Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm

  • In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63% and 76%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Alanna EbigboORCiD, Robert MendelORCiD, Markus W. ScheppachORCiD, Andreas Probst, Neal ShahidiORCiD, Friederike Prinz, Carola Fleischmann, Christoph RömmeleORCiD, Stefan Karl Gölder, Georg Braun, David Rauber, Tobias RückertORCiD, Luis Antonio de Souza Jr.ORCiD, João Paulo PapaORCiD, Michael F. Byrne, Christoph PalmORCiDGND, Helmut Messmann
URN:urn:nbn:de:bvb:898-opus4-54293
DOI:https://doi.org/10.1136/gutjnl-2021-326470
Parent Title (English):Gut
Publisher:BMJ
Place of publication:London
Document Type:Article
Language:English
Year of first Publication:2022
Publishing Institution:Ostbayerische Technische Hochschule Regensburg
Release Date:2022/09/16
Tag:Artificial Intelligence; Endoscopy; Medical Image Computing
Volume:71
Issue:12
First Page:2388
Last Page:2390
Institutes:Fakultät Informatik und Mathematik
Fakultät Informatik und Mathematik / Regensburg Medical Image Computing (ReMIC)
Begutachtungsstatus:peer-reviewed
research focus:Lebenswissenschaften und Ethik
OpenAccess Publikationsweg:Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium
Licence (German):Creative Commons - CC BY-NC - Namensnennung - Nicht kommerziell 4.0 International