Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study
Histopathology · 2026-12 · 89 (6) · 1042-1055
DOI: 10.1111/his.70258 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Histopathology, online erschienen am 15.08.2026. Verfasst von Ho Heon Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: AI R&D Center, Seegene Medical Foundation, Seoul, Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Gastritis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Aims
The Updated Sydney System is the most widely used framework for histological grading of gastritis, but complete grading in routine gastric biopsies is time‐consuming and subject to interobserver variability. We developed an artificial intelligence (AI) system to support comprehensive and reproducible grading of all five Updated Sydney attributes in gastric biopsies. Methods and results We developed SydneyMTL, a weakly supervised multi‐task multiple instance learning framework trained on 50,765 whole‐slide images from routine practice. The model jointly predicts mononuclear cell infiltration, neutrophil activity, glandular atrophy, intestinal metaplasia and Helicobacter pylori density, with atrophy including a separate not applicable category when muscularis mucosae is absent. Performance was assessed against routine labels from 24 board‐certified pathologists and against a consensus‐adjudicated Golden dataset. SydneyMTL achieved a mean lenient accuracy of 89.1% across the 24 pathologists, with >80% agreement for 21 of 24 readers on the retrospective dataset. In a two‐reader randomized crossover study, AI assistance improved interobserver agreement and reduced review time by 34.2% for complete Updated Sydney grading.
Conclusions
AI can support more reproducible and efficient grading of Updated Sydney histological attributes in gastric biopsies. By combining multi‐pathologist validation, consensus‐based evaluation and explicit handling of non‐assessable atrophy, SydneyMTL provides a clinically realistic decision‐support approach for routine digital pathology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- AI R&D Center, Seegene Medical Foundation, Seoul, Korea.
- Department of Medical Sciences, Graduate School, The Catholic University of Korea, Seoul, Korea.
- Pathology Center, Seegene Medical Foundation, Seoul, Korea.
ORCID-Profile: Ho Heon Kim, Won Chan Jeong, Yuri Hwang, Gisu Hwang, Kyungeun Kim, Young Sin Ko
Zitieren
APA
Kim, H. H., Jeong, W. C., Hwang, Y., Hwang, G., Kim, K., & Ko, Y. S. (2026). Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study. Histopathology, 89(6), 1042-1055. https://doi.org/10.1111/his.70258
Vancouver
Kim HH, Jeong WC, Hwang Y, Hwang G, Kim K, Ko YS. Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study. Histopathology. 2026;89(6):1042-1055. doi:10.1111/his.70258
BibTeX
@article{Kim2026,
author = {Kim, Ho Heon and Jeong, Won Chan and Hwang, Yuri and Hwang, Gisu and Kim, Kyungeun and Ko, Young Sin},
title = {Comprehensive and reproducible grading of the Updated Sydney System in gastric biopsies using artificial intelligence: multi‐pathologist validation and a reader study},
journal = {Histopathology},
year = {2026},
volume = {89},
number = {6},
pages = {1042--1055},
doi = {10.1111/his.70258}
}
EUVIMED