High-speed Reconstruction Of SPECT Mages With A Tailored Piecewise Neural Network

Artificial neural networks (ANNs) have proven to be highly adept at mapping complex functional relationships. We have previously shown that a standard backpropagation neural network can be trained to reconstruct sections of single photon emission computed tomography (SPECT) images based on the planar image projections as inputs. In this study, we demonstrate that a neural network that utilizes a tailored three-phase piecewise activation function is able to perform high-speed reconstructions of SPECT images after learning the relationship between the planar images and the tomographic reconstructions. In addition, the tailored piecewise neural network produces reconstructions with significantly lower RMS error, and does so in far less training iterations, than a standard backpropagation ANN. The tailored piecewise function used in this research enables the network to train on a continuous range of outputs more efficiently than with a standard sigmoidal function. Based on the results obtained, we hypothesize that the optimal ANN transfer function or functions, are directly related to the statistical distribution of the training set data. As a preliminary demonstration, a neural network with statistically derived activation functions is shown to have better training and generalization characteristics for SPECT reconstruction than either the single sigmoidal or the three- phase sigmoidalmore » activation functions.« less