A spatio-temporal network for video semantic segmentation in surgical videos.

Journal: International journal of computer assisted radiology and surgery
PMID: 37347345

Abstract

PURPOSE: Semantic segmentation in surgical videos has applications in intra-operative guidance, post-operative analytics and surgical education. Models need to provide accurate predictions since temporally inconsistent identification of anatomy can hinder patient safety. We propose a novel architecture for modelling temporal relationships in videos to address these issues.

Authors

  • Maria Grammatikopoulou
    Medtronic plc, London, UK. maria.grammatikopoulou@medtronic.com.
  • Ricardo Sanchez-Matilla
    Medtronic plc, London, UK.
  • Felix Bragman
    Medtronic plc, London, UK.
  • David Owen
    Medtronic plc, London, UK.
  • Lucy Culshaw
    Medtronic plc, London, UK.
  • Karen Kerr
    Medtronic plc, London, UK.
  • Danail Stoyanov
    University College London, London, UK.
  • Imanol Luengo
    Innovation Department, Medtronic Digital Surgery, 230 City Road, London, EC1V 2QY, UK.

Keywords

External Resources

Popular Topics
Recent Journals