Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: Automatic segmentation and classification of surgical activity is crucial for providing advanced support in computer-assisted interventions and autonomous functionalities in robot-assisted surgeries. Prior works have focused on recognizing either coarse activities, such as phases, or fine-grained activities, such as gestures. This work aims at jointly recognizing two complementary levels of granularity directly from videos, namely phases and steps.

Authors

  • Sanat Ramesh
    Altair Robotics Lab, Department of Computer Science, University of Verona, Verona, Italy. sanat.ramesh@univr.it.
  • Diego Dall'Alba
    University of Verona, Verona, Italy.
  • Cristians Gonzalez
    University Hospital of Strasbourg, IHU Strasbourg, France.
  • Tong Yu
  • Pietro Mascagni
    IHU Strasbourg, Strasbourg, France.
  • Didier Mutter
    Institut Hospitalo-Universitaire, Institute of Image-Guided Surgery, University of Strasbourg, Fédération de Médecine Translationnelle de Strasbourg, Strasbourg, France3Department of Digestive Surgery, Strasbourg University Hospital, Fédération de Médecin.
  • Jacques Marescaux
  • Paolo Fiorini
    University of Verona, Verona, Italy.
  • Nicolas Padoy
    IHU Strasbourg, Strasbourg, France.