Method For Image Denoising Research Articles

Enhanced Wavelet-Based Medical Image Denoising with Bayesian-Optimized Bilateral Filtering

Medical image denoising is essential for improving the clarity and accuracy of diagnostic images. In this paper, we present an enhanced wavelet-based method for medical image denoising, aiming to effectively remove noise while preserving critical image details. After applying wavelet denoising, a bilateral filter is utilized as a post-processing step to further enhance image quality by reducing noise while maintaining edge sharpness. The bilateral filter’s effectiveness heavily depends on its parameters, which must be carefully optimized. To achieve this, we employ Bayesian optimization, a powerful technique that efficiently identifies the optimal filter parameters, ensuring the best balance between noise reduction and detail preservation. The experimental results demonstrate a significant improvement in image denoising performance, validating the effectiveness of our approach.

Lightweight Infrared Image Denoising Method Based on Adversarial Transfer Learning.

A lightweight infrared image denoising method based on adversarial transfer learning is proposed. The method adopts a generative adversarial network (GAN) framework and optimizes the model through a phased transfer learning strategy. In the initial stage, the generator is pre-trained using a large-scale grayscale visible light image dataset. Subsequently, the generator is fine-tuned on an infrared image dataset using feature transfer techniques. This phased transfer strategy helps address the problem of insufficient sample quantity and variety in infrared images. Through the adversarial process of the GAN, the generator is continuously optimized to enhance its feature extraction capabilities in environments with limited data. Moreover, the generator structure incorporates structural reparameterization technology, edge convolution modules, and progressive multi-scale attention block (PMAB), significantly improving the model's ability to recognize edge and texture features. During the inference stage, structural reparameterization further optimizes the network architecture, significantly reducing model parameters and complexity and thereby improving denoising efficiency. The experimental results of public and real-world datasets demonstrate that this method effectively removes additive white Gaussian noise from infrared images, showing outstanding denoising performance.

Benchmarking deep learning-based low-dose CT image denoising algorithms.

Long-lasting efforts have been made to reduce radiation dose and thus the potential radiation risk to the patient for computed tomography (CT) acquisitions without severe deterioration of image quality. To this end, various techniques have been employed over the years including iterative reconstruction methods and noise reductionalgorithms. Recently, deep learning-based methods for noise reduction became increasingly popular and a multitude of papers claim ever improving performance both quantitatively and qualitatively. However, the lack of a standardized benchmark setup and inconsistencies in experimental design across studies hinder the verifiability and reproducibility of reportedresults. In this study, we propose a benchmark setup to overcome those flaws and improve reproducibility and verifiability of experimental results in the field. We perform a comprehensive and fair evaluation of several state-of-the-art methods using this standardizedsetup. Our evaluation reveals that most deep learning-based methods show statistically similar performance, and improvements over the past years have been marginal atbest. This study highlights the need for a more rigorous and fair evaluation of novel deep learning-based methods for low-dose CT image denoising. Our benchmark setup is a first and important step towards this direction and can be used by future researchers to evaluate theiralgorithms.

Self-supervised learning for CT image denoising and reconstruction: a review.

This article reviews the self-supervised learning methods for CT image denoising and reconstruction. Currently, deep learning has become a dominant tool in medical imaging as well as computer vision. In particular, self-supervised learning approaches have attracted great attention as a technique for learning CT images without clean/noisy references. After briefly reviewing the fundamentals of CT image denoising and reconstruction, we examine the progress of deep learning in CT image denoising and reconstruction. Finally, we focus on the theoretical and methodological evolution of self-supervised learning for image denoising and reconstruction.

Noise-imitation learning: unpaired speckle noise reduction for optical coherence tomography

