Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Interactive neural network texture analysis and visualization for surface reconstruction in medical imaging

: Busch, C.; Groß, M.

Brunet, P. ; European Association for Computer Graphics -EUROGRAPHICS-:
Eurographics '93 : The European Association for Computer Graphics 14th annual conference and exhibition, Barcelona, Spain, 6 - 10 September 1993
Barcelona; Cambridge: Blackwell Scientific Publications, 1993 (Computer graphics forum 12.1993,3)
Eurographics <1993, Barcelona>
Conference Paper
Fraunhofer IGD ()
3D-reconstruction; artificial neural network; brain tumor; cluster analysis; magnetic resonance imaging; marching cube; multidimensional feature space; subspace mapping; texture analysis; tissue classification; visualisation

The following paper describes a new approach for the automatic segmentation and tissue classification of anatomical objects such as brain tumors from magnetic resonance imaging (MRI) data sets using artificial neural networks. These segmentations serve as an input for 3D-reconstruction algorithms. Since MR images require a careful interpretation of the underlying physics and parameters, we first give the reader a tutorial style introduction to the physical basics of MR technology. Secondly, we describe our approach that is based on a two-pass method including non-supervised cluster analysis, dimensionality reduction and visualization of the texture features by means of nonlinear topographic mappings. An additional classification of the MR data set can be obtained using a post-processing technique to approximate the Bayes decision boundaries. Interactions between the user and the network allow an optimization of the results. For fast 3D-reconstructions, we use a modified marching cubes algorithm but our scheme can easily serve as a preprocessor for any kind of volume renderer. The applications we present in our paper aim at the automatic extraction and fast reconstruction of brain tumors for surgery and therapy planing. We use the neural networks on pathological data sets and show how the method generalizes to physically comparable data sets.