Title :
Approximate reconstruction of PET data with a self-organizing neural network
Author :
Comtat, C. ; Morel, C.
Author_Institution :
Inst. de Phys. Nucleaire, Lausanne Univ., Switzerland
fDate :
5/1/1995 12:00:00 AM
Abstract :
Self-organization was observed using the algorithm of Kohonen with an original “distance” adapted to stimuli resulting from coincident detections of electron-positron annihilation photon pairs. This has led to a method for approximate reconstruction of two-dimensional positron emission tomography (2-D PET) images that is totally independent of the number of detectors. To obtain meaningful information about the distribution of the radioactive tracer, a toroidal architecture must be used for the network
Keywords :
biomedical imaging; image reconstruction; medical image processing; positron emission tomography; self-organising feature maps; 2-D PET images; approximate reconstruction; electron-positron annihilation photon pairs; self-organizing neural network; two-dimensional positron emission tomography images; Cognitive science; Computer networks; Detectors; Econometrics; Equations; Image reconstruction; Neural networks; Positron emission tomography; Random number generation; Recurrent neural networks;
Journal_Title :
Neural Networks, IEEE Transactions on
