Correction for Scatter and Cross-talk Contaminations in Dual Radionuclide 99m-Tc and 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 99mTc/123I 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 99mTc/123I images acquired using two photo-peak windows. We trained the network using experimentally acquired 99mTc and 123I 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 99mTc/ 123I imaging data and apply it to other radionuclide combinations such as 201Tl / 99mTc.