FIGURE 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Denoising plays an important role in the Magnetic Resonance Imaging (MRI) applications for medical diagnosis. MRI images usually contain undesired noises which would negatively affect the exactitude of pathological diagnosis. Recently, many models for MRI denoising have been developed from deep learning networks. In this paper, we propose a novel M...
Contexts in source publication
Context 1
... due to the limitation of hardware technology, MRI images are easily contaminated by noises, such as thermal noise. Figure 1 shows a typical contrast between noise-free and noisy MRI images. As seen in Figure 1, the noise usually manifests itself as random speckles on a smooth surface, which disturbs the visual inspection and may affect the accuracy of clinical diagnosis. ...
Context 2
... 1 shows a typical contrast between noise-free and noisy MRI images. As seen in Figure 1, the noise usually manifests itself as random speckles on a smooth surface, which disturbs the visual inspection and may affect the accuracy of clinical diagnosis. Hence, denoising is crucial for MRI images analysis. ...
Similar publications
Image denoising is an important research direction of image restoration. With the increasing requirements of image quality, image denoising has been widely concerned by scholars at home and abroad. This paper studies the problem of noise image denoising, using improved sparse representation algorithm and deep learning technology to denoise the nois...
Citations
... Jiwoo Mun et al. applied recurrent neural network (RNN) to the problem of automobile radar interference suppression, effectively solving the issue of mutual interference between multiple automobile radar signals [13]. In addition, the application of generative adversarial network (GAN) to image denoising has yielded remarkable results [14]. Inspired by this, we propose leveraging the power of GAN to solve the problem of radar active oppressive interference suppression in this paper. ...
Modern radar systems often face various interference signals in complex and rapidly changing electronic environments. The task of suppressing this interference in the radar echo signal to extract vital information is challenging. A radar interference suppression method is proposed based on a generative adversarial network (GAN). This method effectively recovers the target signal from the echo signal, which contains interference and noise, by leveraging the powerful fitting ability of GAN. Specifically, this method was tested using coherent suppression interference, smart noise interference, and noise frequency modulation suppression interference. We compared the proposed GAN method with recurrent neural network, short‐time Fourier transform time‐varying filtering, short‐time fractional Fourier transform time‐varying filtering algorithms and RNN approach. The results show that the interference suppression algorithm based on GAN is superior to the other three algorithms.
... Previous studies have addressed this issue by removing noise from the images or separating the noisy data. There are studies aimed at alleviating the interfering image problems by utilizing generative model-based methods and removing perturbations that occur within the image [34][35][36][37]. On the other hand, there are studies that have also been conducted to separate noisy data. ...
Background
Convolutional neural network-based image processing research is actively being conducted for pathology image analysis. As a convolutional neural network model requires a large amount of image data for training, active learning (AL) has been developed to produce efficient learning with a small amount of training data. However, existing studies have not specifically considered the characteristics of pathological data collected from the workplace. For various reasons, noisy patches can be selected instead of clean patches during AL, thereby reducing its efficiency. This study proposes an effective AL method for cancer pathology that works robustly on noisy datasets.
Methods
Our proposed method to develop a robust AL approach for noisy histopathology datasets consists of the following three steps: 1) training a loss prediction module, 2) collecting predicted loss values, and 3) sampling data for labeling. This proposed method calculates the amount of information in unlabeled data as predicted loss values and removes noisy data based on predicted loss values to reduce the rate at which noisy data are selected from the unlabeled dataset. We identified a suitable threshold for optimizing the efficiency of AL through sensitivity analysis.
Results
We compared the results obtained with the identified threshold with those of existing representative AL methods. In the final iteration, the proposed method achieved a performance of 91.7% on the noisy dataset and 92.4% on the clean dataset, resulting in a performance reduction of less than 1%. Concomitantly, the noise selection ratio averaged only 2.93% on each iteration.
Conclusions
The proposed AL method showed robust performance on datasets containing noisy data by avoiding data selection in predictive loss intervals where noisy data are likely to be distributed. The proposed method contributes to medical image analysis by screening data and producing a robust and effective classification model tailored for cancer pathology image processing in the workplace.
