The use of fuzzy rules in classification of normal human brain tissues

Automatic classification and tissue labeling of 2D magnetic resonance images of the human brain may involve a preliminary clustering stage. Segmenting large multidimensional data sets like those from magnetic resonance images is very time consuming. Better performance at the clustering stage as achieved if partial classification of the image can be done before applying clustering. We show the use of fuzzy rules to do this partial classification to be very effective. Fuzzy rules can preclassify a major portion of the image giving a clustering algorithm a lesser number of pixels to operate upon. Furthermore, as the preclassification stage is itself fuzzy, it can be directly used to initialize a fuzzy clustering algorithm, giving it a much needed headstart. We present an approach to using fuzzy rules to preclassify magnetic resonance images of the normal human brain. Good segmentation of normal brain into tissues of interest is obtained much faster than with clustering alone.