TY - JOUR
T1 - Towards a robust and compact deep learning system for primary detection of early Barrett’s neoplasia
T2 - Initial image-based results of training on a multi-center retrospectively collected data set
AU - Fockens, Kiki N.
AU - Jukema, Jelmer B.
AU - Boers, Tim
AU - Jong, Martijn R.
AU - van der Putten, Joost A.
AU - Pouw, Roos E.
AU - Weusten, Bas L. A. M.
AU - Alvarez Herrero, Lorenza
AU - Houben, Martin H. M. G.
AU - Nagengast, Wouter B.
AU - Westerhof, Jessie
AU - Alkhalaf, Alaa
AU - Mallant, Rosalie
AU - Ragunath, Krish
AU - Seewald, Stefan
AU - Elbe, Peter
AU - Barret, Maximilien
AU - Ortiz Fernández-Sordo, Jacobo
AU - Pech, Oliver
AU - Beyna, Torsten
AU - van der Sommen, Fons
AU - de With, Peter H.
AU - de Groof, A. Jeroen
AU - Bergman, Jacques J.
N1 - Funding Information: This project was financially supported by Olympus Tokyo, Japan. Publisher Copyright: © 2023 The Authors. United European Gastroenterology Journal published by Wiley Periodicals LLC on behalf of United European Gastroenterology.
PY - 2023/5/1
Y1 - 2023/5/1
N2 - 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.
AB - 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.
KW - Barrett's esophagus
KW - Barrett's neoplasia
KW - artificial intelligence
KW - computer aided detection
KW - endoscopy
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85153605716&partnerID=8YFLogxK
U2 - https://doi.org/10.1002/ueg2.12363
DO - https://doi.org/10.1002/ueg2.12363
M3 - Article
C2 - 37095718
SN - 2050-6406
VL - 11
SP - 324
EP - 336
JO - United European gastroenterology journal
JF - United European gastroenterology journal
IS - 4
ER -