Abstract
The boundaries of many biological objects are two-dimensional curves which evolve non-rigidly with time. This paper contains a theory and experiments for estimating motion of such curves using local shape. Beginning from first principles, a symmetric and explicitly non-rigid formulation is developed. The formulation uses the topology of correspondences and its associated geometry.
A numerical implementation of the resulting algorithm is also reported. The algorithm is used to estimate non-rigid motion of the endocardium in 21 MRI image sequences of normal and post-infarct dog hearts. Over 500 correspondences were computed. The measured average return error of the algorithm was less than 1 pixel.
Preview
Unable to display preview. Download preview PDF.
References
Ayache N., Cohen I., Herlin I., “Medical Image Tracking,” in Active Vision, ed. Blake A., Yuille A., M.I.T. Press, 1992.
Duncan J. S., Owen R. L., Staib L. H., Anandan P., “Measurement of Non-Rigid Motion Using Contour Shape Descriptors,” Proc. CVPR, Maui, HI, 1991, 318–324.
Gold S., Lu C. P., Rangarajan A., et al., “New Algorithms for 2D and 3D Point Matching,” Advances in Neural Inf. Proc. Sys., 7, 1995.
McEachen J. C., Duncan J. S., “A Constrained Analytic Solution for Tracking Non-rigid Motion of the Left Ventricle,” IEEE 18th Annual Northeast Bioengineering Conf., Univ. of Rhode Island, March 1992, 137–138.
McEachen J. C., Duncan J. S., “Shape-based Tracking of Naturally Occurring Annuli in Image Sequences,” CVPR, New York City, NY, 1993, 613–614.
Shi P., Robinson G., Duncan J. S., “Myocardial Motion and Function Assessment using 4D Images,” Visualization in Biomedical Computing, 1994, 148–159.
Tagare H. D., O'Shea D., “The Topology and Geometry of Non-rigid Shape-based Correspondence,” Technical Report, 95-3, Yale University, 1995.
Tagare H. D., O'Shea D., “Non-rigid Shape-based Correspondence: The Manifold Formulation,” Technical Report (Forthcoming).
Tagare H. D., O'Shea D., Rangarajan A., “A Geometric Criterion for Shape-Based Non-Rigid Correspondence,” Intl. Conf. on Computer Vision, Boston, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tagare, H.D. (1997). Non-rigid curve correspondence for estimating heart motion. In: Duncan, J., Gindi, G. (eds) Information Processing in Medical Imaging. IPMI 1997. Lecture Notes in Computer Science, vol 1230. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63046-5_48
Download citation
DOI: https://doi.org/10.1007/3-540-63046-5_48
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63046-3
Online ISBN: 978-3-540-69070-2
eBook Packages: Springer Book Archive