Advertisement

Abstract: Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training

  • Sandy EngelhardtEmail author
  • Lalith Sharan
  • Matthias Karck
  • Raffaele De Simone
  • Ivo Wolf
Conference paper
  • 34 Downloads
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Phantoms for surgical training are able to mimic cutting and suturing properties and patient-individual shape of organs, but lack a realistic visual appearance that captures the heterogeneity of surgical scenes. In order to overcome this in endoscopic approaches, hyperrealistic concepts have been proposed to be used in an augmented reality-setting, which are based on deep image-to-image transformation methods. Such concepts are able to generate realistic representations of phantoms learned from real intraoperative endoscopic sequences.

Literatur

  1. 1.
    Engelhardt S, Sharan L, Karck M, et al. Cross-Domain conditional generative adversarial networks for stereoscopic hyperrealism in surgical training. In: Proc MICCAI 2019;. p. 155–163.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  • Sandy Engelhardt
    • 1
    • 4
    Email author
  • Lalith Sharan
    • 1
  • Matthias Karck
    • 3
  • Raffaele De Simone
    • 3
  • Ivo Wolf
    • 2
  1. 1.Working Group Artificial Intelligence in Cardiovascular MedicineUniversity Hospital HeidelbergHeidelbergDeutschland
  2. 2.Faculty of Computer ScienceMannheim University of Applied SciencesMannheimDeutschland
  3. 3.Department of Cardiac SurgeryHeidelberg University HospitalHeidelbergDeutschland
  4. 4.Research Campus STIMULATEMagdeburg UniversityMagdeburgDeutschland

Personalised recommendations