Towards a robust and compact deep learning system for primary detection of early Barrett’s neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set

Kiki N. Fockens, Jelmer B. Jukema, Tim Boers, Martijn R. Jong, Joost A. van der Putten, Roos E. Pouw, Bas L.A.M. Weusten, Lorenza Alvarez Herrero, Martin H.M.G. Houben, Wouter B. Nagengast, Jessie Westerhof, Alaa Alkhalaf, Rosalie Mallant, Krish Ragunath, Stefan Seewald, Peter Elbe, Maximilien Barret, Jacobo Ortiz Fernández-Sordo, Oliver Pech, Torsten BeynaFons van der Sommen, Peter H. de With, A. Jeroen de Groof (Corresponding author), Jacques J. Bergman

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)
2 Downloads (Pure)

Abstract

Introduction: Endoscopic detection of early neoplasia in Barrett's esophagus is difficult. Computer Aided Detection (CADe) systems may assist in neoplasia detection. The aim of this study was to report the first steps in the development of a CADe system for Barrett's neoplasia and to evaluate its performance when compared with endoscopists. Methods: This CADe system was developed by a consortium, consisting of the Amsterdam University Medical Center, Eindhoven University of Technology, and 15 international hospitals. After pretraining, the system was trained and validated using 1.713 neoplastic (564 patients) and 2.707 non-dysplastic Barrett's esophagus (NDBE; 665 patients) images. Neoplastic lesions were delineated by 14 experts. The performance of the CADe system was tested on three independent test sets. Test set 1 (50 neoplastic and 150 NDBE images) contained subtle neoplastic lesions representing challenging cases and was benchmarked by 52 general endoscopists. Test set 2 (50 neoplastic and 50 NDBE images) contained a heterogeneous case-mix of neoplastic lesions, representing distribution in clinical practice. Test set 3 (50 neoplastic and 150 NDBE images) contained prospectively collected imagery. The main outcome was correct classification of the images in terms of sensitivity. Results: The sensitivity of the CADe system on test set 1 was 84%. For general endoscopists, sensitivity was 63%, corresponding to a neoplasia miss-rate of one-third of neoplastic lesions and a potential relative increase in neoplasia detection of 33% for CADe-assisted detection. The sensitivity of the CADe system on test sets 2 and 3 was 100% and 88%, respectively. The specificity of the CADe system varied for the three test sets between 64% and 66%. Conclusion: This study describes the first steps towards the establishment of an unprecedented data infrastructure for using machine learning to improve the endoscopic detection of Barrett's neoplasia. The CADe system detected neoplasia reliably and outperformed a large group of endoscopists in terms of sensitivity.

Original languageEnglish
Pages (from-to)324-336
Number of pages13
JournalUnited European Gastroenterology Journal
Volume11
Issue number4
DOIs
Publication statusPublished - May 2023

Keywords

  • artificial intelligence
  • Barrett's esophagus
  • Barrett's neoplasia
  • computer aided detection
  • endoscopy
  • machine learning

Fingerprint

Dive into the research topics of 'Towards a robust and compact deep learning system for primary detection of early Barrett’s neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set'. Together they form a unique fingerprint.

Cite this