Share Email Print

Proceedings Paper

Efficient similarity search on 3D bounding box annotations
Author(s): Hans-Peter Kriegel; Marisa Petri; Matthias Schubert; Michael Shekelyan; Michael Stockerl
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Searching for similar image regions in medical databases yields valuable information for diagnosis. However, most of the current approaches are restricted to special cases or they are only available for rather small data stores. In this paper, we propose a fast query pipeline for 3D similarity queries on large databases of computed tomography (CT) scans consisting of minimum bounding box annotations. As these box annotations also contain background information which is not part of the item that was actually annotated, we employ approximate segmentation approaches for distinguishing between within-object texture and background texture in order to correctly describe the annotated objects. Our method allows a compact form of object description. In our framework, we exploit this advantage for enabling very fast query times. We have validated our method on data sets of 111 and 1293 bounding box lesion annotations within the liver and other organs. Our experiments show a significant performance improvement over previous approaches in both runtime and precision.

Paper Details

Date Published: 16 February 2012
PDF: 9 pages
Proc. SPIE 8319, Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications, 83190B (16 February 2012); doi: 10.1117/12.911292
Show Author Affiliations
Hans-Peter Kriegel, Ludwig-Maximilians-Univ. München (Germany)
Marisa Petri, Ludwig-Maximilians-Univ. München (Germany)
Matthias Schubert, Ludwig-Maximilians-Univ. München (Germany)
Michael Shekelyan, Ludwig-Maximilians-Univ. München (Germany)
Michael Stockerl, Ludwig-Maximilians-Univ. München (Germany)

Published in SPIE Proceedings Vol. 8319:
Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications
William W. Boonn; Brent J. Liu, Editor(s)

© SPIE. Terms of Use
Back to Top