Addressing multi-label imbalance problem of surgical tool detection using CNN.

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

Abstract

PURPOSE: A fully automated surgical tool detection framework is proposed for endoscopic video streams. State-of-the-art surgical tool detection methods rely on supervised one-vs-all or multi-class classification techniques, completely ignoring the co-occurrence relationship of the tools and the associated class imbalance.

Authors

  • Manish Sahu
    Zuse Institute Berlin, Berlin, Germany. sahu@zib.de.
  • Anirban Mukhopadhyay
    Zuse Institute Berlin, Berlin, Germany.
  • Angelika Szengel
    Zuse Institute Berlin, Berlin, Germany.
  • Stefan Zachow
    Zuse Institute Berlin, Berlin, Germany.