Related Experiment Video
Updated: May 14, 2026
08:05
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Artificial Intelligence for Tumor Tissue Detection in Stomach Cancer: A Retrospective Algorithm Development and
Nikolay Karnaukhov1,2, Vincenzo Davide Palumbo3, Mark Voloshin1
1A.S. Loginov Moscow Clinical Scientific Center, 111123 Moscow, Russia.
Journal of Clinical Medicine
|May 13, 2026
Summary
Artificial intelligence (AI) algorithms were developed to diagnose gastric lesions from digitized slides, improving accuracy and risk stratification. This AI tool aids in reducing diagnostic errors and enhancing patient survival prediction for gastric cancer.
Area of Science:
- Digital pathology
- Artificial intelligence in medicine
- Oncology
Background:
- Gastric cancer is a leading cause of cancer mortality globally.
- Effective diagnostic strategies for gastric lesions are urgently needed.
- This study focuses on developing AI for gastric lesion diagnosis using digitized histology.
Purpose of the Study:
- To develop and validate artificial intelligence (AI) algorithms for diagnosing gastric cancer and precancerous lesions.
- To create a prognostic scoring system for predicting fatal outcomes in gastric cancer patients.
- To improve diagnostic accuracy and risk stratification in gastric pathology.
Main Methods:
- A deep learning tool was developed using 970 digitized gastric biopsy slides.
- Convolutional neural networks (CNNs) were trained for histological recognition and ICD-10 code assignment.
- The AI model was validated on 250 cases, with performance assessed by sensitivity, specificity, and Cohen's kappa. Survival analysis was performed using Kaplan-Meier and log-rank tests.
Main Results:
- A prognostic scoring system based on age and morphology predicted significantly worse survival for high-risk patients (4-5 points) compared to low-risk patients (0-3 points).
- One-year survival rates were 71% for low-risk and 40% for high-risk patients.
- The AI algorithm achieved 79.6% sensitivity and 86.7% specificity in differentiating malignant from benign gastric lesions in the test cohort.
Conclusions:
- An AI-based system combined with a prognostic scoring model can reduce diagnostic errors in gastric cancer pathology.
- The developed system improves risk stratification for gastric cancer patients.
- This approach holds potential for enhancing patient outcomes through more accurate diagnosis and prognosis.