Kügler, David ; Sakas, Georgios (2016)
A Three-Step Approach to Track the Position and the Orientation of a Surgical Instrument in X-ray Images.
Curac 2016.
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
In bone surgery, minimally invasive approaches are currently limited to interventions along straight access paths. In the MUKNO research project (multiport bone surgery for the otobasis) we develop a hybrid image- and electromagnetic- guided navigation system to provide 6 DoF measurements (position and orientation) for a robotic system drilling curved paths. In this paper we propose a novel approach for tracking metallic surgical instruments in x-ray images for navigation of this robot. We track the robot in three steps: initialization with a weighted radon transformation, convolution with specifically designed mask and linear regression on the convolution result. First experiments for artificially generated and manually segmented images show sub-pixel and sub-degree image-coordinate and orientation errors.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2016 |
| Autor(en): | Kügler, David ; Sakas, Georgios |
| Art des Eintrags: | Bibliographie |
| Titel: | A Three-Step Approach to Track the Position and the Orientation of a Surgical Instrument in X-ray Images |
| Sprache: | Englisch |
| Publikationsjahr: | 2016 |
| Veranstaltungstitel: | Curac 2016 |
| Kurzbeschreibung (Abstract): | In bone surgery, minimally invasive approaches are currently limited to interventions along straight access paths. In the MUKNO research project (multiport bone surgery for the otobasis) we develop a hybrid image- and electromagnetic- guided navigation system to provide 6 DoF measurements (position and orientation) for a robotic system drilling curved paths. In this paper we propose a novel approach for tracking metallic surgical instruments in x-ray images for navigation of this robot. We track the robot in three steps: initialization with a weighted radon transformation, convolution with specifically designed mask and linear regression on the convolution result. First experiments for artificially generated and manually segmented images show sub-pixel and sub-degree image-coordinate and orientation errors. |
| Freie Schlagworte: | Forschungsgruppe Medical Computing (MECO), Minimally invasive surgery, Image guided therapy, Navigation |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 08 Mai 2019 06:26 |
| Letzte Änderung: | 08 Mai 2019 06:26 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum