Abstract
Statistical analysis of anatomical shape differences between two different populations can be reduced to a classification problem, i.e., learning a classifier function for assigning new examples to one of the two groups while making as few mistakes as possible. In this framework, feature vectors representing the shape of the organ are extracted from the input images and are passed to the learning algorithm. The resulting classifier then has to be interpreted in terms of shape differences between the two groups back in the image domain. We propose and demonstrate a general approach for such interpretation using deformations of outline meshes to represent shape differences. Given a classifier function in the feature space, we derive a deformation that corresponds to the differences between the two classes while ignoring shape variability within each class. The algorithm essentially estimates the gradient of the classification function with respect to node displacements in the outline mesh and constructs the deformation of the mesh that corresponds to moving along the gradient vector. The advantages of the presented algorithm include its generality (we derive it for a wide class of non-linear classifiers) as well as its flexibility in the choice of shape features used for classification. It provides a link from the classifier in the feature space back to the natural representation of the original shapes as surface meshes. We demonstrate the algorithm on artificial examples, as well as a real data set of the hippocampus-amygdala complex in schizophrenia patients and normal controls.
Acknowledgments
Quadratic optimization was performed using PR LOQO optimizer written by Alex Smola.
This research was supported in part by NSF IIS 9610249 grant.M. E. Shenton was supported by NIMH K02, MH 01110 and R01 MH 50747 grants, R. Kikinis was supported by NIH PO1 CA67165, R01RR11747, P41RR13218 and NSF ERC 9731748 grants.
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
F. L. Bookstein. Landmark methods for forms without landmarks: morphometrics of group differences in outline shape. Medical Image Analysis, 1(3):225–243, 1996.
C. Brechbühler, G. Gerig and O. Kübler. Parameterization of closed surfaces for 3-D shape description. CVGIP: Image Understanding, 61:154–170, 1995.
C. J. C. Burges. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 2(2):121–167, 1998.
C. J. C. Burges. Geometry and Invariance in Kernel Based Methods. In Advances in Kernel Methods: Support Vector Learning, Eds. B. Schölkopf, C. J. C. Burges, A. J. Smola, MIT Press, 89–116, 1998.
T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham. Training Models of Shape from Sets of Examples. In Proc. British Machine Vision Conference, 9–18, Springer-Verlag, 1992.
J. G. Csernansky et al. Hippocampal morphometry in schizophrenia by high dimensional brain mapping. In Proc. Nat. Acad. of Science, 95(19):11406–11411, 1998.
C. Davatzikos, et al. A Computerized Method for Morphological Analysis of the Corpus Callosum. J. Computer Assisted Tomography,20:88–97, 1996.
P. Golland, W. E. L. Grimson and R. Kikinis. Statistical Shape Analysis Using Fixed Topology Skeletons: Corpus Callosum Study. In Proc. IPMI'99, LNCS 1613:382–387, 1999.
P. Golland, W. E. L. Grimson, M. E. Shenton and R. Kikinis. Small Sample Size Learning for Shape Analysis of Anatomical Structures. In Proc. MICCAI'2000, LNCS 1935:72–82, 2000.
A. Kelemen, G. Sz'ekely, and G. Gerig. Three-dimensional Model-Based Segmentation. In Proc. IEEE Intl. Workshop on Model Based 3D Image Analysis, Bombay, India, 87–96, 1998.
J. Martin, A. Pentland, and R. Kikinis. Shape Analysis of Brain Structures Using Physical and Experimental Models. In Proc. CVPR'94, 752–755, 1994.
M. E. Leventon, W. E. L. Grimson and O. Faugeras. Statistical Shape Influence in Geodesic Active Contours. In Proc. CVPR'2000, 316–323, 2000.
A. M. C. Machado and J. C. Gee. Atlas warping for brain morphometry. In Proc. SPIE Medical Imaging 1998: Image Processing, SPIE 3338:642–651, 1998.
S. M. Pizer, et al. Segmentation, Registration, and Measurement of Shape Variation via Image Object Shape. IEEE Transactions on Medical Imaging, 18(10): 851–865, 1996.
S. Romdhani, S. Gong and A. Psarrou. A Multi-View Nonlinear Active Shape Model Using Kernel PCA. In Proc. BMVC'99, 483–492, 1999.
M. E. Shenton, et al. Abnormalities in the left temporal lobe and thought disorder in schizophrenia: A quantitative magnetic resonance imaging study. New England J. Medicine, 327:604–612, 1992.
L. Staib and J. Duncan. Boundary finding with parametrically deformable models. IEEE PAMI, 14(11):1061–1075, 1992.
G. Sz'ekely et al. Segmentation of 2D and 3D objects from MRI volume data using constrained elastic deformations of flexible Fourier contour and surface models. Medical Image Analysis, 1(1):19–34, 1996.
B. Schölkopf, A. Smola, and K.-R. Müller. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 10:1299–1319, 1998.
V. N. Vapnik. Statistical Learning Theory. John Wiley & Sons, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Golland, P., Grimson, W.E.L., Shenton, M.E., Kikinis, R. (2001). Deformation Analysis for Shape Based Classification. In: Insana, M.F., Leahy, R.M. (eds) Information Processing in Medical Imaging. IPMI 2001. Lecture Notes in Computer Science, vol 2082. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45729-1_54
Download citation
DOI: https://doi.org/10.1007/3-540-45729-1_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42245-7
Online ISBN: 978-3-540-45729-9
eBook Packages: Springer Book Archive