Correction for Crosstalk Contaminations in Dual Radionuclide and Images Using Artificial Neural Network

Use of an artificial neural network (ANN) has been previously shown to be an effective tool in compensating scatter and crosstalk from the primary photons in simultaneous dual ra- dionuclide imaging. Generally, a large number of input energy win- dows are required within the network structure while the com- mercial cameras have only 3-8 energy windows. It is difficult to use two input windows within the ANN structure for the crosstalk contamination corrections of images acquired using only two photopeak energy windows. In this paper, we designed an ANN network with 24 inputs, 32 nodes in the hidden layer and two nodes in the output layer, to correct for crosstalk contamination in images acquired using two photopeak windows. We trained the network using experimentally acquired and spectrum data using the RSD brain phantom. The neural net- work package Stuttgart Neural Network Simulator (SNNSv4.2), from the University of Stuttgart, was used for the neural network training and the crosstalk corrections. Two sets of image data were tested. The first was a human activation study and the other used a cylindrical striatal phantom. Our results show a great improve- ment on both the human activation and the cylindrical striatal phantom images. Further work is to test our new approach on more imaging data and apply it to other radionuclide com- binations such as .