Artificial intelligence for endoscopic grading of gastric intestinal metaplasia: advancing risk stratification for gastric cancer
Endoscopy · 2025-11 · 57 (11) · 1254-1260
DOI: 10.1055/a-2657-9906 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy, online erschienen am 08.09.2025. Verfasst von Eduarda Almeida und 9 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência - INESC TEC, Porto, Portugal. Hauptthemen laut MEDLINE: Stomach Neoplasms, Artificial Intelligence, Gastroscopy, Gastric Mucosa. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation, Fundação para a Ciência e a Tecnologia, NextGenerationEU.
Abstract (Originalsprache)
The Endoscopic Grading of Gastric Intestinal Metaplasia (EGGIM) classification correlates with histological assessment of gastric intestinal metaplasia and enables stratification of gastric cancer risk. We developed and evaluated an artificial intelligence (AI) approach for EGGIM estimation. Two datasets (A and B) with 1280 narrow-band imaging images were used for per-image analysis. Still images with manually selected patches of 224 × 224 pixels, annotated by experts, were used. Dataset A was retrospectively collected from clinical routine; Dataset B (used for per-patient analysis) was prospectively collected and included 65 fully documented patients. To mimic clinical practice, a deep neural network classified image patches into three EGGIM classes (0, 1, 2) and calculated the total per-patient EGGIM score (0–10). On per-image analysis, an accuracy of 87% (95%CI 71%–100%) was obtained. Per-patient EGGIM estimation had an average error of 1.15 (out of 10) and showed 88% (95%CI 80%–96%) accurate clinical decisions for surveillance (EGGIM ≥5), with 85% (95%CI 75%–94%) specificity, no false negatives, and positive and negative predictive values of 62% (95%CI 32%–92%) and 100% (95%CI 100%–100%), respectively. EGGIM was estimated with high accuracy using AI tools in endoscopic image analyses. Automated assessment of EGGIM may provide a greener strategy for gastric cancer risk stratification, prospective studies, and interventional trials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência - INESC TEC, Porto, Portugal.
- Faculdade de Ciências da Universidade do Porto (FCUP), Porto, Portugal.
- Département STIC, École Nationale Supérieure de Techniques Avancées Bretagne, Brest, France.
- Precancerous Lesions and Early Cancer Management Group, Research Center of IPO Porto (CI-IPOP)/CI-IPOP@RISE (Health Research Group), Portuguese Institute of Oncology of Porto (IPO Porto)/Porto Comprehensive Cancer Cente…
- Gastroenterology Department, Portuguese Institute of Oncology of Porto, Porto, Portugal.
ORCID-Profile: Eduarda Almeida
Förderung
- UK Research and Innovation
- Fundação para a Ciência e a Tecnologia
- NextGenerationEU
- HORIZON EUROPE Framework Programme
Zitieren
APA
Almeida, E., Martins, M. L., Marques, D., Delas, R., Almeida, T., Chaves, J., Libânio, D., Renna, F., Coimbra, M. T., & Dinis-Ribeiro, M. (2025). Artificial intelligence for endoscopic grading of gastric intestinal metaplasia: advancing risk stratification for gastric cancer. Endoscopy, 57(11), 1254-1260. https://doi.org/10.1055/a-2657-9906
Vancouver
Almeida E, Martins ML, Marques D, Delas R, Almeida T, Chaves J, et al. Artificial intelligence for endoscopic grading of gastric intestinal metaplasia: advancing risk stratification for gastric cancer. Endoscopy. 2025;57(11):1254-1260. doi:10.1055/a-2657-9906
BibTeX
@article{Almeida2025,
author = {Almeida, Eduarda and Martins, Miguel Lopes and Marques, David and Delas, Rose and Almeida, Tatiana and Chaves, Jéssica and Libânio, Diogo and Renna, Francesco and Coimbra, Miguel Tavares and Dinis-Ribeiro, Mário},
title = {Artificial intelligence for endoscopic grading of gastric intestinal metaplasia: advancing risk stratification for gastric cancer},
journal = {Endoscopy},
year = {2025},
volume = {57},
number = {11},
pages = {1254--1260},
doi = {10.1055/a-2657-9906}
}
EUVIMED