Abstract
Applying 3D differential operators to extract point landmarks from medical images generally suffers from false detections. A considerable number of these false detections is caused by neighboring structures that are included in the region-of-interest (ROI) specified by the observer. The main contributions of this paper are two different approaches to reducing false detections resulting from neighboring structures. First, we present a statistical differential approach to selecting a suitable ROI size automatically. Second, we propose a differential approach to incorporating prior knowledge of the intensity structure at a landmark. Also, to cope with anisotropic voxel sizes in estimating partial derivatives, we implemented a computationally efficient scheme based on cubic B-spline image interpolation. Experimental results based on 3D MR and CT images of the human head are presented.
Keywords
This work has been supported by Philips Research Hamburg, Project IMAGINE (IMage- and Atlas-Guided Interventions in NEurosurgery).
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
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, eds., Proc. VBC’96, LNCS 1131, pp. 297-306. Springer, 1996.
K. Rohr. On 3D differential operators for detecting point landmarks. Image and Vision Computing, 15(3)219–233, 1997.
T. Hartkens, K. Rohr, and H.S. Stiehl. Evaluierung der Detektionsleistung von 3DOperatoren zur Ermittlung anatomischer Landmarken in tomographischen Bildern. In T. Lehmann, V. Metzler, K. Spitzer, and T. Tolxdorff, eds., Proc. 2. Workshop Bildverarbeitung für die Medizin, Informatik aktuell, pp. 93-97. Springer, 1998.
S. Frantz, K. Rohr, and H.S. Stiehl. Refined Localization of Three-Dimensional Anatomical Point Landmarks Using Multi-Step Differential Approaches. In K.M. Hanson, ed., Proc. SPIE’s Medical Imaging: Image Processing, vol. 3338, pp. 28-38. SPIE, 1998.
S. Frantz, K. Rohr, and H.S. Stiehl. Multi-step Procedures for the Localization of 2D and 3D Point Landmarks and Automatic ROI Size Selection. In H. Burkhardt and B. Neumann, eds., Proc. ECCV’98, LNCS 1406, pp. 687-703. Springer, 1998.
L.M.J. Florack, B.M. terRomeny, J.J. Koenderink, and M.A. Viergever. General Intensity Transformations and Differential Invariants. Journ. of Mathematical Imaging and Vision, 4:171–187, 1994.
J.-P. Thirion. Extremal Points: Definition and Application to 3D Image Registration. In Proc. CVPR’94, pp. 587-592. IEEE Computer Society Press, 1994.
M. Unser, A. Aldroubi, and M. Eden. B-Spline Signal Processing: Part I—Theory. IEEE Trans, on Signal Processing, 41(2):821–833, 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Frantz, S., Rohr, K., Siegfried Stiehl, H. (1999). Reducing False Detections in Extracting 3D Anatomical Point Landmarks. In: Evers, H., Glombitza, G., Meinzer, HP., Lehmann, T. (eds) Bildverarbeitung für die Medizin 1999. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60125-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-60125-5_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65627-2
Online ISBN: 978-3-642-60125-5
eBook Packages: Springer Book Archive