Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines

Glotsos, D; Tohka, J; Ravazoula, P; Cavouras, D; Nikiforidis, G

dc.contributor.author	Glotsos, D	en
dc.contributor.author	Tohka, J	en
dc.contributor.author	Ravazoula, P	en
dc.contributor.author	Cavouras, D	en
dc.contributor.author	Nikiforidis, G	en
dc.date.accessioned	2014-03-01T01:54:24Z
dc.date.available	2014-03-01T01:54:24Z
dc.date.issued	2005	en
dc.identifier.issn	01290657	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/27370
dc.subject	Astrocytomas	en
dc.subject	Grading	en
dc.subject	Microscopy	en
dc.subject	Probabilistic neural network	en
dc.subject	Support vector machines	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	astrocytoma	en
dc.subject.other	brain tumor	en
dc.subject.other	cluster analysis	en
dc.subject.other	computer assisted diagnosis	en
dc.subject.other	human	en
dc.subject.other	image processing	en
dc.subject.other	methodology	en
dc.subject.other	sensitivity and specificity	en
dc.subject.other	Algorithms	en
dc.subject.other	Astrocytoma	en
dc.subject.other	Brain Neoplasms	en
dc.subject.other	Cluster Analysis	en
dc.subject.other	Diagnosis, Computer-Assisted	en
dc.subject.other	Humans	en
dc.subject.other	Image Processing, Computer-Assisted	en
dc.subject.other	Neural Networks (Computer)	en
dc.subject.other	Sensitivity and Specificity	en
dc.title	Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines	en
heal.type	journalArticle	en
heal.identifier.primary	10.1142/S0129065705000013	en
heal.identifier.secondary	http://dx.doi.org/10.1142/S0129065705000013	en
heal.publicationDate	2005	en
heal.abstract	A computer-aided diagnosis system was developed for assisting brain astrocytomas malignancy grading. Microscopy images from 140 astrocytic biopsies were digitized and cell nuclei were automatically segmented using a Probabilistic Neural Network pixel-based clustering algorithm. A decision tree classification scheme was constructed to discriminate low, intermediate and high-grade tumours by analyzing nuclear features extracted from segmented nuclei with a Support Vector Machine classifier. Nuclei were segmented with an average accuracy of 86.5%. Low, intermediate, and high-grade tumours were identified with 95%, 88.3%, and 91% accuracies respectively. The proposed algorithm could be used as a second opinion tool for the histopathologists. © World Scientific Publishing Company.	en
heal.journalName	International Journal of Neural Systems	en
dc.identifier.doi	10.1142/S0129065705000013	en
dc.identifier.volume	15	en
dc.identifier.issue	1-2	en
dc.identifier.spage	1	en
dc.identifier.epage	11	en