Texture- and Object-Related Automated Information Analysis in Histological Still Images of Various Organs

dc.creatorKayser, K
dc.creatorHoshang, SA
dc.creatorMetze, K
dc.creatorGoldmann, T
dc.creatorVollmer, E
dc.creatorRadziszowski, D
dc.creatorKosjerina, Z
dc.creatorMireskandari, M
dc.creatorKayser, G
dc.date2008
dc.dateDEC
dc.date2014-08-01T18:25:08Z
dc.date2015-11-26T17:04:05Z
dc.date2014-08-01T18:25:08Z
dc.date2015-11-26T17:04:05Z
dc.date.accessioned2018-03-28T23:52:19Z
dc.date.available2018-03-28T23:52:19Z
dc.identifierAnalytical And Quantitative Cytology And Histology. Sci Printers & Publ Inc, v. 30, n. 6, n. 323, n. 335, 2008.
dc.identifier0884-6812
dc.identifierWOS:000261760200003
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/78656
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/78656
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1279262
dc.descriptionOBJECTIVE: To create algorithms and application tools that can support routine diagnoses of various organs. MATERIALS: A generalized algorithm was developed that permits the evaluation of diagnosis-associated image features obtained from hematoxylin-eosin-stained histopathologic slides. The procedure was tested for screening of tumor tissue vs. tumor free tissue in 1,442 cases of various organs. Tissue samples studied include colon, lung, breast, pleura, stomach and thyroid. The algorithm distinguishes between texture- and object-related parameters. Texture-based information-defined as gray value per pixel measure-is independent from any segmentation procedure. It results in recursive vectors derived from time series analysis and image features obtained by spatial dependent and independent transformations. Object-based features are defined as gray value per biologic object measured. RESULTS: The accuracy of automated crude classification was between 95% and 100% based upon a learning set of 10 cases per diagnosis class. Results were independent from the analyzed organ. The algorithm can also distinguish between benign and malignant tumors of colon, between epithelial mesothelioma and pleural carcinomatosis or between different common pulmonary carcinomas. CONCLUSION: Our algorithm distinguishes accurately among crude histologic diagnoses of various organs. It is a promising technique that can assist tissue-based diagnosis and be expanded to virtual slide evaluation.
dc.description30
dc.description6
dc.description323
dc.description335
dc.descriptionInternational Academy of Telepathology, Heidelberg
dc.descriptionVerein zur Forderung des biologisch technologischen Fortschritts in der Medizin
dc.languageen
dc.publisherSci Printers & Publ Inc
dc.publisherSt Louis
dc.publisherEUA
dc.relationAnalytical And Quantitative Cytology And Histology
dc.relationAnal. Quant. Cytol. Histol.
dc.rightsfechado
dc.sourceWeb of Science
dc.subjectalgorithm
dc.subjectanalysis
dc.subjectobject
dc.subjectanalysis
dc.subjecttexture
dc.subjectdiagnosis
dc.subjecttissue-based
dc.subjecthistology
dc.subjectstereology
dc.subjecttumor
dc.subjectProstatic Intraepithelial Neoplasia
dc.subjectBayesian Belief Network
dc.subjectVirtual Microscopy
dc.subjectCell Carcinoma
dc.subjectStereological Methods
dc.subjectDiagnostic Pathology
dc.subjectDifferential-diagnosis
dc.subjectAnalysis Workstation
dc.subjectArbitrary Particles
dc.subjectPattern-recognition
dc.titleTexture- and Object-Related Automated Information Analysis in Histological Still Images of Various Organs
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución