hrcak mascot   Srce   HID

Izvorni znanstveni članak

Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images

Sonke Frantz ; Universitat Hamburg, Fachbereich lnformatik, Arbeitsbereich Kognitive Systeme, Hamburg, Germany
Karl Rohr ; Universitat Hamburg, Fachbereich lnformatik, Arbeitsbereich Kognitive Systeme, Hamburg, Germany
H. Siegfried Stiehl ; Universitat Hamburg, Fachbereich lnformatik, Arbeitsbereich Kognitive Systeme, Hamburg, Germany

Puni tekst: engleski, pdf (6 MB) str. 435-447 preuzimanja: 252* citiraj
APA 6th Edition
Frantz, S., Rohr, K. i Stiehl, H.S. (1998). Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images. Journal of computing and information technology, 6 (4), 435-447. Preuzeto s https://hrcak.srce.hr/150209
MLA 8th Edition
Frantz, Sonke, et al. "Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images." Journal of computing and information technology, vol. 6, br. 4, 1998, str. 435-447. https://hrcak.srce.hr/150209. Citirano 08.03.2021.
Chicago 17th Edition
Frantz, Sonke, Karl Rohr i H. Siegfried Stiehl. "Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images." Journal of computing and information technology 6, br. 4 (1998): 435-447. https://hrcak.srce.hr/150209
Harvard
Frantz, S., Rohr, K., i Stiehl, H.S. (1998). 'Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images', Journal of computing and information technology, 6(4), str. 435-447. Preuzeto s: https://hrcak.srce.hr/150209 (Datum pristupa: 08.03.2021.)
Vancouver
Frantz S, Rohr K, Stiehl HS. Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images. Journal of computing and information technology [Internet]. 1998 [pristupljeno 08.03.2021.];6(4):435-447. Dostupno na: https://hrcak.srce.hr/150209
IEEE
S. Frantz, K. Rohr i H.S. Stiehl, "Multi-Step Differential Approaches for the Localization of 3D Point Landmarks in Medical Images", Journal of computing and information technology, vol.6, br. 4, str. 435-447, 1998. [Online]. Dostupno na: https://hrcak.srce.hr/150209. [Citirano: 08.03.2021.]

Sažetak
In this contribution, we are concerned with the detection and refined subvoxel localization of 3D point landmarks. We propose multi-step differential approaches which are generalizations of an existing two-step approach for subpixel localization of 2D point landmarks. This two-step approach combines landmark detection by applying a differential operator with refined localization through a differential edge intersection approach. In this paper, we investigate the localization performance of this two-step approach for an analytical model of a Gaussian blurred L-corner as well as a Gaussian blurred ellipse. By varying the model parameters, differently tapered and curved structures are represented. The results motivate the use of an analogous approach to 3D point landmark localization. We generalize the edge intersection approach to 3D and, by combining it with 3D differential operators for landmark detection, we propose multi-step approaches for subvoxel localization of 3D point landmarks. The multi-step approaches are experimentally tested on 3D synthetic images and 3D MR images of the human head. We show that the multi-step approaches significantly improve the localization accuracy in comparison to applying a 3D detection operator alone.

Ključne riječi
3D anatomical point landmarks; 3D differential operators; 3D differential edge intersection approach; subvoxel localization

Hrčak ID: 150209

URI
https://hrcak.srce.hr/150209

Posjeta: 466 *