Real-Time-Capable GPU-Framework for Depth-Aware Rigid 2D/3D Registration

Autor:	Matthias Utzschneider, Andreas Maier, Jian Wang, Anja Borsdorf, Roman Schaffert
Rok vydání:	2017
Předmět:	Hardware architecture 2d images 3d registration 3d image Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer vision Overlay Artificial intelligence business Variety (cybernetics)
Zdroj:	Informatik aktuell ISBN: 9783662543443 Bildverarbeitung für die Medizin
DOI:	10.1007/978-3-662-54345-0_43
Popis:	2D/3D image fusion is used for a variety of interventional procedures. Overlays of 2D images with perspective-correctly rendered 3D images provide the physicians additional information during the interventions. In this work, a real-time capable 2D/3D registration framework is presented. An adapted parallelization using GPU is investigated for the depth-aware registration algorithm. The GPU hardware architecture is specially taken into account by optimizing memory access patterns and exploiting CUDA-texture memory. The real-time capability is achieved with a median runtime of one 2D/3D registration iteration of 86.1ms with an median accuracy of up to 1.15 mm.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b32a5fc15c140c883d9f37ede1508d21 https://doi.org/10.1007/978-3-662-54345-0_43 Zobrazit plný text záznamu