Hakimi, Wissam El ; Beutel, Johannes ; Sakas, Georgios (2014)
Particle Path Segmentation: a Fast, Accurate, and Robust Method for Localization of Spherical Markers in Cone-beam CT Projections.
Proceedings BMT 2014. 48. DGBMT Jahrestagung.
doi: 10.1515/bmt-2014-5005
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Spherical fiducial markers are widely used for point-based registration of intra-operative 2D X-ray projections to preoperative 3D computed tomography images. The automatic localization of marker centers on X-rays speeds up the registration process and reduces the human error. However, a sub-pixel accurate localization of said centers is at present a challenging task, especially when fiducials overlap dense anatomical structures on the radiographs. In this paper, we propose a new method for automated and accurate detection of centers of fiducial markers in 2D projections, even in presence of structure overlapping. Several experiments confirm the high accuracy and robustness of the proposed algorithm achieving a localization error - mean (std) - equal to 0.059 (0.062) mm.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2014 |
| Autor(en): | Hakimi, Wissam El ; Beutel, Johannes ; Sakas, Georgios |
| Art des Eintrags: | Bibliographie |
| Titel: | Particle Path Segmentation: a Fast, Accurate, and Robust Method for Localization of Spherical Markers in Cone-beam CT Projections |
| Sprache: | Englisch |
| Publikationsjahr: | 2014 |
| Verlag: | de Gruyter, Berlin |
| Veranstaltungstitel: | Proceedings BMT 2014. 48. DGBMT Jahrestagung |
| DOI: | 10.1515/bmt-2014-5005 |
| Kurzbeschreibung (Abstract): | Spherical fiducial markers are widely used for point-based registration of intra-operative 2D X-ray projections to preoperative 3D computed tomography images. The automatic localization of marker centers on X-rays speeds up the registration process and reduces the human error. However, a sub-pixel accurate localization of said centers is at present a challenging task, especially when fiducials overlap dense anatomical structures on the radiographs. In this paper, we propose a new method for automated and accurate detection of centers of fiducial markers in 2D projections, even in presence of structure overlapping. Several experiments confirm the high accuracy and robustness of the proposed algorithm achieving a localization error - mean (std) - equal to 0.059 (0.062) mm. |
| Freie Schlagworte: | Forschungsgruppe Medical Computing (MECO), Registration, Marker localization, Computer vision, Cone-beam computed tomography (CBCT) |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 12 Nov 2018 11:16 |
| Letzte Änderung: | 26 Jul 2021 15:28 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum