Fuzzy rule based clustering algorithm for medical image segmentation

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations



Original languageEnglish
Pages (from-to)177-180
Journal / PublicationNational Conference Publication - Institution of Engineers, Australia
Issue number94 /9
Publication statusPublished - 1994
Externally publishedYes


TitleProceedings of the International Symposium on Information Theory & Its Applications 1994. Part 1 (of 2)
CitySydney, Aust
Period20 - 24 November 1994


Segmentation of biological images into tissue components is becoming increasingly important in the clinical environment. One example is the segregation of brain tissues for the study of degenerative diseases. In this paper, we present a fuzzy rule based approach for classification and tissue labeling of magnetic resonance (MR) images of the human brain. K-means clustering is applied to produce clusters whose centers and variances are then used to determine fuzzy membership functions. The fuzzy rules are then directly extracted from learning examples. Our experiments show that the proposed method has a number of advantages over conventional clustering methods.