Skip to main content
main-content

Über dieses Buch

Andreas Bihlmaier describes a novel method to model dynamic spatial relations by machine learning techniques. The method is applied to the task of representing the tacit knowledge of a trained camera assistant in minimally-invasive surgery. The model is then used for intraoperative control of a robot that autonomously positions the endoscope. Furthermore, a modular robotics platform is described, which forms the basis for this knowledge-based assistance system. Promising results from a complex phantom study are presented.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

The aim of this thesis is to describe novel methods that facilitate autonomous robotic endoscope assistance, which is derived from actual surgical know-how. In minimally-invasive surgery (MIS), the surgeon has to rely on an assistant to guide the endoscope camera for him in order to get a view at the surgical site. Given the many issues that arise from this situation, motorized endoscope holders appeared early in the short history of MIS.

Andreas Bihlmaier

Chapter 2. Endoscope Robots and Automated Camera Guidance

This section describes in chronological order the development of motorized endoscope holders. In the literature these are often referred to as active endoscope holders. However, this term is avoided here as it suggests active robots as defined in the previous chapter (p. 1.2) as opposed to telemanipulated robots.

Andreas Bihlmaier

Chapter 3. System Architecture and Conceptual Overview

After motorized endoscope holders and approaches to the automation of camera positioning were surveyed in the previous chapter, the architecture of the new method put forth in this thesis is described. Referring to the classification of viewpoint automation from section 2.2.2, the new approach can be characterized as context-aware, model-based planned (number 8 in Fig. 2.39).

Andreas Bihlmaier

Chapter 4. Modular Research Platform for Robot-Assisted Minimally-Invasive Surgery

The Robot Operating System (ROS) [229] is an open source middleware and a collection of associated software frameworks for modular (distributed) robot software. A focus of the middleware is exchange of streaming data under soft real-time conditions while maintaining a high runtime flexibility. ROS is often used in a research context where heterogeneous software components, often developed in isolation by different people, must work together across multiple computers.

Andreas Bihlmaier

Chapter 5. Learning of Surgical Know-How by Models of Spatial Relations

The optimal spatial relation between instruments and endoscope is not a static one. It changes with the surgical task and the anatomical structures that are manipulated (Fig. 5.2). Even the optimal distance of endoscope to instruments varies widely, in relation to the optimal visual zoom of the operating site.

Andreas Bihlmaier

Chapter 6. Intraoperative Robot-Based Camera Assistance

In this chapter the two remaining components required for an intraoperative camera assistance are discussed: First, the necessary preliminaries to utilize the modular platform that was discussed in chapter 4 for endoscope positioning (6.1). Second, how the learned camera guidance model is deployed for optimal endoscope positioning over time (6.2).

Andreas Bihlmaier

Chapter 7. Evaluation Studies

All parts of the knowledge-based endoscope guidance system have been described in the previous chapters: System architecture, modular platform, tracking of surgical instruments, learning of endoscope guidance know-how and intraoperative robot-based action. In this chapter the evaluation results of the system in a phantom study of laparoscopic rectal resection with total mesorectal resection (TME) are provided. Starting from n=20 human assisted interventions, overall n=16 robotassisted interventions were undertaken by one surgeon. Two robots with very different structure, the ViKY (2.1.9) and the LWR (4.2.4), have been used to position the endoscope.

Andreas Bihlmaier

Chapter 8. Conclusion

The knowledge-based approach to autonomous endoscope positioning showed good performance in a complex phantom study. As shown in the previous chapter, in this study of overall n=36 interventions of about 25 minutes each, the system described in this thesis was actually superior to human camera assistance. Intervention duration was lower and the endoscopic view was considered good more often.

Andreas Bihlmaier

Backmatter

Weitere Informationen

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

INDUSTRIE 4.0

Der Hype um Industrie 4.0 hat sich gelegt – nun geht es an die Umsetzung. Das Whitepaper von Protolabs zeigt Unternehmen und Führungskräften, wie sie die 4. Industrielle Revolution erfolgreich meistern. Es liegt an den Herstellern, die besten Möglichkeiten und effizientesten Prozesse bereitzustellen, die Unternehmen für die Herstellung von Produkten nutzen können. Lesen Sie mehr zu: Verbesserten Strukturen von Herstellern und Fabriken | Konvergenz zwischen Soft- und Hardwareautomatisierung | Auswirkungen auf die Neuaufstellung von Unternehmen | verkürzten Produkteinführungszeiten
Jetzt gratis downloaden!

Bildnachweise