Early detection of esophageal cancer: Evaluating AI algorithms with multi-institutional narrowband and white-light imaging data
PLOS ONE · 2025
DOI: 10.1371/journal.pone.0321092 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift PLOS ONE, 2025. Verfasst von Young Seo Baik und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Gachon University, Seongnam-si, Gyeonggi-do, Republic of Korea. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Early Detection of Cancer, Algorithms, Artificial Intelligence. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gachon University research fund of 2023, Korean Gastrointestinal Endoscopy Research Foundation, Gil Medical Center, Gachon University.
Abstract (Originalsprache)
Esophageal cancer is one of the most common cancers worldwide, especially esophageal squamous cell carcinoma, which is often diagnosed at a late stage and has a poor prognosis. This study aimed to develop an algorithm to detect tumors in esophageal endoscopy images using innovative artificial intelligence (AI) techniques for early diagnosis and detection of esophageal cancer. We used white light and narrowband imaging data collected from Gachon University Gil Hospital, and applied YOLOv5 and RetinaNet detection models to detect lesions. The models demonstrated high performance, with RetinaNet achieving a precision of 98.4% and sensitivity of 91.3% in the NBI dataset, and YOLOv5 attaining a precision of 93.7% and sensitivity of 89.9% in the WLI dataset. The generalizability of these models was further validated using external data from multiple institutions. This study demonstrates an effective method for detecting esophageal tumors through AI-based esophageal endoscopic image analysis. These efforts are expected to significantly reduce misdiagnosis rates, enhance the effective diagnosis and treatment of esophageal cancer, and promote the standardization of medical services.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Engineering, Gachon University, Seongnam-si, Gyeonggi-do, Republic of Korea.
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon, Republic of Korea.
- Department of Gachon Biomedical & Convergence Institute, Gachon University Gil Medical Center, Incheon, Republic of Korea.
- Department of Biomedical Engineering, College of IT Convergence, Gachon University, Seongnam-si, Gyeonggi-do, Republic of Korea.
ORCID-Profile: Kwang Gi Kim
Förderung
- Gachon University research fund of 2023
- Korean Gastrointestinal Endoscopy Research Foundation
- Gil Medical Center, Gachon University
Zitieren
APA
Baik, Y. S., Lee, H., Kim, Y. J., Chung, J. W., & Kim, K. G. (2025). Early detection of esophageal cancer: Evaluating AI algorithms with multi-institutional narrowband and white-light imaging data. PLOS ONE. https://doi.org/10.1371/journal.pone.0321092
Vancouver
Baik YS, Lee H, Kim YJ, Chung JW, Kim KG. Early detection of esophageal cancer: Evaluating AI algorithms with multi-institutional narrowband and white-light imaging data. PLOS ONE. 2025. doi:10.1371/journal.pone.0321092
BibTeX
@article{Baik2025,
author = {Baik, Young Seo and Lee, Hannah and Kim, Young Jae and Chung, Jun-Won and Kim, Kwang Gi},
title = {Early detection of esophageal cancer: Evaluating AI algorithms with multi-institutional narrowband and white-light imaging data},
journal = {PLOS ONE},
year = {2025},
doi = {10.1371/journal.pone.0321092}
}
EUVIMED