Download PDF
Endoscopy
DOI: 10.1055/a-2534-1164
Innovations and brief communications

Artificial intelligence improves submucosal vessel detection during third space endoscopy

Markus Wolfgang Scheppach 
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
,
Robert Mendel
3   Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany (Ringgold ID: RIN84614)
,
Anna Muzalyova
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
,
David Rauber
3   Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany (Ringgold ID: RIN84614)
,
Andreas Probst
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
,
Sandra Nagl
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
,
Christoph Römmele 
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
,
Hon Chi Yip 
4   Department of Surgery, The Chinese University of Hong Kong Faculty of Medicine, Hong Kong, Hong Kong (Ringgold ID: RIN71024)
,
Ho Shing Louis Lau 
5   Department of Medicine and Therapeutics, The Chinese University of Hong Kong Faculty of Medicine, Hong Kong, Hong Kong (Ringgold ID: RIN71024)
,
Stefan Karl Gölder
6   Department of Internal Medicine I - Gastroenterology, Ostalb Hospital Aalen, Aalen, Germany (Ringgold ID: RIN39481)
,
Arthur Schmidt
7   Department of Gastroenterology, Hepatology and Endocrinology, Robert Bosch Hospital, Stuttgart, Germany (Ringgold ID: RIN15000)
,
Konstantinos Kouladouros
8   Central Inderdisciplinary Endoscopy, Department of Hepatology and Gastroenterology, Charite University Hospital Berlin, Berlin, Germany (Ringgold ID: RIN14903)
,
Mohamed Abdelhafez
9   Department of internal Medicine, Klinikum rechts der Isar der Technischen Universitat Munchen, Munchen, Germany (Ringgold ID: RIN27190)
,
Benjamin M Walter
10   Department of Internal Medicine I, Ulm University Hospital, Ulm, Germany (Ringgold ID: RIN27197)
,
Michael Meinikheim
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
,
Philip Wai Yan Chiu 
4   Department of Surgery, The Chinese University of Hong Kong Faculty of Medicine, Hong Kong, Hong Kong (Ringgold ID: RIN71024)
,
Christoph Palm
3   Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany (Ringgold ID: RIN84614)
11   Regensburg Center of Health Sciences and Technology (RCHST), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany (Ringgold ID: RIN84614)
,
Helmut Messmann
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
,
Alanna Ebigbo
1   Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany (Ringgold ID: RIN39694)
2   University Hospital of Augsburg, Bavarian Cancer Research Center, Erlangen, Germany (Ringgold ID: RIN653574)
› Author Affiliations
› Further Information
Also available at
  PDF Download

Background and study aims: While artificial intelligence (AI) shows high potential in decision support for diagnostic gastrointestinal endoscopy, its role in therapeutic endoscopy remains unclear. Third space endoscopic procedures pose the risk of intraprocedural bleeding. Therefore, we aimed to develop an AI algorithm for intraprocedural blood vessel detection. Patients and Methods: Using a test dataset with 101 standardized video clips containing 200 predefined submucosal blood vessels, 19 endoscopists were evaluated for the vessel detection rate (VDR) and time (VDT) with and without support of an AI algorithm. Test subjects were grouped according to experience in ESD. Results: With AI support, endoscopists VDR increased from 56.4% [CI 54.1–58.6] to 72.4% [CI 70.3–74.4]. Endoscopists‘ VDT dropped from 6.7sec [CI 6.2-7.1] to 5.2sec [CI 4.8-5.7]. False positive (FP) readings appeared in 4.5% of frames and were marked significantly shorter than true positives (6.0sec [CI 5.28-6.70] vs. 0.7sec [CI 0.55-0.87]). Conclusions: AI improved the vessel detection rate and time of endoscopists during third space endoscopy. While these data need to be corroborated by clinical trials, AI may prove to be an invaluable tool for the improvement of endoscopic interventions.



Publication History

Received: 24 June 2024

Accepted after revision: 05 February 2025

Accepted Manuscript online:
05 February 2025

© . Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany