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

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] an...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yiyu Hong, You Jeong Heo, Binnari Kim, Donghwan Lee, Soomin Ahn, Sang Yun Ha, Insuk Sohn, Kyoung-Mee Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/665a23e325834b819fadac98a5eb0531
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:665a23e325834b819fadac98a5eb0531
record_format	dspace
spelling	oai:doaj.org-article:665a23e325834b819fadac98a5eb05312021-12-02T18:51:35ZDeep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio10.1038/s41598-021-98857-12045-2322https://doaj.org/article/665a23e325834b819fadac98a5eb05312021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98857-1https://doaj.org/toc/2045-2322Abstract 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.Yiyu HongYou Jeong HeoBinnari KimDonghwan LeeSoomin AhnSang Yun HaInsuk SohnKyoung-Mee KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yiyu Hong You Jeong Heo Binnari Kim Donghwan Lee Soomin Ahn Sang Yun Ha Insuk Sohn Kyoung-Mee Kim Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
description	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.
format	article
author	Yiyu Hong You Jeong Heo Binnari Kim Donghwan Lee Soomin Ahn Sang Yun Ha Insuk Sohn Kyoung-Mee Kim
author_facet	Yiyu Hong You Jeong Heo Binnari Kim Donghwan Lee Soomin Ahn Sang Yun Ha Insuk Sohn Kyoung-Mee Kim
author_sort	Yiyu Hong
title	Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
title_short	Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
title_full	Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
title_fullStr	Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
title_full_unstemmed	Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
title_sort	deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/665a23e325834b819fadac98a5eb0531
work_keys_str_mv	AT yiyuhong deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT youjeongheo deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT binnarikim deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT donghwanlee deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT soominahn deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT sangyunha deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT insuksohn deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio AT kyoungmeekim deeplearningbasedvirtualcytokeratinstainingofgastriccarcinomastomeasuretumorstromaratio
_version_	1718377388529680384

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

Ejemplares similares