Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-13779
Authors: Schüle, Johannes
Title: Intraoperative localization and scene reconstruction using differentiable rendering and graph-based landmark registration with application to cystoscopy
Issue Date: 2023
metadata.ubs.publikation.typ: Dissertation
metadata.ubs.publikation.seiten: X, 226
URI: http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-137982
http://elib.uni-stuttgart.de/handle/11682/13798
http://dx.doi.org/10.18419/opus-13779
metadata.ubs.bemerkung.extern: Druck-Ausgabe als: Berichte aus dem Institut für Systemdynamik, Universität Stuttgart ; Band 71 beim Shaker Verlag, Düren erschienen. ISBN 978-3-8440-9262-2
Abstract: Minimally invasive procedures, such as bladder endoscopy, reduce trauma but present navigation challenges due to restricted visibility. Traditional mapping methods are often insufficient, and comprehensive solutions in the literature are scarce. This work introduces a novel approach for intraoperative navigation and scene reconstruction, focusing on deformable environments, such as those encountered in cystoscopy. The proposed reconstruction concept relies on a monocular camera image but can be flexibly extended to include additional sensor data. The fundamental reconstruction strategy employed in this work follows the question: How does the model representation and camera perspective need to be adjusted such that the rendering of the model matches the current observation? The reconstruction process requires the formulation of several optimization objectives, necessitating a fully differentiable rendering approach. To this end, a novel formulation of an inverse rendering process is proposed, where 2D image data is projected from the camera's perspective onto a 3D mesh model. Vascular structures, which remain consistent despite deformations, serve as dependable landmarks. Combining graph-based landmark recognition with rendering-based reconstruction techniques offers a comprehensive solution for determining the intraoperative location and scene, especially considering the complexity of deformable surgical environments.
Appears in Collections:07 Fakultät Konstruktions-, Produktions- und Fahrzeugtechnik

Files in This Item:
File Description SizeFormat 
diss_intraoperative_localization_schuelej.pdfDissertation Schuele Intraoperative Localization112,41 MBAdobe PDFView/Open


Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.