Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions
Endoscopy · 01.12.2025 · 57 (12) · 1327-1337
DOI: 10.1055/a-2642-7584 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Endoscopy, erschienen am 01.12.2025. Verfasst von Martijn R Jong und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology, Endocrinology and Metabolism, Amsterdam UMC, University of Amsterdam, Amst…. Hauptthemen laut MEDLINE: Barrett Esophagus, Esophageal Neoplasms, Esophagoscopy, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: KWF Kankerbestrijding, DANAE project, supported by the NWO/KWF foundation, Nederlandse Organisatie voor Wetenschappelijk Onderzoek.
Abstract (Originalsprache)
Background
Computer-aided detection (CADe) systems may improve detection of Barrett’s neoplasia. Most CADe systems are developed with data from expert centers, unrepresentative of heterogeneous imaging conditions in community hospitals, and therefore may underperform in routine practice. We aimed to develop a robust CADe system (CADe 2.0) and compare its performance to a previously published system (CADe 1.0) under heterogeneous imaging conditions representative of real-world clinical practice.
Method
CADe 2.0 was improved through a larger and more diverse training dataset, optimized pretraining, data augmentation, ground truth use, and architectural adjustments. CADe systems were evaluated using three prospective test sets. Test set 1 comprised 428 Barrett’s videos (114 patients across five referral centers). Test set 2 addressed endoscopist-dependent variation (e. g. mucosal cleaning and esophageal expansion), with paired subsets of high, moderate, and low quality images (122 patients). Test set 3 addressed endoscopist-independent variation, with 16 paired subsets of 396 images (122 patients), each being based on a different software image-enhancement setting.
Results
CADe 2.0 outperformed CADe 1.0 on all three test sets. In test set 1, sensitivity increased significantly from 87 % to 96 % (P = 0.02), while specificity remained comparable (73 % vs. 74 %; P = 0.73). In test set 2, CADe 2.0 consistently surpassed CADe 1.0 across all image quality levels, with the largest performance gains observed on lower quality images (sensitivity 78 % vs. 61 %; specificity 89 % vs. 77 %; area under the curve 89 % vs. 75 %). In test set 3, CADe 2.0 showed improved performance and displayed reduced performance variability across enhancement settings.
Conclusion
Based on several key improvements, CADe 2.0 demonstrated increased detection rates and better robustness to data heterogeneity, making it ready for clinical implementation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology, Endocrinology and Metabolism, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
- Department of Gastroenterology and Hepatology, St Antonius Hospital, Nieuwegein, The Netherlands.
- Department of Gastroenterology and Hepatology, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
- Department of Gastroenterology and Hepatology, Isala Hospital, Zwolle, The Netherlands.
ORCID-Profile: Bas L A M Weusten, Jacques J Bergman
Förderung
- KWF Kankerbestrijding
- DANAE project, supported by the NWO/KWF foundation
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Zitieren
APA
Jong, M. R., van Eijck van Heslinga, R. A. H., Kusters, C. H. J., Jaspers, T. J. M., Boers, T. G. W., Duits, L. C., Pouw, R. E., Weusten, B. L. A. M., Alkhalaf, A., van der Sommen, F., de With, P. H. N., de Groof, A. J., Bergman, J. J., & BONSAI Consortium (2025). Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions. Endoscopy, 57(12), 1327-1337. https://doi.org/10.1055/a-2642-7584
Vancouver
Jong MR, van Eijck van Heslinga RAH, Kusters CHJ, Jaspers TJM, Boers TGW, Duits LC, et al. Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions. Endoscopy. 2025;57(12):1327-1337. doi:10.1055/a-2642-7584
BibTeX
@article{Jong2025,
author = {Jong, Martijn R and van Eijck van Heslinga, Rixta A H and Kusters, Carolus H J and Jaspers, Tim J M and Boers, Tim G W and Duits, Lucas C and Pouw, Roos E and Weusten, Bas L A M and Alkhalaf, Alaa and van der Sommen, Fons and de With, Peter H N and de Groof, Albert J and Bergman, Jacques J and BONSAI Consortium, BONSAI Consortium},
title = {Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions},
journal = {Endoscopy},
year = {2025},
volume = {57},
number = {12},
pages = {1327--1337},
doi = {10.1055/a-2642-7584}
}
EUVIMED