Non-blind Method Research Articles

Efficacy and safety of aripiprazole or bupropion augmentation and switching in patients with treatment-resistant depression or major depressive disorder: A systematic review and meta-analysis of randomized controlled trials.

To report the first and largest systematic review and meta-analysis of randomized controlled trials (RCT) to evaluate the efficacy and safety of aripiprazole or bupropion augmentation and switching in patients with treatment-resistant depression (TRD) or major depressive disorder(MDD). We conducted a systematic literature retrieval via PubMed, Embase, Web of Science, and Cochrane until April 2023 for RCT, which evaluated the efficacy and safety of aripiprazole or bupropion augmentation and switching for patients with TRD or MDD. Outcomes measured were changes in the Montgomery-Asberg Depression Rating Scale (MADRS), response and remission rate, and serious adverse events. Five RCTs, including 4480 patients, were included for meta-analysis. Among them, two RCTs were rated as "high risk" in three aspects (allocation concealment, blinding of participants and personnel and blinding of outcome assessment) because of the non-blind method, and the quality evaluation of the remaining works of literature was "low risk". Augmentation treatment with Aripiprazole (A-ARI) was associated with a significant higher response rate compared with augmentation treatment with bupropion (A-BUP) (RR: 1.15; 95% CI: 1.05, 1.25; P = 0.0007; I2 = 23%). Besides, A-ARI had a significant higher remission rate compared with switching to bupropion (S-BUP) (RR: 1.22; 95% CI: 1.00, 1.49; P = 0.05; I2 = 59%) and A-BUP had a significant higher remission rate compared with S-BUP (RR: 1.20; 95% CI: 1.06, 1.36; P = 0.0004; I2 = 0%). In addition, there was no significant difference in remission rate(RR: 1.05; 95% CI: 0.94, 1.17; P = 0.42; I2 = 33%), improvement of MADRS(WMD: -2.07; 95% CI: -5.84, 1.70; P = 0.28; I2 = 70%) between A-ARI and A-BUP. No significant difference was observed in adverse events and serious adverse events among the three treatment strategies. A-ARI may be a better comprehensive antidepressant treatment strategy than A-BUP or S-BUP for patients with TRD or MDD. More large-scale, multi-center, double-blind RCTs are needed to further evaluated the efficacy and safety of aripiprazole or bupropion augmentation and switching treatment strategies.

Blind Image Denoising via Deep Unfolding Network With Degradation Information Guidance

Blind denoising is an active research area in image processing. In recent years, denoising methods based on deep learning have achieved outstanding results. However, directly designing more complex networks is very challenging and often lacks interpretability. Besides, existing methods also often ignore the guidance of degradation information. Therefore, how to guide the design of deep neural networks by combining traditional algorithms while predicting and utilizing degradation information is an open problem. In this brief, based on the maximum a posterior (MAP) framework, we first estimate the degradation information, and design corresponding operators to obtain initial restoration estimation in high-dimensional mapping space. On this basis, the initial estimation is substituted into the denoising problem. According to the splitting algorithm and momentum based gradient descent method, the iterative optimization of the substituted problem is carried out, and the proposed algorithm framework is obtained. Furthermore, according to the proposed algorithm framework, we design the corresponding network structure, and a novel blind unfolding network named BDUNet is introduced. Experimental results show that our network not only outperforms blind methods but also has advantages over non-blind methods.

Hyperspectral Multispectral Image Fusion via Fast Matrix Truncated Singular Value Decomposition

Recently, methods for obtaining a high spatial resolution hyperspectral image (HR-HSI) by fusing a low spatial resolution hyperspectral image (LR-HSI) and high spatial resolution multispectral image (HR-MSI) have become increasingly popular. However, most fusion methods require knowing the point spread function (PSF) or the spectral response function (SRF) in advance, which are uncertain and thus limit the practicability of these fusion methods. To solve this problem, we propose a fast fusion method based on the matrix truncated singular value decomposition (FTMSVD) without using the SRF, in which our first finding about the similarity between the HR-HSI and HR-MSI is utilized after matrix truncated singular value decomposition (TMSVD). We tested the FTMSVD method on two simulated data sets, Pavia University and CAVE, and a real data set wherein the remote sensing images are generated by two different spectral cameras, Sentinel 2 and Hyperion. The advantages of FTMSVD method are demonstrated by the experimental results for all data sets. Compared with the state-of-the-art non-blind methods, our proposed method can achieve more effective fusion results while reducing the fusing time to less than 1% of such methods; moreover, our proposed method can improve the PSNR value by up to 16 dB compared with the state-of-the-art blind methods.

Conditional Hyper-Network for Blind Super-Resolution With Multiple Degradations.

Although the single-image super-resolution (SISR) methods have achieved great success on the single degradation, they still suffer performance drop with multiple degrading effects in real scenarios. Recently, some blind and non-blind models for multiple degradations have been explored. However, these methods usually degrade significantly for distribution shifts between the training and test data. Towards this end, we propose a novel conditional hyper-network framework for super-resolution with multiple degradations (named CMDSR), which helps the SR framework learn how to adapt to changes in the degradation distribution of input. We extract degradation prior at the task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet). Specifically, the ConditionNet of our framework first learns the degradation prior from a support set, which is composed of a series of degraded image patches from the same task. Then the adaptive BaseNet rapidly shifts its parameters according to the conditional features. Moreover, in order to better extract degradation prior, we propose a task contrastive loss to shorten the inner-task distance and enlarge the cross-task distance between task-level features. Without predefining degradation maps, our blind framework can conduct one single parameter update to yield considerable improvement in SR results. Extensive experiments demonstrate the effectiveness of CMDSR over various blind, and even several non-blind methods. The flexible BaseNet structure also reveals that CMDSR can be a general framework for a large series of SISR models. Our code is available at https://github.com/guanghaoyin/CMDSR.

Blur Kernel Estimation and Non-Blind Super-Resolution for Power Equipment Infrared Images by Compressed Sensing and Adaptive Regularization.

Infrared sensing technology is more and more widely used in the construction of power Internet of Things. However, due to cost constraints, it is difficult to achieve the large-scale installation of high-precision infrared sensors. Therefore, we propose a blind super-resolution method for infrared images of power equipment to improve the imaging quality of low-cost infrared sensors. If the blur kernel estimation and non-blind super-resolution are performed at the same time, it is easy to produce sub-optimal results, so we chose to divide the blind super-resolution into two parts. First, we propose a blur kernel estimation method based on compressed sensing theory, which accurately estimates the blur kernel through low-resolution images. After estimating the blur kernel, we propose an adaptive regularization non-blind super-resolution method to achieve the high-quality reconstruction of high-resolution infrared images. According to the final experimental demonstration, the blind super-resolution method we proposed can effectively reconstruct low-resolution infrared images of power equipment. The reconstructed image has richer details and better visual effects, which can provide better conditions for the infrared diagnosis of the power system.

RestoreNet-Plus: Image restoration via deep learning in optical synthetic aperture imaging system

The synthetic aperture technology can improve the resolution effectively in the optical imaging system. In fact, the imaging blur, turbulence aberration and noise can affect the imaging quality of optical synthetic aperture imaging system seriously. Several non-blind methods are applied generally to recover the degraded maps with the prior information. However, the restoration effect is not stable enough and satisfactory. As a data-driven approach, the deep learning framework possesses advantages in solving this problem. In this paper we propose an improved network, RestoreNet-Plus, for the image restoration of optical synthetic aperture imaging system. After the proofs of numerical simulation and experiment results, RestoreNet-Plus is a better alternative compared with other methods, owing to its better restoration ability, strong denoising ability and capacity for turbulence correction error.

Blind Identification of Sparse Systems Using Symbolic Dynamics Encoding

The unique properties of chaotic signals have led to their application in improving blind system identification performance. However, the role of chaos in blind identification of a sparse system has not been investigated. In this letter, we apply symbolic dynamics to encode a random signal to reap the benefits of chaos in improving blind identification of a sparse Moving Average (MA) system. We derive an estimation technique using the encoded signal by training a machine learning model that mimics a chaotic map. The novelty of our work is to exploit the merits of chaos in improving blind estimation performance of sparse systems at low signal-to-noise (SNR) ratio. The estimation error of our method is close to the minimum mean square error of the nonblind method for sparse system estimation and works well for a short data sequence.

Nonuniform blind deblurring for single images based on adaptive edge-enhanced regularization

Natural images inevitably suffer from spatially variant blur caused by the relative motion between a camera and objects. We present an effective and efficient patch-wise edge-enhanced image regularization and a robust kernel similarity constraint to perform an accurate kernel estimation from coarse-to-fine iterations. The proposed adaptive regularization introduces a gradient magnitude penalty function into total variation to preserve and enhance salient edges while smoothing out harmful subtle structures. In addition, the similarity constraint is engaged in each patch without camera rotation effects, ensuring that the erroneous kernels can be identified by measuring the similarity among the kernels of neighbor patches and be replaced with the well-estimated ones. After obtaining accurate kernels, numerous nonblind deblurring methods can be applied to restore an image. Numerical experiments demonstrate that the proposed algorithm performs favorably without ringing artifacts and possesses high processing efficiency for natural nonuniform blurred images.

Lung ultrasound vs chest radiography in the diagnosis of children pneumonia

Background:The aim of this meta-analysis was to evaluate the diagnostic value of lung ultrasound (LUS) in comparison to chest radiography (CXR) in children with pneumonia.Methods:Computer-based retrieval was performed on PubMed and EMBASE. Quality was evaluated according to the quality assessment of diagnostic accuracy studies-2, and Meta-Disc was adopted to perform meta-analysis. Heterogeneity was assessed using Q and I2 statistics. The pooled sensitivity, specificity, and diagnostic odds ratio (DOR) with 95% confidence intervals (CIs) as the primary outcomes were calculated for each index test.Results:Twenty two studies with a total of 2470 patients met the inclusion criteria. Our results showed that the pooled sensitivity, specificity, and DOR for children with pneumonia diagnosed by LUS were 0.95 (95% CI: 0.94 to 0.96), 0.90 (95% CI: 0.87 to 0.92), and 137.49 (95% CI: 60.21 to 313.98), respectively. The pooled sensitivity, specificity, and DOR for pediatric pneumonia diagnosed by CXR was 0.91 (95% CI: 0.90 to 0.93), 1.00 (95% CI: 0.99 to 1.00), and 369.66 (95% CI: 137.14 to 996.47), respectively. Four clinical signs, including pulmonary consolidation, positive air bronchogram, abnormal pleural line, and pleural effusion were most frequently observed using LUS in the screening of children with pneumonia.Conclusions:The available evidence suggests that LUS is a reliable, valuable, and alternative method to CXR for the diagnosis of pediatric pneumonia.

RestoreNet: a deep learning framework for image restoration in optical synthetic aperture imaging system

Imaging blur is an inevitable problem in optical synthetic aperture imaging system because of the low response of frequency. Non-blind deconvolution algorithms are usually used for image restoration to obtain clear and high-resolution images. However, accurate prior information on the optical transfer function of system is required in the non-blind methods. As a data-driven approach, recent developments in deep learning have shown great potential in image processing. In this paper, a U-shaped deep learning framework named RestoreNet is proposed for image restoration, especially for removing the blur of optical synthetic aperture imaging system in a blind way. Numerical simulation and experiment results show that RestoreNet is an effective alternative with great restoration ability, stability and generalization in the image restoration of optical synthetic aperture imaging system.

Non-blind image blur removal method based on a Bayesian hierarchical model with hyperparameter priors

In many image blur removal schemes, a proper point spread function is usually estimated in advance from the blurry image, then the latent image comes out by using existing non-blind techniques. However, some of the techniques suffer from strong artifacts. Therefore, an efficient non-blind method plays an important role in image restoration issues. In most models, image priors act as the regularization terms that hold image details and suppress noises. This paper introduces a new image prior based on a parameterized scaled Gaussian model and a gamma distribution, with hyperparameters based on the statistical properties of tens of thousands of images. Our regularized cost function is then formed via a Bayesian hierarchical approach. It consists of a data fidelity term and a series of constraints on image gradients in multiple orientations. The former is used to assure the best approximation of the original image, and the latter is for preserving sharp edges. The optimization problem is solved by an effective tail-recursive algorithm based on the conjugate descent technique. Experimental results show that our model can both deal with simulated data and real scenes. The comparisons show our method outperforms others and achieves promising results.

Improved Reference Image Encryption Methods Based on 2 K Correction in the Integer Wavelet Domain

Abstract Many visually meaningful image encryption (VMIE) methods have been proposed in the literature using reference encryption. However, the most important problems of these methods are low visual quality and blindness. Owing to the low visual quality, the pre-encrypted image can be analyzed simply from the reference image and, in order to decrypt nonblind methods, users should use original reference images. In this paper, two novel reference image encryption methods based on the integer DWT (discrete wavelet transform) using 2 k correction are proposed. These methods are blind and have high visual quality, as well as short execution times. The main aim of the proposed methods is to solve the problem of the three VMIE methods existing in the literature. The proposed methods mainly consist of the integer DWT, pre-encrypted image embedding by kLSBs (k least significant bits) and 2 k correction. In the decryption phase, the integer DWT and pre-encrypted image extraction with the mod operator are used. Peak signal-to-noise ratio (PSNR) measures the performances of the proposed methods. Experimental results clearly illustrate that the proposed methods improve the visual quality of the reference image encryption methods. Overall, 2 k correction and kLSBs provide high visual quality and blindness.

Enhancing Blurred Low-Resolution Images via Exploring the Potentials of Learning-Based Super-Resolution

This paper aims to propose a candidate solution to the challenging task of single-image blind super-resolution (SR), via extensively exploring the potentials of learning-based SR schemes in the literature. The task is formulated into an energy functional to be minimized with respect to both an intermediate super-resolved image and a nonparametric blur-kernel. The functional includes a so-called convolutional consistency term which incorporates a nonblind learning-based SR result to better guide the kernel estimation process, and a bi-[Formula: see text]-[Formula: see text]-norm regularization imposed on both the super-resolved sharp image and the nonparametric blur-kernel. A numerical algorithm is deduced via coupling the splitting augmented Lagrangian (SAL) and the conjugate gradient (CG) method. With the estimated blur-kernel, the final SR image is reconstructed using a simple TV-based nonblind SR method. The proposed blind SR approach is demonstrated to achieve better performance than [T. Michaeli and M. Irani, Nonparametric Blind Super-resolution, in Proc. IEEE Conf. Comput. Vision (IEEE Press, Washington, 2013), pp. 945–952.] in terms of both blur-kernel estimation accuracy and image ehancement quality. In the meanwhile, the experimental results demonstrate surprisingly that the local linear regression-based SR method, anchored neighbor regression (ANR) serves the proposed functional more appropriately than those harnessing the deep convolutional neural networks.

Combined Treatment with Autologous CIK Cells, Radiotherapy and Chemotherapy in Advanced Cervical Cancer

To investigate the clinical efficacy of autologous cytokine induced killer (CIK) cells transfusion combined with radiochemotherapy in the treatment of advanced cervical cancer. A total of 89 hospitalized patients with advanced cervical cancer were admitted and divided into the treatment group (44 cases, autologous CIK cells transfusion combined with radiochemotherapy) and the control group (45 cases, radiochemotherapy) by a randomized non-blind method. Comparisons of therapeutic efficacies, immune functions, life qualities and survival rates were analyzed between the two groups. The short-term therapeutic efficacy of the treatment group was significantly higher than that of the control group. There was no significant difference in 1, 2 and 3year survival rates between the two groups. Compared with pre-treatment, levels of CD3+, CD4+/CD8+ in peripheral blood were increased in the CIK group, which were reduced in the control group. In the CIK group,only the feeling was depressed on the 25th day post-treatment (T25) compared with the day before treatment (B1). However in the control group, the function of body, role, social and holistic health was obvious disordered on day T25 compared with day B1. On day T25, there were significant differences in function of body, social and holistic health between two groups. Autologous CIK cells transfusion combined with radiochemotherapy shows better short-term efficacy than radiochemotherapy alone in the treatment of advanced cervical cancer, which obviously improves immune function and life quality of patients with low side effects.

