Skip to main content

Nuclear medicine image segmentation using a connective network

Publication ,  Journal Article
Peter, J; Freyer, R; Smith, MF; Scarfone, C; Coleman, RE; Jaszczak, RJ
Published in: IEEE Transactions on Nuclear Science
December 1, 1997

A method for post-reconstruction nuclear medicine image segmentation based on an analogy to the Ising model of a two-dimensional square lattice of N particles (pixels) is presented. A reconstructed 2-D slice image is analyzed as a multi-pixel system where pixels correspond to a 2-D lattice of points with non-zero interaction energy with their nearest neighbors. The model assumes that pixel intensities belonging to the same homogeneous image region are relatively constant, where region intensity means (or labels) are determined by both statistical parameter estimation and deterministic image analysis. The change in value of each pixel during the segmentation process depends on (1) the statistical properties in the reconstructed image and (2) the states of its nearest neighbors. These changes are either in the direction of statistically estimated intensity means or other previously analyzed regions of significance. The segmentation technique uses a new innovative relaxation labeling connective network. The global relaxation dynamics of the network are controlled by the interaction of local synergetic and logistic functions assigned to each pixel. This result may improve the localization of hot and cold regions of interest as compared to the original image. © 1997 IEEE.

Duke Scholars

Published In

IEEE Transactions on Nuclear Science

DOI

ISSN

0018-9499

Publication Date

December 1, 1997

Volume

44

Issue

4 PART 1

Start / End Page

1583 / 1590

Related Subject Headings

  • Nuclear & Particles Physics
  • 5106 Nuclear and plasma physics
  • 0903 Biomedical Engineering
  • 0299 Other Physical Sciences
  • 0202 Atomic, Molecular, Nuclear, Particle and Plasma Physics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Peter, J., Freyer, R., Smith, M. F., Scarfone, C., Coleman, R. E., & Jaszczak, R. J. (1997). Nuclear medicine image segmentation using a connective network. IEEE Transactions on Nuclear Science, 44(4 PART 1), 1583–1590. https://doi.org/10.1109/23.632736
Peter, J., R. Freyer, M. F. Smith, C. Scarfone, R. E. Coleman, and R. J. Jaszczak. “Nuclear medicine image segmentation using a connective network.” IEEE Transactions on Nuclear Science 44, no. 4 PART 1 (December 1, 1997): 1583–90. https://doi.org/10.1109/23.632736.
Peter J, Freyer R, Smith MF, Scarfone C, Coleman RE, Jaszczak RJ. Nuclear medicine image segmentation using a connective network. IEEE Transactions on Nuclear Science. 1997 Dec 1;44(4 PART 1):1583–90.
Peter, J., et al. “Nuclear medicine image segmentation using a connective network.” IEEE Transactions on Nuclear Science, vol. 44, no. 4 PART 1, Dec. 1997, pp. 1583–90. Scopus, doi:10.1109/23.632736.
Peter J, Freyer R, Smith MF, Scarfone C, Coleman RE, Jaszczak RJ. Nuclear medicine image segmentation using a connective network. IEEE Transactions on Nuclear Science. 1997 Dec 1;44(4 PART 1):1583–1590.

Published In

IEEE Transactions on Nuclear Science

DOI

ISSN

0018-9499

Publication Date

December 1, 1997

Volume

44

Issue

4 PART 1

Start / End Page

1583 / 1590

Related Subject Headings

  • Nuclear & Particles Physics
  • 5106 Nuclear and plasma physics
  • 0903 Biomedical Engineering
  • 0299 Other Physical Sciences
  • 0202 Atomic, Molecular, Nuclear, Particle and Plasma Physics