An approach to use linguistic and model-based fuzzy expert knowledge for the analysis of MRT images

Processing of medical image data is much more difficult than industrial ima ge processing resulting from the higher degree of variability. However the improvement of the already existing technique and the development of new im aging techniques as well as the widespread availability of recording device s (e.g. CTs and MRTs) emphasize the importance of this application field wo rldwide. Although the image quality increases steadily, data contains diffe rent kinds of uncertainties and variabilities that have to be handled in co mputerized analysis. In this paper the handling of such kinds of variabilit ies by using iconic fuzzy sets for the description and recognition of anato mical structures in magnetic resonance tomograms (MRT, MRI) of human heads will be presented. (C) 2001 Elsevier Science B.V. All rights reserved.