Scatter correction in multinuclide data acquisition by means of a neural network

Abstract

Presents a new method for estimating primary photons with an artificial neural network in a dual isotope SPECT study. The target isotopes are /sup 123/I and /sup 99m/Tc which are used for myocardial imaging (/sup 99m/Tc-MIBI and /sup 123/I-BMIPP). These two radionuclides have close photopeak energies. To estimate the primary photons the authors used a neural network which had three layers: one input layer with ten units, one hidden layer with twenty units and one output layer with two units. As input values to the input units, the authors used count ratios which were the ratios of the counts acquired with narrow energy windows (6 keV) to the total count acquired with a broad window in an energy range from 120 to 180 keV. The outputs were a primary count ratio of /sup 123/I and a primary count ratio of /sup 99m/Tc and /sup 123/I. With these primary count ratios and the total count the authors calculated the primary count of the pixel directly. The neural network was trained true energy spectra calculated by a Monte Carlo simulation. The simulation showed that an accurate estimation of primary photons was accomplished.