Share Email Print
cover

Proceedings Paper

Fully automatic estimation of object pose for segmentation initialization: application to cardiac MR and echocardiography images
Author(s): Meng Ma; Johan G. Bosch; Johan H. C. Reiber; Boudewijn P. F. Lelieveldt
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Automatic image segmentation techniques are essential for medical image interpretation and analysis. Though numerous methods on image segmentation have been reported, the quality of a segmentation often heavily relies on the positioning of an accurate initial contour. In this paper, a novel solution is presented for the automated object detection in medical image data. A shape- and intensity template is generated from a training set, and both the search image and the template are mapped into a log-polar domain, where rotation and scale are represented by a translation. Orientation and scale of the object are estimated by determining maximum normalized correlation using a Symmetric Phase Only Matched Filter (SPOMF) with a peak enhancement filter. The detected orientation and scale are subsequently applied to the template, and a second pass of the SPOMF using the transformed template yields the actual position of the object in the search image. Performance tests were carried out on two imaging modalities: a set of cardiac MRI images from 34 patients and 2D echocardiograms from 100 patients.

Paper Details

Date Published: 26 March 2007
PDF: 8 pages
Proc. SPIE 6512, Medical Imaging 2007: Image Processing, 65123J (26 March 2007); doi: 10.1117/12.711125
Show Author Affiliations
Meng Ma, Leiden Univ. Medical Ctr. (Netherlands)
Johan G. Bosch, Erasmus Medical Ctr., Rotterdam (Netherlands)
Johan H. C. Reiber, Leiden Univ. Medical Ctr. (Netherlands)
Boudewijn P. F. Lelieveldt, Leiden Univ. Medical Ctr. (Netherlands)


Published in SPIE Proceedings Vol. 6512:
Medical Imaging 2007: Image Processing
Josien P. W. Pluim; Joseph M. Reinhardt, Editor(s)

© SPIE. Terms of Use
Back to Top