Surgical instrument similarity metrics and tray analysis for multi-sensor instrument identification

Bernhard Glaser; Tobias Schellenberg; Stefan Franke; Stefan Dänzer; Thomas Neumuth

doi:10.1117/12.2082091

18 March 2015 Surgical instrument similarity metrics and tray analysis for multi-sensor instrument identification

Bernhard Glaser, Tobias Schellenberg, Stefan Franke, Stefan Dänzer, Thomas Neumuth

Proceedings Volume 9415, Medical Imaging 2015: Image-Guided Procedures, Robotic Interventions, and Modeling; 941526 (2015) https://doi.org/10.1117/12.2082091
Event: SPIE Medical Imaging, 2015, Orlando, Florida, United States

Abstract

A robust identification of the instrument currently used by the surgeon is crucial for the automatic modeling and analysis of surgical procedures. Various approaches for intra-operative surgical instrument identification have been presented, mostly based on radio-frequency identification (RFID) or endoscopic video analysis. A novel approach is to identify the instruments on the instrument table of the scrub nurse with a combination of video and weight information. In a previous article, we successfully followed this approach and applied it to multiple instances of an ear, nose and throat (ENT) procedure and the surgical tray used therein. In this article, we present a metric for the suitability of the instruments of a surgical tray for identification by video and weight analysis and apply it to twelve trays of four different surgical domains (abdominal surgery, neurosurgery, orthopedics and urology). The used trays were digitized at the central sterile services department of the hospital. The results illustrate that surgical trays differ in their suitability for the approach. In general, additional weight information can significantly contribute to the successful identification of surgical instruments. Additionally, for ten different surgical instruments, ten exemplars of each instrument were tested for their weight differences. The samples indicate high weight variability in instruments with identical brand and model number. The results present a new metric for approaches aiming towards intra-operative surgical instrument detection and imply consequences for algorithms exploiting video and weight information for identification purposes.

Citation Download Citation

Bernhard Glaser, Tobias Schellenberg, Stefan Franke, Stefan Dänzer, and Thomas Neumuth "Surgical instrument similarity metrics and tray analysis for multi-sensor instrument identification", Proc. SPIE 9415, Medical Imaging 2015: Image-Guided Procedures, Robotic Interventions, and Modeling, 941526 (18 March 2015); https://doi.org/10.1117/12.2082091

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available