Interactive Segmentation and Visualization of Volume Data Sets

A two-stage methodology for interactive segmentation of volume data sets is presented in this paper. In the first stage (presegmentation) a 3D watershed transformation is used for segmenting the data in different small regions. According to the neighboring relationships between this regions a region adjacency graph (RAG) is constructed. During the second stage (interactive information extraction), a 3D region growing algorithm driven by user controlled parameters is applied to the RAG until a satisfactory segmentation result is achieved. The presegmentation step greatly reduces the complexity of the segmentation problem. On account of that, a fast information extraction is possible in the second stage. In combination with our realtime volume rendering hardware VIRIM, the response time of the information extraction stage performed on a medical data set with 256 256 128 voxels is less than a second. CR Categories: I.3.1 [Computer Graphics]: Hardware Architecture—Parallel Processing; I.3.7 [Computer Graphics]: ThreeDimensional Graphics and Realism—Raytracing; I.4.6 [Image Processing]: Segmentation—Region Growing, Partitioning.