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.

Details

Title
Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor–stroma ratio
Author
Hong Yiyu 1 ; Heo You Jeong 2 ; Kim Binnari 3 ; Lee, Donghwan 4 ; Ahn Soomin 5 ; Ha Sang Yun 5 ; Sohn Insuk 6 ; Kyoung-Mee, Kim 7 

 Arontier Co., Ltd, Department of R&D Center, Seoul, Republic of Korea 
 Sungkyunkwan University School of Medicine, The Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Samsung Medical Center, Seoul, Republic of Korea (GRID:grid.264381.a) (ISNI:0000 0001 2181 989X) 
 Sungkyunkwan University School of Medicine, Department of Pathology and Translational Genomics, Samsung Medical Center, Seoul, Korea (GRID:grid.264381.a) (ISNI:0000 0001 2181 989X); Samsung Medical Center, Center of Companion Diagnostics, Seoul, Republic of Korea (GRID:grid.414964.a) (ISNI:0000 0001 0640 5613); University of Ulsan College of Medicine, Department of Pathology, Ulsan University Hospital, Ulsan, Republic of Korea (GRID:grid.267370.7) (ISNI:0000 0004 0533 4667) 
 Arontier Co., Ltd, Department of R&D Center, Seoul, Republic of Korea (GRID:grid.267370.7) 
 Sungkyunkwan University School of Medicine, Department of Pathology and Translational Genomics, Samsung Medical Center, Seoul, Korea (GRID:grid.264381.a) (ISNI:0000 0001 2181 989X) 
 Arontier Co., Ltd, Department of R&D Center, Seoul, Republic of Korea (GRID:grid.264381.a) 
 Sungkyunkwan University School of Medicine, The Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Samsung Medical Center, Seoul, Republic of Korea (GRID:grid.264381.a) (ISNI:0000 0001 2181 989X); Sungkyunkwan University School of Medicine, Department of Pathology and Translational Genomics, Samsung Medical Center, Seoul, Korea (GRID:grid.264381.a) (ISNI:0000 0001 2181 989X); Samsung Medical Center, Center of Companion Diagnostics, Seoul, Republic of Korea (GRID:grid.414964.a) (ISNI:0000 0001 0640 5613) 
Publication year
2021
Publication date
2021
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2576849614
Copyright
© The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.