Abstract
In this paper, we investigate differential approaches for the localization of 3D anatomical point landmarks in 3D medical images. First, we study an existing 2D edge intersection approach for localizing corners and theoretically analyze the localization accuracy of this method for an analytic model of an L-junction. Then, we extend this approach to 3D. We propose two two-step and one three-step procedures for refined localization of 3D point landmarks. For these approaches, we experimentally analyze their localization accuracy for 3D synthetic images. Finally, we investigate the localization of anatomical landmarks of the human brain in 3D MR images. It turns out that the multi-step procedures can considerably improve the localization accuracy of landmarks in comparison to existing single-step approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
P. R. Beaudet. Rotationally invariant image operators. In Proc. Intern. Conf. Pattern Recognition, pages 579–583, Kyoto, Japan, November 1978.
F. L. Bookstein. Principal Warps: Thin-Plate Splines and the Decomposition of Deformations. IEEE Transactions On Pattern Analysis And Machine Intelligence, 11 (6): 567–585, June 1989.
L. Dreschler. Ermittlung markanter Punkte auf den Bildern bewegter Objekte und Berechnung einer 3D-Beschreibung auf dieser Grundlage. Dissertation. Fachbereich Informatik, Universität Hamburg, 1981.
W. Förstner and E. Gülch. A Fast Operator for Detection and Precise Location of Distinct Points, Corners and Centres of Circular Features. In Proc. of Intercom-mission Conference on Fast Processing on Photogrammetric Data,pages 281–305, Interlaken, Switzerland, June 1987. ISPRS Intercommission Workshop.
T. Hartkens, K. Rohr, and H. S. Stiehl. Evaluierung von Differentialoperatoren zur Detektion charakteristischer Punkte in tomographischen Bildern. In B. Jähne, P. Geißler, H. Haußecker, and F. Hering, editors, 18. DAGM-Symposium Mustererkennung, Informatik aktuell, pages 637–644. Springer-Verlag Berlin Heidelberg, September 1996.
D. F. Morrison. Multivariate Statistical Methods. McGraw-Hill Book Company, New York, NY, USA, 1967.
K. Rohr. Untersuchung von grauwertabhängigen Transformationen zur Ermittlung des optischen Flusses in Bildfolgen. Diplomarbeit. Institut für Nachrichtensysteme, Fakultät für Elektrotechnik, Universität Karlsruhe, November 1987.
K. Rohr. Localization Properties of Direct Corner Detectors. Journal of Mathematical Imaging and Vision, 4: 139–150, May 1994.
K. Rohr. On 3D Differential Operators for Detecting Point Landmarks. Image and Vision Computing, 15: 219–233, 1997.
K. Rohr, H. S. Stiehl, R. Sprengel, W. Beil, T. M. Buzug, J. Weese, and M. H. Kuhn. Point-Based Elastic Registration of Medical Image Data Using Approximating Thin-Plate Splines. In K.-H. Höhne and R. Kikinis, editors, Proc. 4th Intern. Conf. Visualization in Biomedical Computing (VBC’96), Lecture Notes in Computer Science No. 1131, pages 297–306, Hamburg, Germany, September 1996. Springer-Verlag.
J. Sobotta. Atlas der Anatomie des Menschen. Urban & Schwarzenberg, München, 19 edition, 1988.
J.-P. Thirion. Extremal Points: Definition and Application to 3D Image Registration. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1994 (CVPR ‘84),pages 587–592, Seattle, WA, USA, June 1994. IEEE Computer Society Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Frantz, S., Rohr, K., Stiehl, H.S. (1997). On the Localization of 3D Anatomical Point Landmarks in Medical Imagery Using Multi-step Differential Approaches. In: Paulus, E., Wahl, F.M. (eds) Mustererkennung 1997. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60893-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-60893-3_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63426-3
Online ISBN: 978-3-642-60893-3
eBook Packages: Springer Book Archive