A Smart Trocar for Automatic Tool Recognition in Laparoscopic Surgery. (February 2015)

• Record Type: Journal Article
• Authors: Toti, Giulia; Garbey, Marc; Sherman, Vadim; Bass, Barbara L.; Dunkin, Brian J.
• Is Part Of: Surgical innovation. Volume 22:Number 1(2015:Feb.)
• Page Start: 77
• Page End: 82
• Publication Date: 2015-02
• Subjects: operating room awareness -- automatic tool recognition -- surgical assessment -- training; Surgery, Operative -- Periodicals; Endoscopic surgery -- Periodicals; Laparoscopic surgery -- Periodicals; Surgical Procedures, Operative -- Periodicals; Surgical Procedures, Minimally Invasive -- Periodicals; Diffusion of Innovation -- Periodicals; Chirurgie opératoire -- Périodiques; Chirurgie endoscopique -- Périodiques; Chirurgie laparoscopique -- Périodiques; 617.91
• DOI: 10.1177/1553350614531659
• Languages: English
• ISSNs: 1553-3506

Abstract

Background . Operating rooms have become increasingly complex environments and more prone to errors because of loss of situation awareness. Adding computer intelligence to the operating room may help overcome these limitations particularly if the system can automatically track which step of an operation a surgeon is performing. To develop such a platform, it is necessary to track which laparoscopic instruments are being used and in which port they are inserted. This article describes the development and validation of a "Smart Trocar" that can automatically perform this function. Methods . A Smart Trocar system prototype was developed that uses a wireless camera attached to a standard laparoscopic port and custom software algorithms. The system recognizes color wheels attached to the handle of a laparoscopic instrument and compares the unique color pattern to an instrument library for proper tool identification. The system was tested for reliability in a box trainer environment using a variety of tool positions and levels of room light illumination. Results . Correct color classification was achieved in 96.7% of trials. There were no errors in detection of the color wheel in space. In addition, the distance of the color wheel from the camera did not influence results and correct classifications were evenly distributed among the 12 laparoscopic tool positions tested. Conclusion . This work describes a Smart Trocar system that identifies which laparoscopic tool is being used and in which port and proves its reliability. The system is an important element of a more comprehensive program being developed to automatically understand what step of an operation a surgeon is performing and use these data to improve situation awareness in the operating room.