KLI

Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor-stroma ratio

Metadata Downloads
Abstract
The tumor-stroma ratio (TSR) determined by pathologists is subject to intra- and inter-observer variability. We aimed to develop a computational quantification method of TSR using deep learning-based virtual cytokeratin staining algorithms. Patients with 373 advanced (stage III [n = 171] and IV [n = 202]) gastric cancers were analyzed for TSR. Moderate agreement was observed, with a kappa value of 0.623, between deep learning metrics (dTSR) and visual measurement by pathologists (vTSR) and the area under the curve of receiver operating characteristic of 0.907. Moreover, dTSR was significantly associated with the overall survival of the patients (P = 0.0024). In conclusion, we developed a virtual cytokeratin staining and deep learning-based TSR measurement, which may aid in the diagnosis of TSR in gastric cancer.
Author(s)
홍이유허유정김빛나리이동환안수민하상윤손인석김경미
Issued Date
2021
Type
Article
Keyword
AdultAgedCarcinomaCarcinoma - diagnosisCarcinoma - mortalityCarcinoma - pathologyCarcinoma - surgeryComputer applicationsCytokeratinDeep LearningFemaleFollow-Up StudiesGastrectomyGastric cancerHumansImage ProcessingComputer-Assisted - methodsKaplan-Meier EstimateKeratins - analysisMaleMiddle AgedNeoplasm StagingObserver VariationRisk Assessment - methodsROC CurveStomach - pathologyStomach - surgeryStomach Neoplasms - diagnosisStomachNeoplasms - mortalityStomach Neoplasms - pathologyStomach Neoplasms - surgeryStromaTreatment OutcomeVisual discrimination learning
DOI
10.1038/s41598-021-98857-1
URI
https://oak.ulsan.ac.kr/handle/2021.oak/8299
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_doaj_primary_oai_doaj_org_article_665a23e325834b819fadac98a5eb0531&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,Deep%20learning-based%20virtual%20cytokeratin%20staining%20of%20gastric%20carcinomas%20to%20measure%20tumor-stroma%20ratio&offset=0&pcAvailability=true
Publisher
SCIENTIFIC REPORTS
Location
독일
Language
영어
ISSN
2045-2322
Citation Volume
11
Citation Number
1
Citation Start Page
19255
Citation End Page
19255
Appears in Collections:
Medicine > Medicine
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

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