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 (with video)

BONS-AI consortium; Tim Boers; Joost A. van der Putten; Koen Kusters; Fons van der Sommen; Peter H.N. de With; Jacques B. Bergman

doi:10.1016/j.gie.2024.04.011

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 (with video)

BONS-AI consortium
, Tim Boers
, Joost A. van der Putten
, Koen Kusters
, Fons van der Sommen
, Peter H.N. de With
, Jacques B. Bergman (Corresponding author)

Research output: Contribution to journal › Article › Academic › peer-review

10 Citations (Scopus)

35 Downloads (Pure)

Abstract

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.)

Original language	English
Pages (from-to)	527-531.e3
Number of pages	8
Journal	Gastrointestinal Endoscopy
Volume	100
Issue number	3
Early online date	9 Apr 2024
DOIs	https://doi.org/10.1016/j.gie.2024.04.011
Publication status	Published - Sept 2024

Bibliographical note

The authors thank the members and collaborators of the BONS-AI consortium, as listed here in alphabetical order: Alaa Alkhalaf, Isala Hospital, Zwolle, the Netherlands; Lorenza Alvarez Herrero, St. Antonius Hospital, Utrecht, the Netherlands; Francisco Baldaque-Silva, Karolinska University Hospital, Stockholm, Sweden; Maximilien Barret, Cochin Hospital, Paris, France; Jacques J. Bergman, Amsterdam UMC, Amsterdam, the Netherlands; Torsten Beyna, Evangelisches Krankenhaus D\u00FCsseldorf, D\u00FCsseldorf, Germany; Tim G. Boers, TU Eindhoven, Eindhoven, the Netherlands; Peter Elbe, Karolinska University Hospital and Karolinska Institute, Stockholm, Sweden; Kiki N. Fockens, Amsterdam UMC, Amsterdam, the Netherlands; Albert J. de Groof, Amsterdam UMC, Amsterdam, the Netherlands; Martin H. Houben, HagaZiekenhuis, The Hague, the Netherlands; Martijn Jong, Amsterdam UMC, Amsterdam, the Netherlands; Jelmer B. Jukema, Amsterdam UMC, Amsterdam, the Netherlands; Koen C. Kusters, TU Eindhoven, Eindhoven, the Netherlands; Rosalie C. Mallant-Hent, Flevoziekenhuis, Almere, the Netherlands; Guiomar Moral Villarejo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Wouter Nagengast, UMC Groningen, Groningen, the Netherlands; Jacobo Ortiz Fern\u00E1ndez-Sordo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Oliver Pech, St. John of God Hospital, Regensburg, Germany; Roos E. Pouw, Amsterdam UMC, Amsterdam, the Netherlands; Joost A. van der Putten, TU Eindhoven, Eindhoven, the Netherlands; Krish Ragunath, Royal Perth Hospital, Perth, Australia; Pieter Scholten, Onze Lieve Vrouwe Gasthuis, Amsterdam, the Netherlands; Stefan Seewald, Klinik Hirslanden, Zurich, Switzerland; Fons van der Sommen, TU Eindhoven, Eindhoven, the Netherlands; Jessie Westerhof, UMC Groningen, Groningen, the Netherlands; Bas L. Weusten, UMC Utrecht & St. Antonius Hospital, Utrecht, the Netherlands; and Peter H. de With, TU Eindhoven, Eindhoven, the Netherlands. Research support provided by Olympus Tokyo.

