Full metadata record

DC Field Value Language
dc.contributor.authorFeng, Linqing-
dc.contributor.authorSong, Jun Ho-
dc.contributor.authorKim, Jiwon-
dc.contributor.authorJeong, Soomin-
dc.contributor.authorPark, Jin Sung-
dc.contributor.authorKim, Jinhyun-
dc.date.accessioned2024-01-19T19:00:59Z-
dc.date.available2024-01-19T19:00:59Z-
dc.date.created2021-09-05-
dc.date.issued2019-11-
dc.identifier.issn2169-3536-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/119377-
dc.description.abstractQuantitative analysis of cell nuclei in microscopic images is an essential yet challenging source of biological and pathological information. The major challenge is accurate detection and segmentation of densely packed nuclei in images acquired under a variety of conditions. Mask R-CNN-based methods have achieved state-of-the-art nucleus segmentation. However, the current pipeline requires fully annotated training images, which are time consuming to create and sometimes noisy. Importantly, nuclei often appear similar within the same image. This similarity could be utilized to segment nuclei with only partially labeled training examples. We propose a simple yet effective region-proposal module for the current Mask R-CNN pipeline to perform few-exemplar learning. To capture the similarities between unlabeled regions and labeled nuclei, we apply decomposed self-attention to learned features. On the self-attention map, we observe strong activation at the centers and edges of all nuclei, including unlabeled nuclei. On this basis, our region-proposal module propagates partial annotations to the whole image and proposes effective bounding boxes for the bounding box-regression and binary mask-generation modules. Our method effectively learns from unlabeled regions thereby improving detection performance. We test our method with various nuclear images. When trained with only 1/4 of the nuclei annotated, our approach retains a detection accuracy comparable to that from training with fully annotated data. Moreover, our method can serve as a bootstrapping step to create full annotations of datasets, iteratively generating and correcting annotations until a predetermined coverage and accuracy are reached. The source code is available at <uri>https://github.com/feng-lab/nuclei</uri>.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectSEGMENTATION-
dc.subjectTRACKING-
dc.subjectCELLS-
dc.subjectINFORMATION-
dc.titleRobust Nucleus Detection With Partially Labeled Exemplars-
dc.typeArticle-
dc.identifier.doi10.1109/ACCESS.2019.2952098-
dc.description.journalClass1-
dc.identifier.bibliographicCitationIEEE ACCESS, v.7, pp.162169 - 162178-
dc.citation.titleIEEE ACCESS-
dc.citation.volume7-
dc.citation.startPage162169-
dc.citation.endPage162178-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.identifier.wosid000497169800098-
dc.identifier.scopusid2-s2.0-85078698821-
dc.relation.journalWebOfScienceCategoryComputer Science, Information Systems-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.relation.journalWebOfScienceCategoryTelecommunications-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalResearchAreaTelecommunications-
dc.type.docTypeArticle-
dc.subject.keywordPlusSEGMENTATION-
dc.subject.keywordPlusTRACKING-
dc.subject.keywordPlusCELLS-
dc.subject.keywordPlusINFORMATION-
dc.subject.keywordAuthorTraining-
dc.subject.keywordAuthorImage segmentation-
dc.subject.keywordAuthorTask analysis-
dc.subject.keywordAuthorPipelines-
dc.subject.keywordAuthorProposals-
dc.subject.keywordAuthorHead-
dc.subject.keywordAuthorImage edge detection-
dc.subject.keywordAuthorNucleus segmentation-
dc.subject.keywordAuthordeep learning-
dc.subject.keywordAuthorconvolutional neural networks-
dc.subject.keywordAuthorfew-exemplar learning-
dc.subject.keywordAuthorsemisupervised learning-
dc.subject.keywordAuthorcomputer-assisted annotating-
Appears in Collections:
KIST Article > 2019
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE