Designing a Computer-Aided Detection system for Barrett ’s neoplasia: Insights in architectural choices, training strategies and inference approaches
This study provides critical insights into the structured development of effective CADe systems for Barrett's neoplasia detection. By addressing the specific challenges associated with endoscopic imaging and Barrett's neoplasia, the study demonstrates that careful consideration of architectural choices, training strategies, and inference approaches results in significantly improved CADe performance. These findings underscore the importance of tailored design and optimization in developing robust and clinically effective CADe systems. The code is made publicly available at: https://github.com/BONS-AI-VCA-AMC/Insights-CADe-BE.
Authors
- Kiki Fockens
- Peter H. N. de With (ORCID: https://orcid.org/0000-0002-7639-7716)
- Martijn R. Jong (ORCID: https://orcid.org/0000-0002-8593-3875)
- Tim J. M. Jaspers (ORCID: https://orcid.org/0009-0001-8306-5058)
- Jacques J.G.H.M. Bergman (ORCID: https://orcid.org/0000-0001-7548-6955)
- Carolus H. J. Kusters (ORCID: https://orcid.org/0009-0004-3114-3888)
- Jelmer B. Jukema (ORCID: https://orcid.org/0000-0002-4536-8349)
- Fons van der Sommen (ORCID: https://orcid.org/0000-0002-3593-2356)
- Rixta A. H. van Eijck van Heslinga
- Albert J. de Groof
Institutions
- Amsterdam University Medical Centers (NL)
- Eindhoven University of Technology (NL)
- University of Amsterdam (NL)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2025-06-18
- DOI
- https://doi.org/10.1016/j.cmpb.2025.108891
- Citations
- 1
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Olympus