Performance issues in shape classification

S. J. Timoner, P. Golland, R. Kikinis, M. E. Shenton, W. E. L. Grimson, W. M. Wells III
Proceedings of the 5th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI 2002
Pages 355-362.
2002

Download full paper

Abstract

Shape comparisons of two groups of objects often have two goals: to create a classifier to separate the groups and to provide information that shows differences between classes. We examine issues that are important for shape analysis in a study comparing schizophrenic patients to normal subjects. For this study, non-linear classifiers provide large accuracy gains over linear ones. Using volume information directly in the classifier provides gains over a classifier that normalizes the data for volume. We compare two different representations of shape: displacement fields and distance maps. We show that the classifier based on displacement fields outperforms the one based on distance maps. We also show that displacement fields provide more information in visualizing shape differences than distance maps.

Reference

Timoner SJ, Golland P, Kikinis R, Shenton ME, Grimson WEL, III WMW. Performance issues in shape classification. In Proceedings of the 5th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI 2002. Springer-Verlag GmbH, 2002;355-362.

Grants

NIH/NIMH 2RO1 MH50740, NIH/NIMH 2K02 MH01110, Martinos Center, Fannie and John Hertz Foundation, NSF ERC, NIH P41 RR13218, NSF IIS 9610249, VA Merit Award(MES) 2000-2008

Research area

shapeanalysis
© 2013 Psychiatry Neuroimaging Laboratory | Last updated 04.15.2013