TY - JOUR
T1 - The use of a real-time computer-aided detection system for visible lesions in the Barrett's esophagus during live endoscopic procedures
T2 - a pilot study (with video)
AU - BONS-AI consortium
AU - Fockens, Kiki N.
AU - Jukema, Jelmer B.
AU - Jong, Martijn R.
AU - Boers, Tim G.
AU - van der Putten, Joost A.
AU - Kusters, Carolus H.J.
AU - Pouw, Roos E.
AU - Duits, Lucas C.
AU - der Sommen, Fons van
AU - de With, Peter H.
AU - de Groof, A. Jeroen
AU - Bergman, Jacques J.
AU - Alkhalaf, Alaa
AU - Herrero, Lorenza Alvarez
AU - Baldaque-Silva, Francisco
AU - Barret, Maximilien
AU - Beyna, Torsten
AU - Boers, Tim G.
AU - Elbe, Peter
AU - de Groof, Albert J.
AU - Houben, Martin H.
AU - Jong, Martijn
AU - Kusters, Koen C.
AU - Mallant-Hent, Rosalie C.
AU - Villarejo, Guiomar Moral
AU - Nagengast, Wouter
AU - Fernández-Sordo, Jacobo Ortiz
AU - Pech, Oliver
AU - Ragunath, Krish
AU - Scholten, Pieter
AU - Seewald, Stefan
AU - der Sommen, Fons van
AU - Westerhof, Jessie
AU - Weusten, Bas L.
AU - de With, Peter H N
N1 - Publisher Copyright:
© 2024 American Society for Gastrointestinal Endoscopy
PY - 2024/9
Y1 - 2024/9
N2 - Background and Aims: This pilot study evaluated the performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures. Methods: Fifteen patients with a visible lesion and 15 without were included in this study. A CAD-assisted workflow was used 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 2 cm of the Barrett's segment. Outcomes were per-patient and per-level diagnostic accuracy of the CAD-assisted workflow, in which the primary outcome was per-patient in vivo CADe sensitivity. 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. Conclusions: In this pilot study, detection by the CADe system of all potentially neoplastic lesions in Barrett's esophagus was comparable to that of an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned. (Clinical trial registration number: NCT05628441.)
AB - Background and Aims: This pilot study evaluated the performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures. Methods: Fifteen patients with a visible lesion and 15 without were included in this study. A CAD-assisted workflow was used 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 2 cm of the Barrett's segment. Outcomes were per-patient and per-level diagnostic accuracy of the CAD-assisted workflow, in which the primary outcome was per-patient in vivo CADe sensitivity. 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. Conclusions: In this pilot study, detection by the CADe system of all potentially neoplastic lesions in Barrett's esophagus was comparable to that of an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned. (Clinical trial registration number: NCT05628441.)
UR - https://www.scopus.com/pages/publications/85197053713
U2 - 10.1016/j.gie.2024.04.011
DO - 10.1016/j.gie.2024.04.011
M3 - Article
C2 - 38604297
AN - SCOPUS:85197053713
SN - 0016-5107
VL - 100
SP - 527
EP - 531
JO - Gastrointestinal endoscopy
JF - Gastrointestinal endoscopy
IS - 3
ER -