loading page

A Deep Recurrent Neural Network with Gated Momentum Unit for CT Image Reconstruction
  • Masaki Ikuta
Masaki Ikuta
Author Profile


Many algorithms and methods have been proposed for Computed Tomography (CT) image reconstruction, partic- ularly with the recent surge of interest in machine learning and deep learning methods. The majority of recently proposed methods are, however, limited to the image domain processing where deep learning is used to learn the mapping from a noisy image data set to a true image data set. While deep learning-based methods can produce higher quality images than conventional model-based post-processing algorithms, these methods have lim- itations. Deep learning-based methods used in the image domain are not sufficient for compensating for lost information during a forward and a backward projection in CT image reconstruction especially with a presence of high noise. In this paper, we propose a new Recurrent Neural Network (RNN) architecture for CT image reconstruction. We propose the Gated Momentum Unit (GMU) that has been extended from the Gated Recurrent Unit (GRU) but it is specifically designed for image processing inverse problems. This new RNN cell performs an iterative optimization with an accelerated convergence. The GMU has a few gates to regulate information flow where the gates decide to keep important long-term information and discard insignificant short- term detail. Besides, the GMU has a likelihood term and a prior term analogous to the Iterative Reconstruction (IR). This helps ensure estimated images are consistent with observation data while the prior term makes sure the likelihood term does not overfit each individual observation data. We conducted a synthetic image study along with a real CT image study to demonstrate this proposed method achieved the highest level of Peak Signal to Noise Ratio (PSNR) and Structure Similarity (SSIM). Also, we showed this algorithm converged faster than other well-known methods.