Robot assisted minimally invasive surgery (RAMIS) has been widely applied in various clinical treatment, and da Vinci surgical system is the most typical representative because of its special advantages, like handeye coordination and 3D vision. However, the movement of the stereo endoscope inside human body is limited. Augmented reality (AR) is considered to be integrated into RAMIS, since it can provide more visualization. Recovering 3D information of surgical scene directly affects the performance of AR. Many researchers have implemented 3D reconstruction based on stereo images, such as the semi-global block matching (SGBM) [1]. It has high disparity search efficiency for common stereo images, while the effect in medical field remains to be explored. Hence, an enhanced semi-global block matching approach with preprocessing (P-SGBM) is developed to recover the 3D information of endoscopic images in this paper.

Recovering 3D information of human soft tissue using stereo endoscopic images

Chen, Ziyang;Alberti, Davide;Marzullo, Aldo;Ferrigno, Giancarlo;De Momi, Elena
2022

Abstract

Robot assisted minimally invasive surgery (RAMIS) has been widely applied in various clinical treatment, and da Vinci surgical system is the most typical representative because of its special advantages, like handeye coordination and 3D vision. However, the movement of the stereo endoscope inside human body is limited. Augmented reality (AR) is considered to be integrated into RAMIS, since it can provide more visualization. Recovering 3D information of surgical scene directly affects the performance of AR. Many researchers have implemented 3D reconstruction based on stereo images, such as the semi-global block matching (SGBM) [1]. It has high disparity search efficiency for common stereo images, while the effect in medical field remains to be explored. Hence, an enhanced semi-global block matching approach with preprocessing (P-SGBM) is developed to recover the 3D information of endoscopic images in this paper.
File in questo prodotto:
File Dimensione Formato  
2022_ZIYANG_CHEN_CRAS.pdf

accesso aperto

: Publisher’s version
Dimensione 1.52 MB
Formato Adobe PDF
1.52 MB Adobe PDF Visualizza/Apri

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: http://hdl.handle.net/11311/1215236
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact