Abbonarsi

Computer-aided diagnosis improves characterization of Barrett’s neoplasia by general endoscopists (with video) - 16/10/24

Doi : 10.1016/j.gie.2024.04.013 
Jelmer B. Jukema, MD 1, Carolus H.J. Kusters, MS 2, Martijn R. Jong, MD 1, Kiki N. Fockens, MD, PhD 1, Tim Boers, MS 2, Joost A. van der Putten, PhD 2, Roos E. Pouw, MD, PhD 1, Lucas C. Duits, MD, PhD 1, Bas L.A.M. Weusten, MD, PhD 3, 4, Lorenza Alvarez Herrero, MD, PhD 4, Martin H.M.G. Houben, MD, PhD 5, Wouter B. Nagengast, MD, PhD 6, Jessie Westerhof, MD, PhD 6, Alaa Alkhalaf, MD, PhD 7, Rosalie Mallant-Hent, MD, PhD 8, Pieter Scholten, MD 9, Krish Ragunath, MD, PhD 10, Stefan Seewald, MD, PhD 11, Peter Elbe, MD 12, 13, Francisco Baldaque Silva, MD, PhD 12, 14, Maximilien Barret, MD, PhD 15, Jacobo Ortiz Fernández-Sordo, MD 16, Guiomar Moral Villarejo, MD 16, Oliver Pech, MD, PhD 17, Torsten Beyna, MD, PhD 18, Nahid S.M. Montazeri, PhD 19, Fons van der Sommen, PhD 2, Peter H. de With, PhD 2, A. Jeroen de Groof, MD, PhD 1, Jacques J. Bergman, MD, PhD 1, ⁎
on behalf of the

BONS-AI consortium∗

  All members and collaborators of the BONS-AI consortium are listed in the Supplementary Materials.
Alaa Alkhalaf 20, Lorenza Alvarez Herrero 21, Francisco Baldaque-Silva 22, Maximilien Barret 23, Jacques J. Bergman 24, Torsten Beyna 25, Raf Bisschops 26, Tim G. Boers 27, Wouter Curvers 28, Pierre H. Deprez 29, Lucas C. Duits 30, Peter Elbe 31, Jose Miguel Esteban 32, Gary W. Falk 33, Kiki N. Fockens 34, Gregory G. Ginsberg 35, Albert J. de Groof 36, Rehan Haidry 37, Martin H. Houben 38, Anthony Infantolino 39, Prasad G. Iyer 40, Martijn Jong 41, Pieter-Jan de Jonge 42, Jelmer B. Jukema 43, Arjun Koch 44, Srinadh Komanduri 45, Vani Konda 46, Koen C. Kusters 47, Philippe Leclerq 48, Cadman L. Leggett 49, Charles J. Lightdale 50, Rosalie C. Mallant-Hent 51, Guiomar Moral Villarejo 52, Jacobo Ortiz Fernández-Sordo 53, Oliver Pech 54, Ian Penman 55, Roos E. Pouw 56, Joost A. van der Putten 57, Krish Ragunath 58, Pieter Scholten 59, Stefan Seewald 60, Amritha Sethi 61, Michael S. Smith 62, Fons van der Sommen 63, Arvind Trindade 64, Sachin Wani 65, Irving Waxman 66, Jessie Westerhof 67, Bas L. Weusten 68, Peter H. de With 69, Herbert C. Wolfsen 70
20 Isala Hospital, Zwolle, the Netherlands 
21 St. Antonius Hospital, Utrecht, the Netherlands 
22 Karolinska University Hospital, Stockholm, Sweden 
23 Cochin Hospital, Paris, France 
24 Amsterdam UMC, Amsterdam, the Netherlands 
25 Evangelisches Krankenhaus Düsseldorf, Düsseldorf, Germany 
26 University Hospitals Leuven, Leuven, Belgium 
27 TU Eindhoven, Eindhoven, the Netherlands 
28 Catharina Hospital, Eindhoven, the Netherlands 
29 University Hospital Saint-Luc, Brussels, Belgium 
30 Amsterdam UMC, Amsterdam, the Netherlands 
31 Karolinska University Hospital & Karolinska Institute, Stockholm, Sweden 
32 Clínico San Carlos, Madrid, Spain 
33 Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania, USA 
34 Amsterdam UMC, Amsterdam, the Netherlands 
35 University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA 
36 Amsterdam UMC, Amsterdam, the Netherlands 
37 Cleveland Clinic London and University College Hospitals NHS, London, United Kingdom 
38 HagaZiekenhuis, The Hague, the Netherlands 
39 Thomas Jefferson University Hospital, Philadelphia, Pennsylvania, USA 
40 Mayo Clinic, Rochester, Minnesota, USA 
41 Amsterdam UMC, Amsterdam, the Netherlands 
42 Erasmus MC, Rotterdam, the Netherlands 
43 Amsterdam UMC, Amsterdam the Netherlands 
44 Erasmus MC, Rotterdam, the Netherlands 
45 Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA 
46 Baylor University Medical Center, Dallas, Texas, USA 
47 TU Eindhoven, Eindhoven, the Netherlands 
48 University Hospitals Leuven, Leuven, Belgium 
49 Mayo Clinic, Rochester, Minnesota, USA 
50 Columbia University Medical Center, New York, New York, USA 
51 Flevoziekenhuis, Almere, the Netherlands 
52 Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom. V. Raman Muthusamy, UCLA Health, Los Angeles, California, USA 
53 Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom 
54 St. John of God Hospital, Regensburg, Germany 
55 Royal Infirmary Edinburgh, Edinburgh, United Kingdom 
56 Amsterdam UMC, Amsterdam, the Netherlands 
57 TU Eindhoven, Eindhoven, the Netherlands 
58 Royal Perth Hospital, Perth, Australia 
59 Onze Lieve Vrouwe Gasthuis, Amsterdam, the Netherlands 
60 Klinik Hirslanden, Zurich, Switzerland 
61 Columbia University Medical Center, New York, New York, USA 
62 Mount Sinai West & Mount Sinai Morningside Hospitals, New York, New York, USA 
63 TU Eindhoven, Eindhoven, the Netherlands 
64 Zucker School of Medicine at Hofstra/Northwell, Long Island Jewish Medical Center, New Hyde Park, New York, New York, USA 
65 University of Colorado Anschutz Medical Center, Aurora, Colorado, USA 
66 Rush University Medical Center, Chicago, Illinois, USA 
67 UMC Groningen, Groningen, the Netherlands 
68 UMC Utrecht & St. Antonius Hospital, Utrecht, the Netherlands 
69 TU Eindhoven, Eindhoven, the Netherlands 
70 Mayo Clinic, Jacksonville, Florida, USA 

1 Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology Endocrinology Metabolism, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands 
2 Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands 
3 Department of Gastroenterology and Hepatology, UMC Utrecht, University of Utrecht, Utrecht, the Netherlands 
4 Department of Gastroenterology and Hepatology, Sint Antonius Hospital, Nieuwegein, the Netherlands 
5 Department of Gastroenterology and Hepatology, HagaZiekenhuis Den Haag, Den Haag, the Netherlands 
6 Department of Gastroenterology and Hepatology, UMC Groningen, University of Groningen, Groningen, the Netherlands 
7 Department of Gastroenterology and Hepatology, Isala Hospital Zwolle, Zwolle, the Netherlands 
8 Department of Gastroenterology and Hepatology, Flevoziekenhuis Almere, Almere, the Netherlands 
9 Department of Gastroenterology and Hepatology, Onze Lieve Vrouwe Gasthuis, Amsterdam, the Netherlands 
10 Department of Gastroenterology and Hepatology, Royal Perth Hospital, Curtin University, Perth, WA, Australia 
11 Department of Gastroenterology and Hepatology, Hirslanden Klinik, Zurich, Switzerland 
12 Department of Digestive Diseases, Karolinska University Hospital, Stockholm, Sweden 
13 Division of Surgery, Department of Clinical Science, Intervention and Technology, CLINTEC, Karolinska Institutet, Stockholm, Sweden 
14 Center for Advanced Endoscopy Carlos Moreira da Silva, Gastroenterology Department, Pedro Hispano Hospital, ULSM Matosinhos, Portugal 
15 Department of Gastroenterology and Hepatology, Cochin Hospital Paris, Paris, France 
16 Department of Gastroenterology and Hepatology, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom 
17 Department of Gastroenterology and Hepatology, St. John of God Hospital, Regensburg, Germany 
18 Department of Gastroenterology and Hepatology, Evangalisches Krankenhaus Düsseldorf, Düsseldorf, Germany 
19 Biostatistics Unit, Department of Gastroenterology and Hepatology, Amsterdam University Medical Center, location Academic Medical Center, University of Amsterdam, Amsterdam, the Netherlands 

∗Reprint requests: Jacques J. Bergman, MD, PhD, Amsterdam UMC, De Boelelaan 1117, 1081 HV Amsterdam, the Netherlands.Amsterdam UMCDe Boelelaan 1117Amsterdam1081 HVthe Netherlands

Abstract

Background and Aims

Characterization of visible abnormalities in patients with Barrett’s esophagus (BE) can be challenging, especially for inexperienced endoscopists. This results in suboptimal diagnostic accuracy and poor interobserver agreement. Computer-aided diagnosis (CADx) systems may assist endoscopists. We aimed to develop, validate, and benchmark a CADx system for BE neoplasia.