Objective.Optical coherence tomography (OCT) is widely used in clinical practice for its non-invasive, high-resolution imaging capabilities. However, speckle noise inherent to its low coherence principle can degrade image quality and compromise diagnostic accuracy. While deep learning methods have shown promise in reducing speckle noise, obtaining well-registered image pairs remains challenging, leading to the development of unpaired methods. Despite their potential, existing unpaired methods suffer from redundancy in network structures or interaction mechanisms. Therefore, a more streamlined method for unpaired OCT denoising is essential.Approach.In this work, we propose a novel unpaired method for OCT image denoising, referred to as noise-imitation learning (NIL). NIL comprises three primary modules: the noise extraction module, which extracts noise features by denoising noisy images; the noise imitation module, which synthesizes noisy images and generates fake clean images; and the adversarial learning module, which differentiates between real and fake clean images through adversarial training. The complexity of NIL is significantly lower than that of previous unpaired methods, utilizing only one generator and one discriminator for training.Main results.By efficiently fusing unpaired images and employing adversarial training, NIL can extract more speckle noise information to enhance denoising performance. Building on NIL, we propose an OCT image denoising pipeline, NIL-NAFNet. This pipeline achieved PSNR, SSIM, and RMSE values of 31.27 dB, 0.865, and 7.00, respectively, on the PKU37 dataset. Extensive experiments suggest that our method outperforms state-of-the-art unpaired methods both qualitatively and quantitatively.Significance.These findings indicate that the proposed NIL is a simple yet effective method for unpaired OCT speckle noise reduction. The OCT denoising pipeline based on NIL demonstrates exceptional performance and efficiency. By addressing speckle noise without requiring well-registered image pairs, this method can enhance image quality and diagnostic accuracy in clinical practice.

Transformer for low concentration image denoising in magnetic particle imaging.

Objective.Magnetic particle imaging (MPI) is an emerging tracer-basedin vivoimaging technology. The use of MPI at low superparamagnetic iron oxide nanoparticle concentrations has the potential to be a promising area of clinical application due to the inherent safety for humans. However, low tracer concentrations reduce the signal-to-noise ratio of the magnetization signal, leading to severe noise artifacts in the reconstructed MPI images. Hardware improvements have high complexity, while traditional methods lack robustness to different noise levels, making it difficult to improve the quality of low concentration MPI images.Approach.Here, we propose a novel deep learning method for MPI image denoising and quality enhancing based on a sparse lightweight transformer model. The proposed residual-local transformer structure reduces model complexity to avoid overfitting, in which an information retention block facilitates feature extraction capabilities for the image details. Besides, we design a noisy concentration dataset to train our model. Then, we evaluate our method with both simulated and real MPI image data.Main results.Simulation experiment results show that our method can achieve the best performance compared with the existing deep learning methods for MPI image denoising. More importantly, our method is effectively performed on the real MPI image of samples with an Fe concentration down to 67μgFeml-1.Significance.Our method provides great potential for obtaining high quality MPI images at low concentrations.

Multi-Branch Network for Color Image Denoising Using Dilated Convolution and Attention Mechanisms.

Image denoising is regarded as an ill-posed problem in computer vision tasks that removes additive noise from imaging sensors. Recently, several convolution neural network-based image-denoising methods have achieved remarkable advances. However, it is difficult for a simple denoising network to recover aesthetically pleasing images owing to the complexity of image content. Therefore, this study proposes a multi-branch network to improve the performance of the denoising method. First, the proposed network is designed based on a conventional autoencoder to learn multi-level contextual features from input images. Subsequently, we integrate two modules into the network, including the Pyramid Context Module (PCM) and the Residual Bottleneck Attention Module (RBAM), to extract salient information for the training process. More specifically, PCM is applied at the beginning of the network to enlarge the receptive field and successfully address the loss of global information using dilated convolution. Meanwhile, RBAM is inserted into the middle of the encoder and decoder to eliminate degraded features and reduce undesired artifacts. Finally, extensive experimental results prove the superiority of the proposed method over state-of-the-art deep-learning methods in terms of objective and subjective performances.

A Dynamic Network with Transformer for Image Denoising

Deep convolutional neural networks (CNNs) can achieve good performance in image denoising due to their superiority in the extraction of structural information. However, they may ignore the relationships between pixels to limit effects for image denoising. Transformer, focusing on pixel to pixel relationships can effectively solve this problem. This article aims to make a CNN and Transformer complement each other in image denoising. In this study, we propose a dynamic network with Transformer for image denoising (DTNet), with a residual block (RB), a multi-head self-attention block (MSAB), and a multidimensional dynamic enhancement block (MDEB). Firstly, the RB not only utilizes a CNN but also lays the foundation for the combination with Transformer. Then, the MSAB adds positional encoding and applies multi-head self-attention, which enables the preservation of sequential positional information while employing the Transformer to obtain global information. Finally, the MDEB uses dimension enhancement and dynamic convolution to improve the adaptive ability. The experiments show that our DTNet is superior to some existing methods for image denoising.

