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

Journal: Gut
Published Date: Sep 15, 2022

Abstract

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.

Authors

  • Alanna Ebigbo
    Medizinische Klinik III, Klinikum Augsburg, Germany.
  • Robert Mendel
    Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Germany.
  • Markus W Scheppach
    Department of Gastroenterology, Universitätsklinikum Augsburg, Augsburg, Germany.
  • Andreas Probst
    Medizinische Klinik III, Klinikum Augsburg, Germany.
  • Neal Shahidi
    St. Paul's Hospital, Division of Gastroenterology, Department of Medicine, University of British Columbia, Vancouver, BC, Canada.
  • Friederike Prinz
    Department of Gastroenterology, Universitätsklinikum Augsburg, Augsburg, Germany.
  • Carola Fleischmann
    Department of Gastroenterology, Universitätsklinikum Augsburg, Augsburg, Germany.
  • Christoph Römmele
    Department of Gastroenterology, Universitätsklinikum Augsburg, Augsburg, Germany.
  • Stefan Karl Goelder
    Department of Gastroenterology, Ostalb-Klinikum Aalen, Aalen, Germany.
  • Georg Braun
    Department of Gastroenterology, Universitätsklinikum Augsburg, Augsburg, Germany.
  • David Rauber
    Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany.
  • Tobias Rueckert
    Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany.
  • Luis A de Souza
    Department of Computing, São Paulo State University, UNESP, Brazil; Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Germany.
  • Joao Papa
    Department of Computing, São Paulo State University, Bauru, Brazil.
  • Michael Byrne
    Division of Gastroenterology, Vancouver General Hospital/University of British Columbia, Vancouver, British Columbia, Canada.
  • Christoph Palm
    Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Germany; Regensburg Center of Biomedical Engineering (RCBE), OTH Regensburg and Regensburg University, Germany.
  • Helmut Messmann
    Medizinische Klinik III, Klinikum Augsburg, Germany.

Keywords

External Resources

Popular Topics
Recent Journals