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.
Barrett's esophagus
Barrett's neoplasia
artificial intelligence
computer aided detection
endoscopy
machine learning
Journal
United European gastroenterology journal
ISSN: 2050-6414
Titre abrégé: United European Gastroenterol J
Pays: England
ID NLM: 101606807
Informations de publication
Date de publication:
05 2023
05 2023
Historique:
received:
23
09
2022
accepted:
09
01
2023
medline:
9
5
2023
pubmed:
25
4
2023
entrez:
25
04
2023
Statut:
ppublish
Résumé
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. 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. 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%. 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.
Identifiants
pubmed: 37095718
doi: 10.1002/ueg2.12363
pmc: PMC10165317
doi:
Types de publication
Multicenter Study
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
324-336Informations de copyright
© 2023 The Authors. United European Gastroenterology Journal published by Wiley Periodicals LLC on behalf of United European Gastroenterology.
Références
Endoscopy. 2017 Feb;49(2):113-120
pubmed: 27855466
Gastrointest Endosc. 2020 May;91(5):1050-1057
pubmed: 31904377
Gastroenterology. 2011 Mar;140(3):1084-91
pubmed: 21376940
Gastroenterology. 2020 Mar;158(4):915-929.e4
pubmed: 31759929
Int J Comput Assist Radiol Surg. 2019 Apr;14(4):611-621
pubmed: 30666547
Gut. 2019 Jul;68(7):1143-1145
pubmed: 30510110
Gastrointest Endosc. 2020 Jun;91(6):1242-1250
pubmed: 31926965
Endoscopy. 2017 Feb;49(2):191-198
pubmed: 28122386
Gastrointest Endosc. 2020 Jun;91(6):1264-1271.e1
pubmed: 31930967
Surg Endosc. 2022 Nov;36(11):8316-8325
pubmed: 35508665
Gastroenterology. 2019 Apr;156(5):1299-1308.e3
pubmed: 30610858
United European Gastroenterol J. 2023 May;11(4):324-336
pubmed: 37095718
Gut. 2020 Nov;69(11):2035-2045
pubmed: 32393540
Gut. 2019 Jan;68(1):94-100
pubmed: 29066576