Comparative Analysis of Deep Learning-Based and Traditional Methods for Image Denoising and Restoration

Abstract: This paper presents a comprehensive comparative analysis of deep learning-based methods and traditional techniques for image denoising and restoration. The objective is to evaluate the performance, computational efficiency, and generalizability of these methods across various types and levels of noise in images. This report presents a comprehensive comparative analysis of image denoising and restoration techniques, focusing on traditional methods and deep learning-based approaches. The study evaluates the performance, computational efficiency, and generalizability of these methods across various types and levels of noise in images.

Hybrid variable exponent model for image denoising: A nonstandard high-order PDE approach with local and nonlocal coupling

In this paper, we propose a novel hybrid model combining local and nonlocal methods for effective image denoising. The model utilizes variable exponents p(x) to achieve adaptive diffusion behavior and preserve image features. Nevertheless, the coupling structure of our proposed process, along with the spatial dependence of p(x), poses challenges in theoretical analysis. To address this, we investigate the existence and uniqueness of the solution using the Faedo-Galerkin approximation, a priori estimates, and compactness considerations. Through these theoretical investigations, we demonstrate the existence of a weak solution for the coupled parabolic system. Overall, our model outperforms existing methods in noise reduction and image quality preservation.

Fuzzy based self-similarity weight estimation in non-local means for gray-scale image de-noising

Image de-noising in imaging systems is one of the most demanding issues that have been addressed in this work. Non-local mean filtering is gaining traction as a convincing method for image de-noising. Nevertheless, the performance of the traditional non-local mean filter is diminished by the computational expense of its weighted averaging process. In the proposed method, the similarity between the two patches of the image subspace is used to find the best weight for each pixel using a fuzzy inference algorithm. By using the similarity of non-local neighborhood pixels as an input antecedent in the input fuzzy set and the degree of weights as a consequent in the output fuzzy set, the fuzzy inference system which consists of IF-THEN rules, implication, and aggregation is employed. Eventually, de-fuzzification helps to measure how similar the pixels are to their non-local neighborhoods and estimates the fuzzy degrees of weight. Experiments on a variety of speckled noisy gray-scale images from standard and real public datasets demonstrate the improved performance of this fuzzy-based self-similar weight approximation in non-local mean filtering when compared to state-of-the-art image de-noising methods and sophisticated non-local mean methods in terms of standard evaluation metrics. Additionally, the suggested technique works satisfactorily when tested on actual speckled synthetic aperture radar images.

Retracted: Ancient Stone Inscription Image Denoising and Inpainting Methods Based on Deep Neural Networks

Retracted: Ancient Stone Inscription Image Denoising and Inpainting Methods Based on Deep Neural Networks

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Manifold-based denoising for Ferumoxytol-enhanced 3D cardiac cine MRI.

The two-dimensional (2D) cine cardiovascular magnetic resonance (CMR) technique is the reference standard for assessing cardiac function. However, one challenge with 2D cine is that the acquisition time for the whole cine stack is long and requires multiple breath holds, which may not be feasible for pediatric or ill patients. Though single breath-hold multi-slice cine may address the issue, it can only acquire low-resolution images, and hence, affect the accuracy of cardiac function assessment. To address these challenges, a Ferumoxytol-enhanced, free breathing, isotropic high-resolution 3D cine technique was developed. The method produces high-contrast cine images with short acquisition times by using compressed sensing together with a manifold-based method for image denoising. This study included fifteen patients (9.1 $ \pm $ 5.6 yrs.) who were referred for clinical cardiovascular magnetic resonance imaging (MRI) with Ferumoxytol contrast and were prescribed the 3D cine sequence. The data was acquired on a 1.5T scanner. Statistical analysis shows that the manifold-based denoised 3D cine can accurately measure ventricular function with no significant differences when compared to the conventional 2D breath-hold (BH) cine. The multiplanar reconstructed images of the proposed 3D cine method are visually comparable to the golden standard 2D BH cine method in terms of clarity, contrast, and anatomical precision. The proposed method eliminated the need for breath holds, reduced scan times, enabled multiplanar reconstruction within an isotropic data set, and has the potential to be used as an effective tool to access cardiovascular conditions.

CMID: Crossmodal Image Denoising via Pixel-Wise Deep Reinforcement Learning.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

PET image denoising based on denoising diffusion probabilistic model.

Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising. Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [[Formula: see text]F]FDG datasets and 140 brain [[Formula: see text]F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods. Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance. DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.

