Deep feature representations for variable-sized regions of ınterest in breast histopathology

Simple item page
buir.contributor.authorAygüneş, Bulut
buir.contributor.authorAksoy, Selim
buir.contributor.authorMercan, Caner
buir.contributor.authorMercan, Ezgi
buir.contributor.orcidMercan, Caner|0000-0003-1913-4669
buir.contributor.orcidAksoy, Selim|0000-0003-4185-0565
buir.contributor.orcidMercan, Ezgi|0000-0001-6920-048X
dc.citation.epage2049en_US
dc.citation.issueNumber6en_US
dc.citation.spage2041en_US
dc.citation.volumeNumber25en_US
dc.contributor.authorMercan, Caneren_US
dc.contributor.authorAygüneş, Buluten_US
dc.contributor.authorAksoy, Selimen_US
dc.contributor.authorMercan, Ezgien_US
dc.contributor.authorShapiro, L. G.en_US
dc.contributor.authorWeaver, D. L.en_US
dc.contributor.authorElmore, J. G.en_US
dc.date.accessioned2021-03-09T06:21:45Z
dc.date.available2021-03-09T06:21:45Z
dc.date.issued2021
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractObjective: Modeling variable-sized regions of interest (ROIs) in whole slide images using deep convolutional networks is a challenging task, as these networks typically require fixed-sized inputs that should contain sufficient structural and contextual information for classification. We propose a deep feature extraction framework that builds an ROI-level feature representation via weighted aggregation of the representations of variable numbers of fixed-sized patches sampled from nuclei-dense regions in breast histopathology images. Methods: First, the initial patch-level feature representations are extracted from both fully-connected layer activations and pixel-level convolutional layer activations of a deep network, and the weights are obtained from the class predictions of the same network trained on patch samples. Then, the final patch-level feature representations are computed by concatenation of weighted instances of the extracted feature activations. Finally, the ROI-level representation is obtained by fusion of the patch-level representations by average pooling. Results: Experiments using a well-characterized data set of 240 slides containing 437 ROIs marked by experienced pathologists with variable sizes and shapes result in an accuracy score of 72.65% in classifying ROIs into four diagnostic categories that cover the whole histologic spectrum. Conclusion: The results show that the proposed feature representations are superior to existing approaches and provide accuracies that are higher than the average accuracy of another set of pathologists. Significance: The proposed generic representation that can be extracted from any type of deep convolutional architecture combines the patch appearance information captured by the network activations and the diagnostic relevance predicted by the class-specific scoring of patches for effective modeling of variable-sized ROIs.en_US
dc.description.provenanceSubmitted by Onur Emek (onur.emek@bilkent.edu.tr) on 2021-03-09T06:21:45Z No. of bitstreams: 1 Deep_Feature_Representations_for_Variable-sized_Regions_of_Interest_in_Breast_Histopathology.pdf: 9612130 bytes, checksum: 481d28a73960cb33729a39c16e944f57 (MD5)en
dc.description.provenanceMade available in DSpace on 2021-03-09T06:21:45Z (GMT). No. of bitstreams: 1 Deep_Feature_Representations_for_Variable-sized_Regions_of_Interest_in_Breast_Histopathology.pdf: 9612130 bytes, checksum: 481d28a73960cb33729a39c16e944f57 (MD5) Previous issue date: 2020en
dc.description.sponsorshipC. Mercan, B. Aygunes, and S. Aksoy were supported in part by the Scientific and Technological Research Council of Turkey under Grant No. 117E172. E. Mercan, L. G. Shapiro, D. L. Weaver, and J. G. Elmore were supported in part by the National Cancer Institute of the National Institutes of Health under Awards No. R01-CA172343, R01-140560, and R01-CA225585.en_US
dc.identifier.doi10.1109/JBHI.2020.3036734en_US
dc.identifier.issn2168-2194
dc.identifier.urihttp://hdl.handle.net/11693/75895
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/JBHI.2020.3036734en_US
dc.source.titleIEEE Journal of Biomedical and Health Informaticsen_US
dc.subjectDigital pathologyen_US
dc.subjectBreast histopathologyen_US
dc.subjectDeep feature representationen_US
dc.subjectWeakly supervised learningen_US
dc.subjectRegion of interest classificationen_US
dc.titleDeep feature representations for variable-sized regions of ınterest in breast histopathologyen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Deep_Feature_Representations_for_Variable-sized_Regions_of_Interest_in_Breast_Histopathology.pdf
Size:
2.77 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Computer Engineering