A fundamental part of MeVisLab is the object-oriented MeVis Image Processing Library (ML), that provides a generic framework for image processing. Each algorithm is represented as a self-descriptive module inside the development environment. These functional units can be arbitrarily combined to form a network via an intuitive graphical user interface. Important ML characteristics:
- Request-driven, page-based image processing library
- Priority-controlled page cache
- Advanced support for:
- Local filters
- Kernel filters
- Global filters
- Special "Virtual Volume" support for global access to large images
- Extended image information access:
- DICOM coordinate system/voxel size
- DICOM tags
- Channel/time information
- User defined objects interface
- Optimization options
Image Processing Modules
Currently, more than 300 image processing modules are available, including image filtering, segmentation, and statistical analysis. This includes, for example:
- Filters: Diffusion filters, morphology filters, kernel filters
- Segmentation: Region growing, live wire, fuzzy connectedness, threshold, manual contours
- Transformations: Affine transformations, distance transformations, Radon transform, manual registration
- Statistics: Histograms, global image statistics, box counting dimension
- Other: Unary/binary arithmetic, resampling/reformatting, dynamic data analysis, noise/test pattern generators
Other Image Processing Modules
Winged-Edged Meshes (WEM)
The WEM (Winged Edge Mesh) library provides unified algorithms for the generation, the processing
and the rendering of surface representations. In MeVisLab, it offers functionalities for common mesh processing tasks:
- An iso surface can be generated at a certain threshold out of medical images, the resulting surface can be
reduced in its amount of primitives or can be smoothed by using different algorithms. - For rendering, the surface can be colored in order to reflect certain additional information or according to a flexible coloring scheme out of the image data itself.
- All the generated and modifed surfaces can be saved and loaded with a variety of different file formats that are compliant with standard 3D applications.
Contour Segmentation Objects (CSO)
The CSO library provides data structures and modules for automatic generation and processing of
contours in voxel images, as well as interactive manipulation of contours.
