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

Sci Rep. 2021 Sep 28;11(1):19255. doi: 10.1038/s41598-021-98857-1.

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.

Publication types

  • Observational Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adult
  • Aged
  • Carcinoma / diagnosis*
  • Carcinoma / mortality
  • Carcinoma / pathology
  • Carcinoma / surgery
  • Deep Learning*
  • Female
  • Follow-Up Studies
  • Gastrectomy
  • Humans
  • Image Processing, Computer-Assisted / methods*
  • Kaplan-Meier Estimate
  • Keratins / analysis
  • Male
  • Middle Aged
  • Neoplasm Staging
  • Observer Variation
  • ROC Curve
  • Risk Assessment / methods
  • Stomach / pathology*
  • Stomach / surgery
  • Stomach Neoplasms / diagnosis*
  • Stomach Neoplasms / mortality
  • Stomach Neoplasms / pathology
  • Stomach Neoplasms / surgery
  • Treatment Outcome

Substances

  • Keratins