In this paper an original approach to the reconstruction problem using a recurrent neural network is presented. In our method parallel beam projections is used. To decrease the number of desired projections the grid "friendly" angles of the parallel projections are selected according to the discrete Radon transform (DRT). Performed computer simulations show that the presented neural network reconstruction algorithm outperforms the convolution/back-projection method in the reconstructed image quality.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.