The Medical Imaging Interaction Toolkit (MITK)
The Medical Imaging Interaction Toolkit (MITK) is a free open-source software system for development of interactive medical image processing software. MITK combines the Insight Toolkit (ITK) and the Visualization Toolkit (VTK) with PIC-based libraries of the DKFZ. As a toolkit, MITK offers those features that are relevant for the development of interactive medical imaging software covered neither by ITK nor VTK, such as:
- Multiple, consistent views on the same data. For example, when you have three orthogonal 2D-views and a 3D view and data consisting of a green surface, the surface will be visible and green in all views (as contour lines in 2D, as a surface in 3D), and when you move the surface, it will move in all views. When you try to realize this with basic VTK, you will need to coordinate the position/orientation/color/... of all the views somewhere in your program - exactly this is done automatically by MITK
An interaction concept based on state machines, which helps you to structure complex interaction mechanisms
An undo/redo concept for interactions
Organization of all application data in a central, hierarchical repository (DataStorage). The hierarchy allow to represent logical relations (such as "the ventricle is part of the heart")
- Description of data items by arbitrary "properties" (key/value list), for communication between program modules or to control rendering
MITK re-uses virtually anything from VTK and ITK. Thus, it is not at all a competitor to VTK or ITK, but an extension, which tries to ease the combination of both and to add the features outlined above. Although it is mainly a toolkit and not an application, MITK offers some support on the application-level, e.g, for structured combination of modules (so-called functionalities), e.g., for combining and switching between one functionality for segmentation and another for registration.
Information for users
Program modules
The main application of MITK currently offers the following program modules:
Interactive segmentation of slices in image volumes, including interactive region growing and easy correction, interpolation of missing slices, surface generation, and volumetry
Point based registration of medical image volumes allows to match two images based on two corresponding sets of points
Rigid registration of images by combination of the ITK registration objects (transforms, optimizers, metrics, etc.)
Measurement of distances and angles (mainly as a programming example)
Volume visualization lets you modify a transfer function and demonstrates the possibilities of VTK volume rendering
DataManager is a program module meant mainly for developers, which allows you to inspect the internal data repository with all the loaded data and its properties (key/value list)
Movie generation is currently possible with Windows
Information for developers