Optimal Embedding for Shape Indexing in Medical Image Databases

1 January 2005

book chapter
Published by Springer Nature

Vol. 8, 377-384
https://doi.org/10.1007/11566489_47

Abstract

Fast retrieval using organ shapes is crucial in medical image databases since shape is a clinically prominent feature. In this paper, we propose that 2-D shapes in medical image databases can be indexed by embedding them into a vector space and using efficient vector space indexing. An optimal shape space embedding is proposed for this purpose. Experimental results of indexing vertebral shapes in the NHANES II database are presented. The results show that vector space indexing following embedding gives superior performance than metric indexing.

Keywords

This publication has 7 references indexed in Scilit:

Searching in metric spaces
ACM Computing Surveys, 2001
Statistical models of appearance for medical image analysis and computer vision
Published by SPIE-Intl Soc Optical Eng ,2001
Shape & Shape Theory
Wiley Series in Probability and Statistics, 1999
Deformable 2-D template matching using orthogonal curves
IEEE Transactions on Medical Imaging, 1997
Increasing retrieval efficiency by index tree adaptation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1997
Robust and Efficient Shape Indexing through Curvature Scale Space
Published by British Machine Vision Association and Society for Pattern Recognition ,1996
Mean size-and-shapes and mean shapes: a geometric point of view
Advances in Applied Probability, 1995