Plug-and-Play gradient-based denoisers applied to CT image enhancement

Blur and noise corrupting Computed Tomography (CT) images can hide or distort small but important details, negatively affecting the consequent diagnosis. In this paper, we present a novel gradient-based Plug-and-Play (PnP) algorithm and we apply it to restore CT images. The plugged denoiser is implemented as a deep Convolutional Neural Network (CNN) trained on the gradient domain (and not on the image one, as in state-of-the-art works) and it induces an external prior onto the restoration model. We further consider a hybrid scheme which combines the gradient-based external denoiser with an internal one, obtained from the Total Variation functional. The proposed frameworks rely on the Half-Quadratic Splitting scheme and we prove a general fixed-point convergence theorem, under weak assumptions on both the denoisers. The experiments confirm the effectiveness of the proposed gradient-based approach in restoring blurred noisy CT images, both in simulated and real medical settings. The obtained performances outperform the achievements of many state-of-the-art methods.