Generative adversarial networks are being extensively studied for low-dose computed tomography denoising. However, due to the similar distribution of noise, artifacts, and high-frequency components of useful tissue images, it is difficult for existing generative adversarial network-based denoising networks to effectively separate the artifacts and noise in the low-dose computed tomography images. In addition, aggressive denoising may damage the edge and structural information of the computed tomography image and make the denoised image too smooth. To solve these problems, we propose a novel denoising network called artifact and detail attention generative adversarial network. First, a multi-channel generator is proposed. Based on the main feature extraction channel, an artifacts and noise attention channel and an edge feature attention channel are added to improve the denoising network’s ability to pay attention to the noise and artifacts features and edge features of the image. Additionally, a new structure called multi-scale Res2Net discriminator is proposed, and the receptive field in the module is expanded by extracting the multi-scale features in the same scale of the image to improve the discriminative ability of discriminator. The loss functions are specially designed for each sub-channel of the denoising network corresponding to its function. Through the cooperation of multiple loss functions, the convergence speed, stability, and denoising effect of the network are accelerated, improved, and guaranteed, respectively. Experimental results show that the proposed denoising network can preserve the important information of the low-dose computed tomography image and achieve better denoising effect when compared to the state-of-the-art algorithms.

Multiple description coding (MDC) is able to stably transmit signal in un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, traditional MDC doesn’t well leverage image’s context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework, which efficiently leverages image’s context information to compress image. Firstly, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image’s content, which are compressed by standard codec. Secondly, we present multiple description reconstruction network (MDRN) including side reconstruction networks (SRN) and central reconstruction network (CRN). When any one of two lossy descriptions is received at decoder, SRN network is used to improve the quality of this decoded lossy description by simultaneously removing compression artifact and up-sampling. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural dis-similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated descriptions are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the effectiveness of our framework.

Low contrast, noise pollution and color distortion of low-light images tremendously affect human visual perception. The Retinex and its variant models are widely used for low-light image enhancement (LLIE). However, the performances of traditional Retinex algorithms are limited by intrinsic non-learnable characteristic. Recently, the latest LLIE methods directly unfold Retinex model as the popular networks such as URetinex-Net and RAUNA to resolve the black-box problem of conventional neural networks. Different from these methods focusing on the unfolding of image decomposition, we treat the classic LLIE as an image reconstruction task. Built upon Retinex theory, we propose a Retinex-Inspired Reconstruction Optimization (RIRO) model, which is unrolled as the RIRO network. This network consists of Low-light Decomposition and Enhancement Sub-Network (LDE Sub-Net) and Image Reconstruction Unrolling Sub-Network (IRU Sub-Net). The LDE Sub-Net is leveraged for the input initialization of the IRU Sub-Net. In RIRO model, we introduce a Dual-Domain Proximal (DDP) block to replace classic proximal operator, in which Fourier transform is utilized to transform spatial domain information into frequency domain information so as to simultaneously extract dual features on both spatial and frequency domains. Besides, we design a residual-aware weighted dual-fusion module and an adaptive weighted triple-fusion module to fuse different kinds of features. Numerous experiments on benchmark datasets have shown that the proposed method outperforms many advanced LIE methods. Our codes are publicly released at here.

Intelligent reflecting surface (IRS) has been deemed as an energy and spectral-efficient technology, that can potentially enhance network coverage and transmission reliability, with minimum impact on transceivers' complexity. Motivated by this, we develop a comprehensive analysis on the performance of integrating IRS into full-duplex (FD) cellular or Internet of Things (IoT) networks in both realistic Rician and Nakagami fadings. Firstly, in the context of reciprocal channels in Rician fadings, we derive the closed-form approximations of the users' outage probability (OP) and ergodic capacity (EC), under the non-central Chi-square distribution assumption on the signal-to-interference-plus-noise ratio (SINR). Further following by the Gamma distribution assumption on the SINR, we derive the cumulative distribution function (CDF) expression of the user's SINR, which is then leveraged to obtain simple yet effective closed-form expressions in terms of OP and EC. Subsequently, in Nakagami fading scenarios with the reciprocal and non-reciprocal channels, the closed forms of both users' OP and EC are obtained. Finally, the correctness of all the theoretical expressions is verified through substantial Monte Carlo simulations. The results indicate that the OP and EC deduced from Gamma distribution exhibit the fairly precise results for the arbitrary number of IRS elements, especially in Nakagami fadings.

Non-orthogonal multiple access (NOMA) has been proposed as a promising technology that is capable of improving the spectral efficiency of fifth-generation wireless networks and beyond. However, in practical communication scenarios, transceiver architectures inevitably suffer from radio frequency (RF) front-end related impairments that cause non-negligible performance degradation. This issue can be addressed by analog and digital signal processing algorithms, however, inevitable aspects of this approach such as time-varying hardware characteristics and imperfect compensation schemes result to detrimental residual distortions. In the present contribution we investigate the physical layer security of NOMA-based amplify-and-forward relay systems under such realistically incurred residual hardware impairment (RHI) effects. Exact and asymptotic analytic expressions for the corresponding outage probability (OP) and intercept probability (IP) of the considered setup over multipath fading channels are derived and corroborated by respective simulation results. Based on this, it is shown that RHI affects both the legitimate users and eavesdroppers by increasing the OP and decreasing the IP. For a fixed OP, RHI generally increases the corresponding IP, thereby reducing the secure performance of the system. Further interesting insights are provided, verifying the importance of the offered results for the effective design and deployment of secure cooperative communication systems.