Modern surgical practice is evolving towards less invasive procedures, where surgeons no longer have a direct view of the anatomical structures, and therefore a mental compensation process is required to reach and identify the desired anatomical area. Image Guide (IG) procedures have been developed that automatically integrate information coming from dierent sensor sources through a registration procedure. Patient tracking is used to measure the position and the movements of the patients during surgery and then to update the relative organ positions in real-time. The availability of Microsoft’s Kinect allows addressing some of the registration problems with a very compact and inexpensive device. However, it was shown that Kinect accuracy is only in the centimeters range, and that it decreases exponentially with distance, making this sensor unsuitable for use in most IG applications. In this paper we present our work aimed at increasing the Kinect performance by introducing simple markers that can signicantly improve Kinect accuracy and precision making it compatible with the requirement of the operating room (OR) tracking.

Marker based accuracy analysis of RGB-D sensor for image guided applications

DALL'ALBA, Diego;MARIS, Bogdan Mihai;REGHELIN, CARLO;FIORINI, Paolo
2012-01-01

Abstract

Modern surgical practice is evolving towards less invasive procedures, where surgeons no longer have a direct view of the anatomical structures, and therefore a mental compensation process is required to reach and identify the desired anatomical area. Image Guide (IG) procedures have been developed that automatically integrate information coming from dierent sensor sources through a registration procedure. Patient tracking is used to measure the position and the movements of the patients during surgery and then to update the relative organ positions in real-time. The availability of Microsoft’s Kinect allows addressing some of the registration problems with a very compact and inexpensive device. However, it was shown that Kinect accuracy is only in the centimeters range, and that it decreases exponentially with distance, making this sensor unsuitable for use in most IG applications. In this paper we present our work aimed at increasing the Kinect performance by introducing simple markers that can signicantly improve Kinect accuracy and precision making it compatible with the requirement of the operating room (OR) tracking.
2012
depth sensor; medical image processing; registration; image guided surgery
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/501160
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact