A hybrid classification model for digital pathology using structural and statistical pattern recognition

Simple item page
dc.citation.epage483en_US
dc.citation.issueNumber2en_US
dc.citation.spage474en_US
dc.citation.volumeNumber32en_US
dc.contributor.authorOzdemir, E.en_US
dc.contributor.authorGunduz-Demir, C.en_US
dc.date.accessioned2016-02-08T09:40:45Z
dc.date.available2016-02-08T09:40:45Z
dc.date.issued2013en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractCancer causes deviations in the distribution of cells, leading to changes in biological structures that they form. Correct localization and characterization of these structures are crucial for accurate cancer diagnosis and grading. In this paper, we introduce an effective hybrid model that employs both structural and statistical pattern recognition techniques to locate and characterize the biological structures in a tissue image for tissue quantification. To this end, this hybrid model defines an attributed graph for a tissue image and a set of query graphs as a reference to the normal biological structure. It then locates key regions that are most similar to a normal biological structure by searching the query graphs over the entire tissue graph. Unlike conventional approaches, this hybrid model quantifies the located key regions with two different types of features extracted using structural and statistical techniques. The first type includes embedding of graph edit distances to the query graphs whereas the second one comprises textural features of the key regions. Working with colon tissue images, our experiments demonstrate that the proposed hybrid model leads to higher classification accuracies, compared against the conventional approaches that use only statistical techniques for tissue quantification. © 2012 IEEE.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:40:45Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2013en
dc.identifier.doi10.1109/TMI.2012.2230186en_US
dc.identifier.issn0278-0062
dc.identifier.urihttp://hdl.handle.net/11693/21079
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/TMI.2012.2230186en_US
dc.source.titleIEEE Transactions on Medical Imagingen_US
dc.subjectAutomated cancer diagnosisen_US
dc.subjectCanceren_US
dc.subjectGraph embeddingen_US
dc.subjectHistopathological image analysisen_US
dc.subjectInexact graph matchingen_US
dc.subjectStructural pattern recognitionen_US
dc.subjectTissue characterizationen_US
dc.subjectMethodologyen_US
dc.subjectReproducibilityen_US
dc.subjectSensitivity and specificityen_US
dc.subjectStatistical analysisen_US
dc.subjectStatistical modelen_US
dc.subjectThree dimensional imagingen_US
dc.subjectBiopsyen_US
dc.subjectComputer simulationen_US
dc.subjectData interpretationen_US
dc.subjectImage enhancementen_US
dc.titleA hybrid classification model for digital pathology using structural and statistical pattern recognitionen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A hybrid classification model for digital pathology using structural and statistical pattern recognition.pdf
Size:
2.02 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering