<title>Re-embedding vs. clustering as shape indexing strategies for medical image databases</title>

Xiaoning Qian, Hemant D. Tagare, Robert K. FulbrightProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2005 · DOI

Abstract

Fast retrieval using complete or partial shapes of organs is an important functionality in medical image databases. Shapes of organs can be defined as points in shape spaces, which, in turn, are curved manifolds with a well-defined metric. In this paper, we experimentally compare two indexing techniques for shape spaces: first, we re-embed the shape space in a Euclidean space and use co-ordinate based indexing, and second, we used metric based hierarchical clustering for directly indexing shape space. The relative performances are evaluated with images from the NHANES II database of lumbar and cervical spine x-ray images on a shape similarity query. The experiments show that indexing using re-embedding is superior to cluster-based indexing.
BibTeX
@inproceedings{qian2005lt,
  author = {Xiaoning Qian and Hemant D. Tagare and Robert K. Fulbright},
  title = {{\<title\>Re-embedding vs. clustering as shape indexing strategies for medical image databases\</title\>}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2005},
  doi = {10.1117/12.595280},
}

Loading related content...

Figure