From patch-level to ROI-level deep feature representations for breast histopathology classification

Simple item page
buir.contributor.authorMercan, Caner
buir.contributor.authorAksoy, Selim
dc.citation.epage8en_US
dc.citation.spage1en_US
dc.citation.volumeNumber10956en_US
dc.contributor.authorMercan, Caneren_US
dc.contributor.authorAksoy, Selimen_US
dc.contributor.authorMercan, E.en_US
dc.contributor.authorShapiro, L. G.en_US
dc.contributor.authorWeaver, D. L.en_US
dc.contributor.authorElmore, J. G.en_US
dc.contributor.editorTomaszewski, J. E.
dc.contributor.editorWard, A. D.
dc.coverage.spatialSan Diego, California, United Statesen_US
dc.date.accessioned2020-01-30T10:32:08Z
dc.date.available2020-01-30T10:32:08Z
dc.date.issued2019
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 16-21 February 2019en_US
dc.descriptionConference Name: SPIE Medical Imaging, 2019en_US
dc.description.abstractWe propose a framework for learning feature representations for variable-sized regions of interest (ROIs) in breast histopathology images from the convolutional network properties at patch-level. The proposed method involves fine-tuning a pre-trained convolutional neural network (CNN) by using small fixed-sized patches sampled from the ROIs. The CNN is then used to extract a convolutional feature vector for each patch. The softmax probabilities of a patch, also obtained from the CNN, are used as weights that are separately applied to the feature vector of the patch. The final feature representation of a patch is the concatenation of the class-probability weighted convolutional feature vectors. Finally, the feature representation of the ROI is computed by average pooling of the feature representations of its associated patches. The feature representation of the ROI contains local information from the feature representations of its patches while encoding cues from the class distribution of the patch classification outputs. The experiments show the discriminative power of this representation in a 4-class ROI-level classification task on breast histopathology slides where our method achieved an accuracy of 66.8% on a data set containing 437 ROIs with different sizes.en_US
dc.description.provenanceSubmitted by Zeynep Aykut (zeynepay@bilkent.edu.tr) on 2020-01-30T10:32:08Z No. of bitstreams: 1 From_patch-level_to_ROI-level_deep_feature_representations_for_breast_histopathology_classification.pdf: 11868660 bytes, checksum: b02c5632d685af51f30bf73f1f550385 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-01-30T10:32:08Z (GMT). No. of bitstreams: 1 From_patch-level_to_ROI-level_deep_feature_representations_for_breast_histopathology_classification.pdf: 11868660 bytes, checksum: b02c5632d685af51f30bf73f1f550385 (MD5) Previous issue date: 2019en
dc.description.sponsorshipThe Society of Photo-Optical Instrumentation Engineers (SPIE)en_US
dc.identifier.doi10.1117/12.2510665en_US
dc.identifier.isbn9781510625594
dc.identifier.issn1605-7422
dc.identifier.urihttp://hdl.handle.net/11693/52927
dc.language.isoEnglishen_US
dc.publisherSPIEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1117/12.2510665en_US
dc.source.titleProceedings of SPIE Vol. 10956, Medical Imaging 2019: Digital Pathologyen_US
dc.subjectDigital pathologyen_US
dc.subjectComputer aided diagnosisen_US
dc.subjectBreast histopathologyen_US
dc.subjectRegion of interest classi cationen_US
dc.titleFrom patch-level to ROI-level deep feature representations for breast histopathology classificationen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
From_patch-level_to_ROI-level_deep_feature_representations_for_breast_histopathology_classification.pdf
Size:
11.32 MB
Format:
Adobe Portable Document Format
Description:
View / Download
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

Department of Computer Engineering