Abstract
We introduce a new approach for the localization of 3D anatomical point landmarks. The approach uses 3D parametric intensity models of anatomical structures which are directly fit to the image intensities. We developed an analytic model based on the Gaussian error function to efficiently model tip-like structures of ellipsoidal shape. The approach has been successfully applied to accurately localize the tips of ventricular horns in 3D MR image data.
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
J.-P. Thirion, “New Feature Points based on Geometric Invariants for 3D Image Registration”, Int. J. of Computer Vision 18:2, 1996, 121–137
K. Rohr, “On 3D differential operators for detecting point landmarks”, Image and Vision Computing 15:3, 1997, 219–233
T. Hartkens, K. Rohr, H.S. Stiehl, “Evaluation of 3D Operators for the Detection of Anatomical Point Landmarks in MR and CT Images”, CVIU 85, 2002, 1–19
S. Frantz, K. Rohr, and H.S. Stiehl, “Localization Of 3D Anatomical Point Landmarks In 3D Tomographic Images Using Deformable Models”, Proc. MICCAI 2000, Springer, 2000, 492–501
M. Alker, S. Frantz, K. Rohr, and H.S. Stiehl, “Hybrid Optimization for 3D Landmark Extraction: Genetic Algorithms and Conjugate Gradient Method”, Proc. BVM 2002, Springer, 2002, 314–317
K. Rohr, “Recognizing Corners by Fitting Parametric Models”, International J. of Computer Vision 9:3, 1992, 213–230
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wörz, S., Rohr, K. (2003). Localization of Anatomical Point Landmarks in 3D Medical Images by Fitting 3D Parametric Intensity Models. In: Wittenberg, T., Hastreiter, P., Hoppe, U., Handels, H., Horsch, A., Meinzer, HP. (eds) Bildverarbeitung für die Medizin 2003. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18993-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-18993-7_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00619-0
Online ISBN: 978-3-642-18993-7
eBook Packages: Springer Book Archive