The use of a real-time computer-aided detection system for visible lesions in the Barrett's esophagus during live endoscopic procedures, a pilot study.
Journal
Gastrointestinal endoscopy
ISSN: 1097-6779
Titre abrégé: Gastrointest Endosc
Pays: United States
ID NLM: 0010505
Informations de publication
Date de publication:
09 Apr 2024
09 Apr 2024
Historique:
received:
10
08
2023
revised:
07
03
2024
accepted:
01
04
2024
medline:
12
4
2024
pubmed:
12
4
2024
entrez:
11
4
2024
Statut:
aheadofprint
Résumé
In this pilot study we evaluated performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures. 15 patients with and 15 without a visible lesion were included in this study. A CAD assisted workflow was employed that included: a slow pullback video recording of the entire Barrett's segment with live CADe assistance, followed by CADe assisted level-based video recordings every 2cm of the Barrett's segment. Outcomes were per patient and per level diagnostic accuracy of the CAD assisted workflow, where the primary outcome was per patient in-vivo CADe sensitivity. In the per patient analyses, the CADe system detected all visible lesions (sensitivity 100%). Per patient CADe specificity was 53%. Per-level sensitivity and specificity of the CADe assisted workflow were 100% and 73%, respectively. In this pilot study, the CADe system detected all potentially neoplastic lesions in Barrett's esophagus comparable to an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned.
Sections du résumé
BACKGROUND AND AIMS
OBJECTIVE
In this pilot study we evaluated performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures.
METHODS
METHODS
15 patients with and 15 without a visible lesion were included in this study. A CAD assisted workflow was employed that included: a slow pullback video recording of the entire Barrett's segment with live CADe assistance, followed by CADe assisted level-based video recordings every 2cm of the Barrett's segment. Outcomes were per patient and per level diagnostic accuracy of the CAD assisted workflow, where the primary outcome was per patient in-vivo CADe sensitivity.
RESULTS
RESULTS
In the per patient analyses, the CADe system detected all visible lesions (sensitivity 100%). Per patient CADe specificity was 53%. Per-level sensitivity and specificity of the CADe assisted workflow were 100% and 73%, respectively.
CONCLUSION
CONCLUSIONS
In this pilot study, the CADe system detected all potentially neoplastic lesions in Barrett's esophagus comparable to an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned.
Identifiants
pubmed: 38604297
pii: S0016-5107(24)00228-1
doi: 10.1016/j.gie.2024.04.011
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2024 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.