Deep learning for fast denoising filtering in ultrasound localization microscopy

Objective. Addition of a denoising filter step in ultrasound localization microscopy (ULM) has been shown to effectively reduce the error localizations of microbubbles (MBs) and achieve resolution improvement for super-resolution ultrasound (SR-US) imaging. However, previous image-denoising methods (e.g. block-matching 3D, BM3D) requires long data processing times, making ULM only able to be processed offline. This work introduces a new way to reduce data processing time through deep learning. Approach. In this study, we propose deep learning (DL) denoising based on contrastive semi-supervised network (CS-Net). The neural network is mainly trained with simulated MBs data to extract MB signals from noise. And the performances of CS-Net denoising are evaluated in both in vitro flow phantom experiment and in vivo experiment of New Zealand rabbit tumor. Main results. For in vitro flow phantom experiment, the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of single microbubble image are 26.91 dB and 4.01 dB, repectively. For in vivo animal experiment , the SNR and CNR were 12.29 dB and 6.06 dB. In addition, single microvessel of 24 μm and two microvessels separated by 46 μm could be clearly displayed. Most importantly,, the CS-Net denoising speeds for in vitro and in vivo experiments were 0.041 s frame−1 and 0.062 s frame−1, respectively. Significance. DL denoising based on CS-Net can improve the resolution of SR-US as well as reducing denoising time, thereby making further contributions to the clinical real-time imaging of ULM.

Time Image De-Noising Method Based on Sparse Regularization

The blurring of texture edges often occurs during image data transmission and acquisition. To ensure the detailed clarity of the drag-time images, we propose a time image de-noising method based on sparse regularization. First, the image pixel sparsity index is set, and then an image de-noising model is established based on sparse regularization processing to obtain the neighborhood weights of similar image blocks. Second, a time image de-noising algorithm is designed to determine whether the coding coefficient reaches the standard value, and a new image de-noising method is obtained. Finally, the images of electronic clocks and mechanical clocks are used as two kinds of time images to compare different image de-noising methods, respectively. The results show that the sparsity regularization method has the highest peak signal-to-noise ratio among the six compared methods for different noise standard deviations and two time images. The image structure similarity is always above which shows that the proposed method is better than the other five image de-noising methods.

Denoising Method Based on Salient Region Recognition for the Spatiotemporal Event Stream.

Event cameras are the emerging bio-mimetic sensors with microsecond-level responsiveness in recent years, also known as dynamic vision sensors. Due to the inherent sensitivity of event camera hardware to light sources and interference from various external factors, various types of noises are inevitably present in the camera's output results. This noise can degrade the camera's perception of events and the performance of algorithms for processing event streams. Moreover, since the output of event cameras is in the form of address-event representation, efficient denoising methods for traditional frame images are no longer applicable in this case. Most existing denoising methods for event cameras target background activity noise and sometimes remove real events as noise. Furthermore, these methods are ineffective in handling noise generated by high-frequency flickering light sources and changes in diffused light reflection. To address these issues, we propose an event stream denoising method based on salient region recognition in this paper. This method can effectively remove conventional background activity noise as well as irregular noise caused by diffuse reflection and flickering light source changes without significantly losing real events. Additionally, we introduce an evaluation metric that can be used to assess the noise removal efficacy and the preservation of real events for various denoising methods.

Gradient extraction based multiscale dense cross network for LDCT denoising

Low-dose computed tomography (LDCT) reduces the damage caused by ionizing radiation by reducing the X-ray dose. However, CT images reconstructed from low-dose X-rays contain a great deal of noise and artifacts that affect a physician’s diagnosis. We propose a gradient extraction based multiscale dense cross network (GE-MDCNet) for LDCT image denoising. This method adds the gradient images (high-frequency information) obtained from the LDCT image through the gradient extraction network and the shallow feature images (low-frequency information) extracted through the shallow feature extraction block to obtain rich feature maps. The feature images are fed into BackboneNet to obtain better-quality prediction images. In addition, we propose a compound loss function based on the Charbonnier loss and gradient loss to enhance the texture details and improve the visual quality of the images. Extensive experiments on the Mayo and Piglet datasets show that GE-MDCNet can effectively remove noise and artifacts from LDCT images while preserving the image structure and edge information. Compared with existing LDCT image post-processing methods, GE-MDCNet significantly improved all metrics. The algorithm offers a novel concept and method for LDCT imaging and other medical image denoising, which can effectively optimize the imaging quality. Moreover, it improves the accuracy and precision of image diagnosis, which has a profound impact on medical imaging.