Deep feature representations for variable-sized regions of ınterest in breast histopathology
buir.contributor.author | Aygüneş, Bulut | |
buir.contributor.author | Aksoy, Selim | |
buir.contributor.author | Mercan, Caner | |
buir.contributor.author | Mercan, Ezgi | |
buir.contributor.orcid | Mercan, Caner|0000-0003-1913-4669 | |
buir.contributor.orcid | Aksoy, Selim|0000-0003-4185-0565 | |
buir.contributor.orcid | Mercan, Ezgi|0000-0001-6920-048X | |
dc.citation.epage | 2049 | en_US |
dc.citation.issueNumber | 6 | en_US |
dc.citation.spage | 2041 | en_US |
dc.citation.volumeNumber | 25 | en_US |
dc.contributor.author | Mercan, Caner | en_US |
dc.contributor.author | Aygüneş, Bulut | en_US |
dc.contributor.author | Aksoy, Selim | en_US |
dc.contributor.author | Mercan, Ezgi | en_US |
dc.contributor.author | Shapiro, L. G. | en_US |
dc.contributor.author | Weaver, D. L. | en_US |
dc.contributor.author | Elmore, J. G. | en_US |
dc.date.accessioned | 2021-03-09T06:21:45Z | |
dc.date.available | 2021-03-09T06:21:45Z | |
dc.date.issued | 2021 | |
dc.department | Department of Computer Engineering | en_US |
dc.description.abstract | Objective: 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.provenance | Submitted 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.provenance | Made 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: 2020 | en |
dc.description.sponsorship | C. 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.doi | 10.1109/JBHI.2020.3036734 | en_US |
dc.identifier.issn | 2168-2194 | |
dc.identifier.uri | http://hdl.handle.net/11693/75895 | |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | https://dx.doi.org/10.1109/JBHI.2020.3036734 | en_US |
dc.source.title | IEEE Journal of Biomedical and Health Informatics | en_US |
dc.subject | Digital pathology | en_US |
dc.subject | Breast histopathology | en_US |
dc.subject | Deep feature representation | en_US |
dc.subject | Weakly supervised learning | en_US |
dc.subject | Region of interest classification | en_US |
dc.title | Deep feature representations for variable-sized regions of ınterest in breast histopathology | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Deep_Feature_Representations_for_Variable-sized_Regions_of_Interest_in_Breast_Histopathology.pdf
- Size:
- 2.77 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: