Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Proteomic Analysis Identifies Potential Biomarkers of ELOC-Mutated Renal Cell Carcinoma.

The American journal of surgical pathology·2026
Same author

Risk-based pathology reporting after endoscopic submucosal dissection for early gastrointestinal cancer: international consensus standards.

Gut·2026
Same author

Histological Analysis of Cryopreserved Venous Allografts Used for Liver Transplantation and Hepato-Biliary-Pancreatic Surgery.

Journal of hepato-biliary-pancreatic sciences·2026
Same author

Inherent tissue homeostasis of the juvenile metaphysis provides a foundation for osteosarcoma development.

Nature communications·2026
Same author

Role of Upregulated Mucin 21 in Detached Lung Cancer Cells.

Pathology international·2026
Same author

TANC1::HTRA1 and KPNA4::WWTR1 fusions in non-vestibular intracranial schwannomas.

Acta neuropathologica·2026

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.6K

Detecting immunotherapy-sensitive subtype in gastric cancer using histologic image-based deep learning.

Munetoshi Hinata1, Tetsuo Ushiku2

  • 1Department of Pathology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-0033, Japan.

Scientific Reports
|November 23, 2021
PubMed
Summary

A new deep learning model can identify immunotherapy-sensitive gastric cancer subtypes (Epstein-Barr virus-positive and microsatellite instability/mismatch repair deficient) using histology images, offering a cost-effective screening tool.

More Related Videos

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.6K
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Area of Science:

  • Oncology
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Immune checkpoint inhibitor (ICI) therapy efficacy in gastric cancer is limited to specific patient subgroups.
  • Epstein-Barr virus (EBV)-positive and microsatellite instability (MSI)/mismatch repair deficient (dMMR) gastric cancers are known to respond well to ICIs.
  • Current detection methods for these subtypes involve expensive immunohistochemistry and molecular testing.

Purpose of the Study:

  • To develop and validate a histology-based deep learning model for efficient screening of EBV-positive and MSI/dMMR gastric cancer subtypes.
  • To assess the model's accuracy in identifying the combined EBV+/MSI/dMMR subgroup compared to separate detection.
  • To explore the histological features identified by the model as predictive of immunotherapy response.

Main Methods:

  • Whole slide images from 408 gastric adenocarcinoma cases were processed.
  • A convolutional neural network was trained using data augmentation techniques to detect EBV and MSI/dMMR subtypes.
  • The model's performance was evaluated on test sets and an external validation cohort from The Cancer Genome Atlas (TCGA).

Main Results:

  • The deep learning model achieved high accuracy in detecting the EBV+/MSI/dMMR subgroup, with an AUC of 0.947 in test cases.
  • The model demonstrated favorable performance in an external validation cohort (TCGA), with an AUC of 0.870.
  • Intraepithelial lymphocytosis was identified as a key histological feature driving the model's predictions for both EBV and MSI/dMMR tumors.

Conclusions:

  • Histology-based deep learning offers an economical and rapid alternative for identifying EBV and MSI/dMMR gastric cancers.
  • This approach can aid in effectively stratifying gastric cancer patients who are likely to respond to immune checkpoint inhibitor therapy.
  • The model's ability to identify shared histological features provides insights into the underlying biology of these immunotherapy-sensitive tumors.