Title :
Application of neural networks to the identification of the compton interaction sequence in compton imagers
Author :
Zoglauer, Andreas ; Boggs, Steven E.
Author_Institution :
Univ. of California at Berkeley, Berkeley
fDate :
Oct. 26 2007-Nov. 3 2007
Abstract :
Compton cameras are well suited to image photons from a few hundred keV up to several MeV. However, one important data analysis step presents a significant challenge: the reconstruction of the Compton interaction sequence (event reconstruction). We present a new approach to event reconstruction based on a multi-layer perceptron neural network with a sigmoid activation function using back-propagation as the learning approach. Simulations show that this new method outperforms the classic event reconstruction approach and achieves roughly the same performance as the Bayesian approach to event reconstruction for events with two interactions and exceeds its performance for events with three interactions.
Keywords :
Compton effect; germanium radiation detectors; image reconstruction; learning (artificial intelligence); multilayer perceptrons; Compton cameras; Compton imagers; Compton interaction sequence identification; back-propagation learning approach; double-sided germanium-strip detectors; event reconstruction; multilayer perceptron neural network; nuclear Compton telescope; sigmoid activation function; Bayesian methods; Energy resolution; Event detection; Gamma ray detection; Gamma ray detectors; Image reconstruction; Neural networks; Particle scattering; Rayleigh scattering; Telescopes;
Conference_Titel :
Nuclear Science Symposium Conference Record, 2007. NSS '07. IEEE
Conference_Location :
Honolulu, HI
Print_ISBN :
978-1-4244-0922-8
Electronic_ISBN :
1095-7863
DOI :
10.1109/NSSMIC.2007.4437096