3D augmentation of the surgical video stream: Toward a modular approach. (July 2020)

• Record Type: Journal Article
• Authors: Gribaudo, Marco; Piazzolla, Pietro; Porpiglia, Francesco; Vezzetti, Enrico; Violante, Maria Grazia
• Is Part Of: Computer methods and programs in biomedicine. Volume 191(2020)
• Publication Date: 2020-07
• Subjects: Augmented reality -- Robot-Assisted surgery -- Surgical navigation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105505
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Augmented Reality systems for Robot-Assisted Surgery use a single tracking strategy. Each stage of the surgery procedure potentially presents different visual features. These visual features can be exploited by different more efficient tracking methods. We combined different tracking methods into a single integrated navigation aid. We provide a formal model to generalize our approach to any surgical specialty. Abstract: Background and Objective. We present an original approach to the development of augmented reality (AR) real-time solutions for robotic surgery navigation. The surgeon operating the robotic system through a console and a visor experiences reduced awareness of the operatory scene. In order to improve the surgeon's spatial perception during robot-assisted minimally invasive procedures, we provide him/her with a solid automatic software system to position, rotate and scale in real-time the 3D virtual model of a patient's organ aligned over its image captured by the endoscope. Methods. We observed that the surgeon may benefit differently from the 3D augmentation during each stage of the surgical procedure; moreover, each stage may present different visual elements that provide specific challenges and opportunities to exploit for organ detection strategies implementation. Hence we integrate different solutions, each dedicated to a specific stage of the surgical procedure, into a single software system. Results. We present a formal model that generalizes our approach, describing a system composed of integrated solutions for AR in robot-assisted surgery. Following the proposed framework, and application has been developed which is currently used during in vivo surgery, for extensive testing, by the Urology unity of the San Luigi Hospital, in Orbassano (To), Italy. Conclusions. The main contribution of this paper is in presenting a modular approach to the tracking problem during in-vivo robotic surgery, whose efficacy from a medical point of view has been assessed in cited works. The segmentation of the whole procedure in a set of stages allows associating the best tracking strategy to each of them, as well as to re-utilize implemented software mechanisms in stages with similar features.