Correction for scatter and cross-talk contaminations in dual radionuclide /sup 99m/Tc and /sup 123/I images using artificial neural network

Artificial neural network (ANN) is shown to be an effective tool in separating scatter and cross-talk from the primary photons in simultaneous dual radionuclide imaging. Generally, a large number of input energy windows are required within the network structure whilst the commercial cameras have only 3-8 energy windows. It is difficult to use two input windows within the ANN structure for the contamination corrections of /sup 99m/Tc//sup 123/I images acquired using only two photo-peak energy windows. In this work, we designed a new ANN network with 24 inputs, and 32 nodes in the hidden layer and two nodes in the output layer, to correct for scatter and cross-talk contaminations on /sup 99m/Tc//sup 123/I images acquired using two photo-peak windows. We trained the network using experimentally acquired /sup 99m/Tc and /sup 123/I spectrum data using RSD brain phantom. The neural network package Stuttgart Neural Network Simulator (SNNSv4.2), from the University of Stuttgart, was used for the neural network training and the cross-talk corrections. Two sets of image data were tested: one was a human activation images and the other was a cylindrical striatal phantom. Our results show a great improvement on both the human activation and the cylindrical striatal phantom images. Further work is to test our new approach on more /sup 99m/Tc//sup 123/I imaging data and apply it to other radionuclide combinations such as /sup 201/Tl//sup 99m/Tc.