Deep learning for surgical phase recognition using endoscopic videos.

Journal: Surgical endoscopy
Published Date:

Abstract

BACKGROUND: Operating room planning is a complex task as pre-operative estimations of procedure duration have a limited accuracy. This is due to large variations in the course of procedures. Therefore, information about the progress of procedures is essential to adapt the daily operating room schedule accordingly. This information should ideally be objective, automatically retrievable and in real-time. Recordings made during endoscopic surgeries are a potential source of progress information. A trained observer is able to recognize the ongoing surgical phase from watching these videos. The introduction of deep learning techniques brought up opportunities to automatically retrieve information from surgical videos. The aim of this study was to apply state-of-the art deep learning techniques on a new set of endoscopic videos to automatically recognize the progress of a procedure, and to assess the feasibility of the approach in terms of performance, scalability and practical considerations.

Authors

  • Annetje C P Guédon
    Department of Clinical Physics, Spaarne Gasthuis, Spaarnepoort 1, 2134TM, Hoofddorp, the Netherlands. aguedon@spaarnegasthuis.nl.
  • Senna E P Meij
    Department of Biomechanical Engineering, Delft University of Technology, Delft, the Netherlands.
  • Karim N M M H Osman
    Department of Biomechanical Engineering, Delft University of Technology, Delft, the Netherlands.
  • Helena A Kloosterman
    Cosmonio, Leeuwarden, the Netherlands.
  • Karlijn J van Stralen
    Spaarne Gasthuis Academie, Spaarne Gasthuis, Hoofddorp, the Netherlands.
  • Matthijs C M Grimbergen
    Department of Radiology, Amsterdam UMC, Amsterdam, the Netherlands.
  • Quirijn A J Eijsbouts
    Department of Surgery, Spaarne Gasthuis, Hoofddorp, the Netherlands.
  • John J van den Dobbelsteen
    Department of Biomechanical Engineering, Delft University of Technology, Delft, the Netherlands.
  • Andru P Twinanda
    Cosmonio, Leeuwarden, the Netherlands.