Neural network with maximum entropy constraint for nuclear medicine image restoration

A neural-network-based algorithm is proposed for the restoration of nuclear medicine images as required for antibody therapy. The method was designed to address the particular problem of restoration of planar and tomographic bremsstrahlung data acquired with a gamma camera. Restoration was achieved by minimizing the energy function of the Hopfield network using a maximum entropy constraint. The performance of the proposed algorithm was tested on simulated data and planar gamma camera images of pure p-emitting radionuclides used in radioimmunotherapy. The results were compared with those of previously reported restoration techniques based on neural networks or traditional filters. Qualitative and quantitative analysis of the data suggested that the neural network with the maximum entropy constraint has good overall restoration performance; it is stable and robust even in cases where the signal-to-noise ratio is poor and scattering effects are significant. This behavior is particularly important in imaging therapeutic doses of pure β emitters such as yttrium-90 in order to provide accurate in vivo estimates of the radiation dose to the target and/or the critical organs.