Blind reverberation energy estimation using exponential averaging with attack and release time constants for hearing aids

Dereverberation signal processing is necessary for hearing-aid systems because reverberation degrades speech intelligibility in reverberant environments. In general, hearing-aid systems require low computational cost and real-time signal processing. The spectral subtraction (SS) method is a simple and frequently used technique which is used not only for noise-reduction but for dereverberation as well. To perform dereverberation methods based on SS for hearing aids, the reverberation energy must be estimated or measured. In this paper, the SS-based blind estimation of reverberation energy in a single-channel speech signal is proposed by using exponential averaging with attack and release time constants. The estimation error, which is the difference between the true and estimated reverberation energy, was used for evaluation. The estimation error of the proposed method was compared with the results of the method proposed by Lebart et al., which is a well-known non-blind SS-based dereverberation method. According to the results, the reverberation energy was more accurately estimated when the reverberation time was longer than 0.6 s, and the estimation error of the proposed method was approximately half of that of the well-known non-blind method by Lebart.

Blind deconvolution using maximum a posteriori (MAP) estimation with directional edge based priori

Image inverse problem or ill-posed problem has been tackled by various researchers in a number of ways. The number of unknown parameters as well as the properties of the parameters makes the problem very challenging. Majority of the research has been focused on using image properties and any prior knowledge of the bwr or degradation phenomenon. The whole process can be classified in to three categories: (i) blind methods; (ii) semi blind methods and (iii) non-blind methods. The proposed work in this paper is based on semi blind method where partial prior in the form of directional edges were used. The Bayesian class of methods using maximum a posteriori (MAP) estimates were proven very successful and used here. The main contribution of the proposed method involves (i) alternating minimization step for PSF (blur) and shape image; (ii) regularization based on adaptive directional gradients and (iii) non-local minima using edge features. The experimental result shows that the proposed algorithm is better than other enriching methods.

Deblurring of motion blurred images using histogram of oriented gradients and geometric moments

In image processing, various motion deblurring methods have been proposed that are based on camera shake and object motion. This paper proposes an effective method of estimating the point spread function (PSF) parameters based on the concepts of Histogram of oriented gradients (HoG) and statistical properties of an image, given the blurred image itself. In particular, HoG and statistical properties helps in estimating the angle and velocity parameters of the motion based PSF. Once these parameters are estimated, restoration of the blurred image is performed using recently introduced non-blind method in moment domain. The advantage of using moment domain are fast convergence and robust to the variations in the parameters of the PSF. The experiments on both the synthesized and real images show that our method can effectively restore the original images and get comparable results with existing algorithms. This is validated by using PSNR and a well known quality metrics BRISQUE and SSIM for evaluating the image quality.

Effect of trigonometric functions-based watermarking on blood vessel extraction: an application in ophthalmology imaging

With the growth of globalisation, security has been a major concern in digital exchange of medical information. Data hiding, also referred as watermarking, was introduced to authenticate medical data which is sent over the network. Watermarking of electronic patient reports (EPR) for telemedicine demands robust, imperceptible, high payload techniques. Blood vessel extraction is mainly used for diabetic retinopathy (DR) for automatic extraction and classification of severity of diseases. In our current work, blood vessel from fundus images is extracted using K-means segmentation. Afterwards, EPR is hidden using interpolation and trigonometric functions in fundus image. Finally, blood vessel is extracted from the watermarked image to measure the changes in accuracy of the proposed system. The percentage difference ( 36) and high correlation (> 87%) between original and watermarked retinal image, establishes the robustness of the proposed non-blind watermarking method.

An improved color image watermarking algorithm based on QR decomposition

Most of the existing color image watermarking schemes use binary or grayscale image as watermark, and many of them belong to non-blind watermarking methods. In this paper, an improved color image w...

CompoundL0regularization method for image blind motion deblurring

Blind image deblurring is one of the challenging problems in image processing and computer vision. The main purpose of blind image deblurring is to estimate the correct blur kernel and restore the latent image with edge-preservation, details-protection, and ringing suppression. In order to achieve ideal results, an innovative compound L0-regularized model is proposed to estimate the blur kernel by regularizing the sparsity property of natural images and two characteristics of blur kernel, such as continuity and sparsity. In the alternating direction framework, the split Bregman algorithm and half-quadratic splitting rule are alternatively employed to optimize the proposed kernel estimation model. Finally, a nonblind restoration method with ringing suppression is developed to obtain the ultimate latent image. Extensive experiments demonstrate the efficiency and viability of the proposed method compared with some state-of-the-art blind deblurring methods.