Abstract
Nonlinear image registration is a prerequisite for various medical image analysis applications. Many data acquisition protocols suffer from problems due to breathing motion which has to be taken into account for further analysis. Intensity based nonlinear registration is often used to align differing images, however this requires a large computational effort, is sensitive to intensity variations and has problems with matching small structures. In this work a feature-based image registration method is proposed that combines runtime efficiency with good registration accuracy by making use of a fully automatic feature matching and registration approach. The algorithm stages are 3D corner detection, calculation of local (SIFT) and global (Shape Context) 3D descriptors, robust feature matching and calculation of a dense displacement field. An evaluation of the algorithm on seven synthetic and four clinical data sets is presented. The quantitative and qualitative evaluations show lower runtime and superior results when compared to the Demons algorithm.
This work was funded by Siemens MED CT, Forchheim and Siemens PSE AS, Graz.
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
Wildberger, J.E., Klotz, E., Ditt, H., Mahnken, A.H., Spüntrup, E., Günther, R.W.: Multi-slice CT for Visualization of Acute Pulmonary Embolism: Single Breath-hold Subtraction Technique. Fortschritte auf dem Gebiet der Roentgenstrahlen und der bildgebenden Verfahren 177, 17–23 (2005)
Maintz, J., Viergever, M.: A Survey of Medical Image Registration. Medical Image Analysis 2(1), 1–36 (1998)
Zitova, B., Flusser, J.: Image registration methods: A survey. Image and Vision Computing 21(11), 977–1000 (2003)
Thirion, J.-P.: Image matching as a diffusion process: An analogy with Maxwell’s demons. Medical Image Analysis 2(3), 243–260 (1998)
Förstner, W.: A Feature Based Correspondence Algorithm for Image Matching. Int. Arch. of Photogrammetry and Remote Sensing 26(3), 150–166 (1986)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal on Computer Vision 60(2), 91–110 (2004)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE PAMI 24(4), 509–522 (2002)
Bookstein, F.L.: Principal Warps: Thin-Plate Splines and the Decomposition of Deformations. IEEE PAMI 11(6), 567–585 (1989)
Rohr, K.: Landmark-Based Image Analysis Using Geometric and Intensity Models. In: Computational Imaging and Vision, Kluwer Academic Publishers, Dordrecht (2001)
Johnson, H.J., Christensen, G.E.: Consistent Landmark and Intensity-Based Image Registration. IEEE Transactions on Medical Imaging 21(5), 450–461 (2002)
Chui, H., Win, L., Schultz, R., Duncan, J., Rangarajan, A.: A unified non-rigid feature registration method for brain mapping. Medical Image Analysis 7, 113–130 (2003)
Mortensen, E.N., Deng, H., Shapiro, L.: A SIFT Descriptor with Global Context. In: IEEE CVPR 2005, pp. 184–190 (2005)
Mikolajczyk, K., Schmid, C.: Performance Evaluation of Local Descriptors. IEEE PAMI 27(10), 1615–1630 (2005)
Fua, P.: A Parallel Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features. Machine Vision and Applications 6, 35–49 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Urschler, M., Bauer, J., Ditt, H., Bischof, H. (2006). SIFT and Shape Context for Feature-Based Nonlinear Registration of Thoracic CT Images. In: Beichel, R.R., Sonka, M. (eds) Computer Vision Approaches to Medical Image Analysis. CVAMIA 2006. Lecture Notes in Computer Science, vol 4241. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11889762_7
Download citation
DOI: https://doi.org/10.1007/11889762_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46257-6
Online ISBN: 978-3-540-46258-3
eBook Packages: Computer ScienceComputer Science (R0)