Cytological diagnosis based on fuzzy neural networks

Blekas, K; Stafylopatis, A; Kontoravdis, D; Likas, A; Karakitsos, P

dc.contributor.author	Blekas, K	en
dc.contributor.author	Stafylopatis, A	en
dc.contributor.author	Kontoravdis, D	en
dc.contributor.author	Likas, A	en
dc.contributor.author	Karakitsos, P	en
dc.date.accessioned	2014-03-01T01:47:09Z
dc.date.available	2014-03-01T01:47:09Z
dc.date.issued	1998	en
dc.identifier.issn	03341860	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/25161
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0031623782&partnerID=40&md5=f5e741095abf3fdbbf6601aa034509a9	en
dc.subject	Classification	en
dc.subject	Cytological diagnosis	en
dc.subject	Fuzzy min-max neural network	en
dc.subject	Image morphometry	en
dc.subject.other	Cells	en
dc.subject.other	Cytology	en
dc.subject.other	Fuzzy sets	en
dc.subject.other	Image analysis	en
dc.subject.other	Neural networks	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Cytological diagnosis	en
dc.subject.other	Fuzzy min max neural networks	en
dc.subject.other	Image morphometry	en
dc.subject.other	Computer aided diagnosis	en
dc.title	Cytological diagnosis based on fuzzy neural networks	en
heal.type	journalArticle	en
heal.publicationDate	1998	en
heal.abstract	A diagnostic system is presented that employs morphometry combined with a fuzzy neural network approach, for the discrimination of benign from malignant gastric lesions. The input to the system consists of images of routine processed gastric smears stained by Papanicolaou technique. The analysis of the images provides a data set of cell features. The fuzzy minmax neural network classifier, an efficient pattern recognition approach, is used to classify benign and malignant cells based on the extracted morphometric and textural features. The fuzzy min-max classification network is based on hyperbox fuzzy sets and can be incrementally trained requiring only one pass through the training set. The application of the fuzzy min-max neural network yields high rates of correct classification at both the cell level and the patient level. These results indicate that the use of intelligent computational techniques along with image morphometry may offer very useful information about the potential of malignancy of gastric cells.	en
heal.journalName	Journal of Intelligent Systems	en
dc.identifier.volume	8	en
dc.identifier.issue	1-2	en
dc.identifier.spage	55	en
dc.identifier.epage	76	en