for Java.


            Project Spotlight

            TurnKey TWiki Appliance

            A TWiki appliance that is easy to use and lightweight.