Keywords

Adenocarcinoma/pathology
Aged
Aged, 80 and over
Barrett Esophagus/pathology
Diagnosis, Computer-Assisted
Esophageal Neoplasms/pathology
Esophagoscopy/methods
Female
Humans
Male
Middle Aged
Pilot Projects
Sensitivity and Specificity
Video Recording

Access to Document

10.1016/j.gie.2024.04.011

pdfFinal published version, 1.96 MBLicence: CC BY

Cite this

BONS-AI consortium, Boers, T., van der Putten, J. A., Kusters, K., van der Sommen, F., de With, P. H. N., & Bergman, J. B. (2024). 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 (with video). Gastrointestinal Endoscopy, 100(3), 527-531.e3. https://doi.org/10.1016/j.gie.2024.04.011

@article{3faffb87f1b44562a3d8eb1c43eed16d,

title = "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 (with video)",

abstract = "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.)",

keywords = "Adenocarcinoma/pathology, Aged, Aged, 80 and over, Barrett Esophagus/pathology, Diagnosis, Computer-Assisted, Esophageal Neoplasms/pathology, Esophagoscopy/methods, Female, Humans, Male, Middle Aged, Pilot Projects, Sensitivity and Specificity, Video Recording",

author = "\{BONS-AI consortium\} and Fockens, \{Kiki N.\} and Jukema, \{Jelmer B.\} and Jong, \{Martijn R.\} and Tim Boers and \{van der Putten\}, \{Joost A.\} and Koen Kusters and Pouw, \{Roos E.\} and Duits, \{Lucas C.\} and \{van der Sommen\}, Fons and \{de With\}, \{Peter H.N.\} and \{de Groof\}, \{Albert J. (Jeroen)\} and Bergman, \{Jacques B.\}",

note = "The authors thank the members and collaborators of the BONS-AI consortium, as listed here in alphabetical order: Alaa Alkhalaf, Isala Hospital, Zwolle, the Netherlands; Lorenza Alvarez Herrero, St. Antonius Hospital, Utrecht, the Netherlands; Francisco Baldaque-Silva, Karolinska University Hospital, Stockholm, Sweden; Maximilien Barret, Cochin Hospital, Paris, France; Jacques J. Bergman, Amsterdam UMC, Amsterdam, the Netherlands; Torsten Beyna, Evangelisches Krankenhaus D\textbackslash{}u00FCsseldorf, D\textbackslash{}u00FCsseldorf, Germany; Tim G. Boers, TU Eindhoven, Eindhoven, the Netherlands; Peter Elbe, Karolinska University Hospital and Karolinska Institute, Stockholm, Sweden; Kiki N. Fockens, Amsterdam UMC, Amsterdam, the Netherlands; Albert J. de Groof, Amsterdam UMC, Amsterdam, the Netherlands; Martin H. Houben, HagaZiekenhuis, The Hague, the Netherlands; Martijn Jong, Amsterdam UMC, Amsterdam, the Netherlands; Jelmer B. Jukema, Amsterdam UMC, Amsterdam, the Netherlands; Koen C. Kusters, TU Eindhoven, Eindhoven, the Netherlands; Rosalie C. Mallant-Hent, Flevoziekenhuis, Almere, the Netherlands; Guiomar Moral Villarejo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Wouter Nagengast, UMC Groningen, Groningen, the Netherlands; Jacobo Ortiz Fern\textbackslash{}u00E1ndez-Sordo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Oliver Pech, St. John of God Hospital, Regensburg, Germany; Roos E. Pouw, Amsterdam UMC, Amsterdam, the Netherlands; Joost A. van der Putten, TU Eindhoven, Eindhoven, the Netherlands; Krish Ragunath, Royal Perth Hospital, Perth, Australia; Pieter Scholten, Onze Lieve Vrouwe Gasthuis, Amsterdam, the Netherlands; Stefan Seewald, Klinik Hirslanden, Zurich, Switzerland; Fons van der Sommen, TU Eindhoven, Eindhoven, the Netherlands; Jessie Westerhof, UMC Groningen, Groningen, the Netherlands; Bas L. Weusten, UMC Utrecht \& St. Antonius Hospital, Utrecht, the Netherlands; and Peter H. de With, TU Eindhoven, Eindhoven, the Netherlands. Research support provided by Olympus Tokyo.",

year = "2024",

month = sep,

doi = "10.1016/j.gie.2024.04.011",

language = "English",

volume = "100",

pages = "527--531.e3",

journal = "Gastrointestinal Endoscopy",

issn = "0016-5107",

publisher = "Elsevier",

number = "3",

}

BONS-AI consortium, Boers, T , van der Putten, JA , Kusters, K , van der Sommen, F , de With, PHN & Bergman, JB 2024, '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 (with video)', Gastrointestinal Endoscopy, vol. 100, no. 3, pp. 527-531.e3. https://doi.org/10.1016/j.gie.2024.04.011

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 (with video). / BONS-AI consortium ; Boers, Tim ; van der Putten, Joost A. et al.
In: Gastrointestinal Endoscopy, Vol. 100, No. 3, 09.2024, p. 527-531.e3.