Methods

The CADx system received pretraining with ImageNet and then consecutive domain-specific pretraining with GastroNet, which includes 5 million endoscopic images. It was subsequently trained and internally validated using 1758 narrow-band imaging (NBI) images of early BE neoplasia (352 patients) and 1838 NBI images of nondysplastic BE (173 patients) from 8 international centers. CADx was tested prospectively on corresponding image and video test sets with 30 cases (20 patients) of BE neoplasia and 60 cases (31 patients) of nondysplastic BE. The test set was benchmarked by 44 general endoscopists in 2 phases (phase 1, no CADx assistance; phase 2, with CADx assistance). Ten international BE experts provided additional benchmark performance.

Results

Stand-alone sensitivity and specificity of the CADx system were 100% and 98% for images and 93% and 96% for videos, respectively. CADx outperformed general endoscopists without CADx assistance in terms of sensitivity (P = .04). Sensitivity and specificity of general endoscopists increased from 84% to 96% and 90% to 98% with CAD assistance (P < .001). CADx assistance increased endoscopists’ confidence in characterization (P < .001). CADx performance was similar to that of the BE experts.

Conclusions

CADx assistance significantly increased characterization performance of BE neoplasia by general endoscopists to the level of expert endoscopists. The use of this CADx system may thereby improve daily Barrett surveillance.

Il testo completo di questo articolo è disponibile in PDF.

Abbreviations : BE, CADe, CADx, NBI, NDBE, WLE


Mappa


 DIVERSITY, EQUITY, AND INCLUSION: One or more of the authors of this paper self-identifies as an under-represented gender minority in science. One or more of the authors of this paper self-identifies as an under-represented ethnic minority in science. The author list of this paper includes contributors from the location where the research was conducted who participated in the data collection, design, analysis, and/or interpretation of the work.


© 2024  American Society for Gastrointestinal Endoscopy. Pubblicato da Elsevier Masson SAS. Tutti i diritti riservati.
Aggiungere alla mia biblioteca Togliere dalla mia biblioteca Stampare
Esportazione

    Citazioni Export

  • File

  • Contenuto

Vol 100 - N° 4

P. 616 - ottobre 2024 Ritorno al numero
Articolo precedente Articolo precedente
  • Risk factors for metachronous colorectal cancer or advanced lesions after endoscopic resection of serrated polyps: a systematic review and meta-analysis
  • Sandra Baile-Maxía, Carolina Mangas-Sanjuán, Uri Ladabaum, Carmen Sánchez-Ardila, Noelia Sala-Miquel, Cesare Hassan, Matthew D. Rutter, Michael Bretthauer, Pedro Zapater, Rodrigo Jover
| Articolo seguente Articolo seguente
  • Endoscopic submucosal dissection for early esophageal adenocarcinoma: low rates of metastases in mucosal cancers with poor differentiation
  • Andreas Probst, Felix Kappler, Alanna Ebigbo, David Albers, Siegbert Faiss, Ingo Steinbrück, Andreas Wannhoff, Hans-Peter Allgaier, Ulrike Denzer, Viktor Rempel, Roland Reinehr, Dani Dakkak, Matthias Mende, Jürgen Pohl, Tina Schaller, Bruno Märkl, Anna Muzalyova, Carola Fleischmann, Helmut Messmann

Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.

Già abbonato a @@106933@@ rivista ?

@@150455@@ Voir plus

Il mio account


Dichiarazione CNIL

EM-CONSULTE.COM è registrato presso la CNIL, dichiarazione n. 1286925.

Ai sensi della legge n. 78-17 del 6 gennaio 1978 sull'informatica, sui file e sulle libertà, Lei puo' esercitare i diritti di opposizione (art.26 della legge), di accesso (art.34 a 38 Legge), e di rettifica (art.36 della legge) per i dati che La riguardano. Lei puo' cosi chiedere che siano rettificati, compeltati, chiariti, aggiornati o cancellati i suoi dati personali inesati, incompleti, equivoci, obsoleti o la cui raccolta o di uso o di conservazione sono vietati.
Le informazioni relative ai visitatori del nostro sito, compresa la loro identità, sono confidenziali.
Il responsabile del sito si impegna sull'onore a rispettare le condizioni legali di confidenzialità applicabili in Francia e a non divulgare tali informazioni a terzi.


Tutto il contenuto di questo sito: Copyright © 2026 Elsevier, i suoi licenziatari e contributori. Tutti i diritti sono riservati. Inclusi diritti per estrazione di testo e di dati, addestramento dell’intelligenza artificiale, e tecnologie simili. Per tutto il contenuto ‘open access’ sono applicati i termini della licenza Creative Commons.