Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks

Simple item page
buir.contributor.authorGeçer, Barış
buir.contributor.authorAksoy, Selim
dc.citation.epage356en_US
dc.citation.spage345en_US
dc.citation.volumeNumber84en_US
dc.contributor.authorGeçer, Barışen_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.date.accessioned2019-02-21T16:01:56Z
dc.date.available2019-02-21T16:01:56Z
dc.date.issued2018en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractGeneralizability of algorithms for binary cancer vs. no cancer classification is unknown for clinically more significant multi-class scenarios where intermediate categories have different risk factors and treatment strategies. We present a system that classifies whole slide images (WSI) of breast biopsies into five diagnostic categories. First, a saliency detector that uses a pipeline of four fully convolutional networks, trained with samples from records of pathologists’ screenings, performs multi-scale localization of diagnostically relevant regions of interest in WSI. Then, a convolutional network, trained from consensus-derived reference samples, classifies image patches as non-proliferative or proliferative changes, atypical ductal hyperplasia, ductal carcinoma in situ, and invasive carcinoma. Finally, the saliency and classification maps are fused for pixel-wise labeling and slide-level categorization. Experiments using 240 WSI showed that both saliency detector and classifier networks performed better than competing algorithms, and the five-class slide-level accuracy of 55% was not statistically different from the predictions of 45 pathologists. We also present example visualizations of the learned representations for breast cancer diagnosis.
dc.embargo.release2020-05-01en_US
dc.identifier.doi10.1016/j.patcog.2018.07.022
dc.identifier.issn0031-3203
dc.identifier.urihttp://hdl.handle.net/11693/49939
dc.language.isoEnglish
dc.publisherElsevier
dc.relation.isversionofhttps://doi.org/10.1016/j.patcog.2018.07.022
dc.source.titlePattern Recognitionen_US
dc.subjectBreast histopathologyen_US
dc.subjectDeep learningen_US
dc.subjectDigital pathologyen_US
dc.subjectMulti-class classificationen_US
dc.subjectRegion of interest detectionen_US
dc.subjectSaliency detectionen_US
dc.subjectWhole slide imagingen_US
dc.titleDetection and classification of cancer in whole slide breast histopathology images using deep convolutional networksen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Detection_and_classification_of_cancer_in_whole_slide_breast.pdf
Size:
3.67 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering