Thermal Noise Removal of Magnetic Resonance Images: A Deep Learning Approach Based on an Attentive Residue Multi-Dilated Network with Adaptive Filtering and Discrete Cosine Transform

Bowen Jiang, Tao Yue, Xuemei Hu

Abstract: Magnetic resonance imaging (MRI) has been applied in various fields, especially for the medical purposes. However, fine details and smooth areas of some critical patterns in an MR image polluted by common thermal noise will interfere with the diagnosis of doctors. Thermal noise in an MR image obeys Rician distribution, which is hard for conventional denoising methods based on shift invariant spatial filtering approaches to dispose. Besides, the fine detail and edge information will be inevitably damaged when smoothing the noise, which is unacceptable for medical images. In this paper, we propose two corresponding solutions. First, we design a convolutional neural network (CNN) to learn a mask that aims to directly eliminate the thermal noise in the background region, and make the noise in the MR image obey almost the same distribution. Second, we propose several improvements in terms of existing deep learning approaches for thermal noise removal. Specifically, we establish a dual-branch neural network, a frequency-domain-optimizable discrete cosine transform (DCT) module, and adopt other effective structures such as residue blocks, convolutional block attention modules (CBAM), and parallel multi-dilated GoogLeNet inception based convolutional blocks to form an attentive residue multi-dilated network (ARM-Net). We evaluate our method over the BraTS 2018 dataset at noise levels ranging from 2% to 20%. Experimental results reveal that our method achieves state-of-the-art (SOTA) performance compared with the most recent works.