Nuclear medicine image segmentation using a connective network

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 (pixel values) is presented. A reconstructed 2-D slice image is analyzed as a multi-pixel system where pixel values 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 values (or 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.