Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deformable Fourier surfaces for volume segmentation in SPECT

Floreby, L ; Sjögreen Gleisner, Katarina LU ; Sörnmo, Leif LU and Ljungberg, Michael LU (1998) 14th International Conference on Pattern Recognition (ICPR 1998) 1. p.358-360
Abstract
Three-dimensional boundary finding based on Fourier surface optimization is presented as a method for segmentation of SPECT images. Being robust against noise and adjustable with respect to its detail resolution, it forms an interesting alternative in this application area. A three-dimensional approach can also be assumed to increase the possibility of delineating low contrast regions, as compared to a two-dimensional slice-by-slice approach. We apply boundary finding to Monte Carlo simulated SPECT images of the computer-based anthropomorphic Zubal phantom in order to evaluate the influence of object contrast and noise on the segmentation accuracy. Segmentation is also performed in real patient images
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceeedings of the Fourteenth International Conference on Pattern Recognition
volume
1
pages
3 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
14th International Conference on Pattern Recognition (ICPR 1998)
conference location
Brisbane, Australia
conference dates
1998-08-16 - 1998-08-20
ISSN
1051-4651
ISBN
0-8186-8512-3
DOI
10.1109/ICPR.1998.711153
language
English
LU publication?
yes
id
89d086c5-2dc9-482f-ab2b-69f5a43400c4 (old id 1114056)
date added to LUP
2016-04-01 16:16:25
date last changed
2018-11-21 20:40:06
@inproceedings{89d086c5-2dc9-482f-ab2b-69f5a43400c4,
  abstract     = {{Three-dimensional boundary finding based on Fourier surface optimization is presented as a method for segmentation of SPECT images. Being robust against noise and adjustable with respect to its detail resolution, it forms an interesting alternative in this application area. A three-dimensional approach can also be assumed to increase the possibility of delineating low contrast regions, as compared to a two-dimensional slice-by-slice approach. We apply boundary finding to Monte Carlo simulated SPECT images of the computer-based anthropomorphic Zubal phantom in order to evaluate the influence of object contrast and noise on the segmentation accuracy. Segmentation is also performed in real patient images}},
  author       = {{Floreby, L and Sjögreen Gleisner, Katarina and Sörnmo, Leif and Ljungberg, Michael}},
  booktitle    = {{Proceeedings of the Fourteenth International Conference on Pattern Recognition}},
  isbn         = {{0-8186-8512-3}},
  issn         = {{1051-4651}},
  language     = {{eng}},
  pages        = {{358--360}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Deformable Fourier surfaces for volume segmentation in SPECT}},
  url          = {{http://dx.doi.org/10.1109/ICPR.1998.711153}},
  doi          = {{10.1109/ICPR.1998.711153}},
  volume       = {{1}},
  year         = {{1998}},
}