A fuzzy clustering based segmentation system as support to diagnosis in medical imaging

In medical imaging uncertainty is widely present in data, because of the no ise in acquisition and of the partial volume effects originating from the l ow resolution of sensors. In particular, borders between tissues are not ex actly defined and memberships in the boundary regions are intrinsically fuz zy. Therefore, computer assisted unsupervised fuzzy clustering methods turn out to be particularly suitable for handling a decision making process con cerning segmentation of multimodal medical images. By using the possibilist ic c-means algorithm as a refinement of a neural network based clustering a lgorithm named capture effect neural network, we developed the possibilisti c neuro fuzzy c-means algorithm (PNFCM). In this paper the PNFCM has been a pplied to two different multimodal data sets and the results have been comp ared to those obtained by using the classical fuzzy c-means algorithm. Furt hermore, a discussion is presented about the role of fuzzy clustering as a support to diagnosis in medical imaging. (C) 1999 Elsevier Science BV. All rights reserved.