Research output: Contribution to journal › Article › Academic › peer-review

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

AU - van der Putten, Joost A.

AU - Kusters, Koen

AU - Pouw, Roos E.

AU - Duits, Lucas C.

AU - van der Sommen, Fons

AU - de With, Peter H.N.

AU - de Groof, Albert J. (Jeroen)

AU - Bergman, Jacques B.

N1 - The authors thank the members and collaborators of the BONS-AI consortium, as listed here in alphabetical order: Alaa Alkhalaf, Isala Hospital, Zwolle, the Netherlands; Lorenza Alvarez Herrero, St. Antonius Hospital, Utrecht, the Netherlands; Francisco Baldaque-Silva, Karolinska University Hospital, Stockholm, Sweden; Maximilien Barret, Cochin Hospital, Paris, France; Jacques J. Bergman, Amsterdam UMC, Amsterdam, the Netherlands; Torsten Beyna, Evangelisches Krankenhaus D\u00FCsseldorf, D\u00FCsseldorf, Germany; Tim G. Boers, TU Eindhoven, Eindhoven, the Netherlands; Peter Elbe, Karolinska University Hospital and Karolinska Institute, Stockholm, Sweden; Kiki N. Fockens, Amsterdam UMC, Amsterdam, the Netherlands; Albert J. de Groof, Amsterdam UMC, Amsterdam, the Netherlands; Martin H. Houben, HagaZiekenhuis, The Hague, the Netherlands; Martijn Jong, Amsterdam UMC, Amsterdam, the Netherlands; Jelmer B. Jukema, Amsterdam UMC, Amsterdam, the Netherlands; Koen C. Kusters, TU Eindhoven, Eindhoven, the Netherlands; Rosalie C. Mallant-Hent, Flevoziekenhuis, Almere, the Netherlands; Guiomar Moral Villarejo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Wouter Nagengast, UMC Groningen, Groningen, the Netherlands; Jacobo Ortiz Fern\u00E1ndez-Sordo, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom; Oliver Pech, St. John of God Hospital, Regensburg, Germany; Roos E. Pouw, Amsterdam UMC, Amsterdam, the Netherlands; Joost A. van der Putten, TU Eindhoven, Eindhoven, the Netherlands; Krish Ragunath, Royal Perth Hospital, Perth, Australia; Pieter Scholten, Onze Lieve Vrouwe Gasthuis, Amsterdam, the Netherlands; Stefan Seewald, Klinik Hirslanden, Zurich, Switzerland; Fons van der Sommen, TU Eindhoven, Eindhoven, the Netherlands; Jessie Westerhof, UMC Groningen, Groningen, the Netherlands; Bas L. Weusten, UMC Utrecht & St. Antonius Hospital, Utrecht, the Netherlands; and Peter H. de With, TU Eindhoven, Eindhoven, the Netherlands. Research support provided by Olympus Tokyo.

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.)

KW - Adenocarcinoma/pathology

KW - Aged

KW - Aged, 80 and over

KW - Barrett Esophagus/pathology

KW - Diagnosis, Computer-Assisted

KW - Esophageal Neoplasms/pathology

KW - Esophagoscopy/methods

KW - Female

KW - Humans

KW - Male

KW - Middle Aged

KW - Pilot Projects

KW - Sensitivity and Specificity

KW - Video Recording

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 - 527-531.e3

JO - Gastrointestinal Endoscopy

JF - Gastrointestinal Endoscopy

IS - 3

ER -

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 (with video)

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this