Show simple item record

dc.contributor.authorAichinger, W.en_US
dc.contributor.authorKrappe, S.en_US
dc.contributor.authorÇetin, Ahmet Enisen_US
dc.contributor.authorÇetin-Atalay, R.en_US
dc.contributor.authorÜner, A.en_US
dc.contributor.authorBenz, M.en_US
dc.contributor.authorWittenberg, T.en_US
dc.contributor.authorStamminger, M.en_US
dc.contributor.authorMünzenmayer, C.en_US
dc.coverage.spatialOrlando, Florida, United Statesen_US
dc.date.accessioned2018-04-12T11:44:00Zen_US
dc.date.available2018-04-12T11:44:00Zen_US
dc.date.issued2017en_US
dc.identifier.issn1605-7422en_US
dc.identifier.urihttp://hdl.handle.net/11693/37562en_US
dc.descriptionDate of Conference: 11-16 February 2017en_US
dc.descriptionConference Name: SPIE Medical Imaging, 2017en_US
dc.description.abstractThe analysis and interpretation of histopathological samples and images is an important discipline in the diagnosis of various diseases, especially cancer. An important factor in prognosis and treatment with the aim of a precision medicine is the determination of so-called cancer stem cells (CSC) which are known for their resistance to chemotherapeutic treatment and involvement in tumor recurrence. Using immunohistochemistry with CSC markers like CD13, CD133 and others is one way to identify CSC. In our work we aim at identifying CSC presence on ubiquitous Hematoxilyn and Eosin (HE) staining as an inexpensive tool for routine histopathology based on their distinct morphological features. We present initial results of a new method based on color deconvolution (CD) and convolutional neural networks (CNN). This method performs favorably (accuracy 0.936) in comparison with a state-of-the-art method based on 1DSIFT and eigen-analysis feature sets evaluated on the same image database. We also show that accuracy of the CNN is improved by the CD pre-processing.en_US
dc.language.isoEnglishen_US
dc.source.titleProceedings of SPIE Vol. 10140, Medical Imaging 2017: Digital Pathologyen_US
dc.relation.isversionofhttp://dx.doi.org/10.1117/12.2254036en_US
dc.subjectColor deconvolutionen_US
dc.subjectConvolutional neural networken_US
dc.subjectDeep learningen_US
dc.subjectDigital pathologyen_US
dc.subjectHistopathologyen_US
dc.subjectTexture analysisen_US
dc.titleAutomated cancer stem cell recognition in H and E stained tissue using convolutional neural networks and color deconvolutionen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Mechanical Engineeringen_US
dc.citation.spage1en_US
dc.citation.epage6en_US
dc.citation.volumeNumber10140en_US
dc.identifier.doi10.1117/12.2254036en_US
dc.publisherSPIEen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record