1. Repository of OAI
  2. ΑΠΟΘΕΤΗΡΙΟ "ΟΛΥΜΠΙΑΣ"
  3. Σχολή Επιστημών Υγείας
  4. Τμήμα Ιατρικής
  5. Άρθρα σε επιστημονικά περιοδικά ( Ανοικτά) - ΙΑΤ
Ελληνικά   English  
Please use this identifier to cite or link to this item: https://olympias.lib.uoi.gr/jspui/handle/123456789/22581
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDaskalakis, A.en
dc.contributor.authorKostopoulos, S.en
dc.contributor.authorSpyridonos, P.en
dc.contributor.authorGlotsos, D.en
dc.contributor.authorRavazoula, P.en
dc.contributor.authorKardari, M.en
dc.contributor.authorKalatzis, I.en
dc.contributor.authorCavouras, D.en
dc.contributor.authorNikiforidis, G.en
dc.date.accessioned2015-11-24T19:25:10Z-
dc.date.available2015-11-24T19:25:10Z-
dc.identifier.issn0010-4825-
dc.identifier.urihttps://olympias.lib.uoi.gr/jspui/handle/123456789/22581-
dc.rightsDefault Licence-
dc.subjectAlgorithmsen
dc.subjectArtificial Intelligenceen
dc.subjectBayes Theoremen
dc.subjectBiopsy, Fine-Needleen
dc.subjectCell Nucleus/metabolismen
dc.subjectCytodiagnosis/methodsen
dc.subjectDiagnosis, Differentialen
dc.subjectEosine Yellowish-(YS)/chemistryen
dc.subjectHematoxylin/chemistryen
dc.subjectHumansen
dc.subjectImage Interpretation, Computer-Assisted/*methodsen
dc.subjectLeast-Squares Analysisen
dc.subjectNeural Networks (Computer)en
dc.subjectSensitivity and Specificityen
dc.subjectStaining and Labeling/methodsen
dc.subjectStatistics, Nonparametricen
dc.subjectThyroid Gland/chemistry/*pathologyen
dc.subjectThyroid Neoplasms/metabolism/*pathologyen
dc.subjectThyroid Nodule/*diagnosis/metabolismen
dc.titleDesign of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological imagesen
heal.typejournalArticle-
heal.type.enJournal articleen
heal.type.elΆρθρο Περιοδικούel
heal.identifier.primary10.1016/j.compbiomed.2007.09.005-
heal.identifier.secondaryhttp://www.ncbi.nlm.nih.gov/pubmed/17996861-
heal.identifier.secondaryhttp://ac.els-cdn.com/S0010482507001588/1-s2.0-S0010482507001588-main.pdf?_tid=a3abe9c61d6ffff80e59ba71a4a7f0ee&acdnat=1333451294_648de2d212352dbfc4b2549151499e23-
heal.languageen-
heal.accesscampus-
heal.recordProviderΠανεπιστήμιο Ιωαννίνων. Σχολή Επιστημών Υγείας. Τμήμα Ιατρικήςel
heal.publicationDate2008-
heal.abstractA multi-classifier diagnostic system was designed for distinguishing between benign and malignant thyroid nodules from routinely taken (FNA, H&E-stained) cytological images. To construct the multi-classifier system, several combination rules and different mixtures of ensemble classifier members, employing morphological and textural nuclear features, were comparatively evaluated. Experimental results illustrated that the classifier combination k-NN/PNN/Bayesian and the majority vote rule enhanced significantly classification accuracy (95.7%) as compared to best single classifier (PNN: 89.6%). The proposed system was designed with purpose to be utilized in daily clinical practice as a second opinion tool to support cytopathologists' decisions, when a definite diagnosis is difficult to be obtained.en
heal.journalNameComput Biol Meden
heal.journalTypepeer-reviewed-
heal.fullTextAvailabilityTRUE-
Appears in Collections:Άρθρα σε επιστημονικά περιοδικά ( Ανοικτά) - ΙΑΤ

Show simple item record
Files in This Item:
File Description SizeFormat 
Daskalakis-2008-Design of a multi-cl.pdf284.03 kBAdobe PDFView/Open    Request a copy
Show simple item record  


This item is licensed under a Creative Commons License Creative Commons