UEG's educational platform for gastroenterology education bringing recordings, courses, guidelines, and more together in one place.

UEG Week Berlin 2025 Recordings Gut Guide online What's new on Gutflix

Trending on Gutflix

Rate for better recommendations!

Your feedback helps us show you more of what you like and less of what you dislike!

More of this!

We will show you more similar content.

Not for me!

We won't suggest this again.

Bookmark!

Save this content for later!

New to myUEG? Create an account! Log In with myUEG account

UEG Poster

Audio / Video Poster

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

This content is part of Gutflix. Log in with your myUEG account, or create one free, to watch it.

Not sure what you can access? Learn more about account types.

DIGITAL PATHOLOGY-BASED DEEP LEARNING SIGNATURE PREDICTS IMMUNOTHERAPY OUTCOMES IN GASTRIC CANCER

Nan Zhang 1, Hong Xu 1, Luping Zhang 1, Ying Li 1

Affiliations

1 The First Hospital of Jilin University, Changchun, China

Summary

AI Generated

A deep learning model analyzing digital pathology images (DPIRS) was developed to predict immunotherapy response in gastric cancer patients, achieving AUC >0.85 in validation cohorts.

Retrospective study of 110 gastric cancer patients receiving immune checkpoint inhibitors at a single center between 2019–2023 used ResNet18 neural network trained on H&E-stained whole-slide images segmented into 256×256 pixel tiles.
Patients with high DPIRS scores had significantly longer progression-free survival and overall survival (p<0.01), higher PD-L1 expression, and greater tumor-infiltrating lymphocyte density compared to those with low scores.
Multivariate Cox regression confirmed DPIRS as an independent prognostic factor for immunotherapy efficacy, with model performance validated in internal and TCGA cohorts.
The authors characterize DPIRS as a novel non-invasive biomarker and state it has potential for clinical application in personalized treatment strategies for gastric cancer patients being considered for immunotherapy.

Download PDF

Was this helpful?

Thanks for your feedback.

This summary was generated by an AI large language model based on the content transcript. It is for informational purposes only and should not be considered a substitute for clinical judgment. Always rely on your professional expertise and the full clinical context when making clinical decisions.

Abstract

Introduction

Gastric cancer (GC) is a major cause of cancer-related death worldwide. Although immune checkpoint inhibitors (ICIs) have improved outcomes in a subset of patients, only 20–30% achieve long-term benefit. Identifying robust biomarkers to predict immunotherapy response remains a critical need. With the rise of digital pathology and deep learning (DL), it is now possible to derive prognostic features from whole-slide images (WSIs), offering a novel means of evaluating the tumor immune microenvironment.

Aims & Methods

This study aimed to develop a Digital Pathology-based Immunotherapy Response Signature (DPIRS) using DL to predict prognosis in GC patients treated with ICIs. We retrospectively analyzed 110 GC patients receiving ICIs at The First Hospital of Jilin University between 2019–2023. H&E-stained WSIs were segmented into 256×256 pixel tiles. A convolutional neural network (ResNet18) was trained to detect immune-relevant histopathological patterns. The DPIRS score for each patient was defined as the proportion of positively scored image tiles. DPIRS was correlated with progression-free survival (PFS), overall survival (OS), immune checkpoint molecule expression, and immune infiltration characteristics.

Results

The DL model showed excellent predictive performance (AUC >0.85) across internal and TCGA validation cohorts. Patients with high DPIRS scores had significantly longer PFS and OS (p<0.01), as well as higher PD-L1 expression and greater tumor-infiltrating lymphocyte (TIL) density. Multivariate Cox regression confirmed DPIRS as an independent prognostic factor for immunotherapy efficacy.

Conclusion

DPIRS is a novel, non-invasive biomarker derived from deep learning-based analysis of digital pathology, enabling precise prediction of immunotherapy response in gastric cancer. This tool holds strong potential for clinical application in personalized treatment strategies.

Conference

UEG Week Berlin 2025

Topics

Oesophagus

Submission format

Abstract

Session

Early detection and outcomes of upper GI cancer (Posters)

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

More Like This:

See It. Learn It. Use It: The new EUS-FNB needle in action

Andrea Lisotti

NURSE-LED CLINIC (NLC) TO STREAMLINE OPHTHALMOLOGY SCREENING FOR IBD PATIENTS PRIOR TO INITIATING SPHINGOSINE-1-PHOSPHATE RECEPTOR (S1PR) MODULATOR THERAPY

Lucy Hicks

Welcome

Deepa Jegadish Gandhi

Developing a nurse-led counselling service in hepatology across two hospitals

Sonja Beckman

DISTINCT GUT MICROBIAL PROFILES IN LYNCH SYNDROME CARRIERS AND AVERAGE-RISK INDIVIDUALS: IMPLICATIONS FOR COLORECTAL CANCER SURVEILLANCE

Joan Brunet

THE OLIVE TREE: AN ELECTRONIC TOOL TO SAFELY INITIATE PARENTERAL NUTRITION IN ADULT HOSPITALIZED PATIENTS WITH INTESTINAL FAILURE

Tim Vanuytsel

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

See It. Learn It. Use It: The new EUS-FNB needle in action

This content is part of Gutflix. Log in with your myUEG account, or create one free, to watch it.

Not sure what you can access? Learn more about account types.