... In 2021, Tian and Song [13] have proposed a new method for Magnetic Resonance Image (MRI) denoising using Generative Adversarial Networks (GANs). The method uses a Convolutional Neural Network (CNN) as a discriminator to distinguish between real and fake image pairs. ...
Deep learning has gained significant interest in image denoising, but there are notable distinctions in the types of deep learning methods used. Discriminative learning is suitable for handling Gaussian noise, while optimization models are effective in estimating real noise. However, there is limited research that summarizes the different deep learning techniques for image denoising. This paper conducts a comprehensive review of techniques and methods used for image denoising and identifying challenges associated with existing approaches. In this paper, a comparative study of deep techniques is offered in image denoising. The study conducted a comprehensive review of 68 papers on image denoising published between 2018 and 2023, providing a detailed analysis of the field’s progress and methodologies over a period of 5 years. Through its literature review, the paper provides a comprehensive summary of image denoising in deep learning, including machine learning methods for image denoising, CNNs for image denoising, additive white noisy-image denoising, real noisy image denoising, blind denoising, hybrid noisy images, state- of-the-art methods for image denoising with deep learning, salt and pepper noise, non-linear filters for digital color images. The main objective of this paper is to provide a comprehensive overview of various approaches used for image denoising, each of which has been explored and developed based on individual research studies. The paper aims to discuss these approaches in a systematic and organized manner, comparing their strengths and weaknesses to provide insights for future research in the field.
... Similar to ResNet, GAN had also been applied to denoising [124,152], dehazing [53,88], deraining [76,85], deblurring [119,120], detargeting [68,126], light revising [22,81], image enhancement [15], image SR [105,141], and image restoration [17,132]. GAN has also been widely applied in different image denoising scenarios, including medical images such as CT [44,48], MRI [116], OCT [35,128], PET [23,89], X-ray [36], and ultrasound [49,58] as well as SAR images [95], seismic images [70,84], stellar images [131], microscopy images [50,160], underwater images [4,110], and some others [78,156]. The novel joint framework proposed by [36] integrated an enhanced super-resolution (SR) GAN with a noise reduction filter bank of wavelet transform CNN on both chest X-ray and chest tomography images to increase COVID-19 identification accuracy. ...
Recently, vision-based detection (VD) technology has been well-developed, and its general-purpose object detection algorithms have been applied in various scenes. VD can be divided into two categories based on the type of modality: single-modal (single RGB or single thermal) and bimodal. Image denoising is typically the first stage of image processing in VD, where redundant information and noisy data are removed to produce clearer images for effective object detection. This study reviews deep learning-based image denoising for RGB and thermal images, investigating the denoising procedure, methodologies, and performances of algorithms tested with benchmark datasets. After introducing denoising models, the main results on public RGB and thermal datasets are presented and analyzed, and conclusions of objective comparison in practical effect are drawn. This review can serve as a reference for researchers in RGB–infrared denoising, image restoration, and related fields.
... Through a series of experiments on synthetic, complex-valued and clinical MR brain images, the authors showed that the approach improved quantitative measures including PSNR and SSIM, as well as visual inspection of edge-like details and anatomical structures. Xu et al. aimed to simultaneously address long-range and hierarchical information and utilize similarity in 3D brain MR images for denoising [120]. They proposed a deep adaptive blending network (DABN) characterized by large receptive field residual dense blocks and an adaptive blending method. ...
Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.
... image generation and image super-resolution. In electromagnetics, several works show their use in the area of magnetic resonance imaging [6,7], antenna Q-factor characterization [8], scattering problems [9]. ...
In computational electromagnetism there are manyfold advantages when using machine learning methods, because no mathematical formulation is required to solve the direct problem for given input geometry. Moreover, thanks to the inherent bidirectionality of a convolutional neural network, it can be trained to identify the geometry giving rise to the prescribed output field. All this puts the ground for the neural meta-modeling of fields, in spite of different levels of cost and accuracy. In the paper it is shown how CNNs can be trained to solve problems of optimal shape synthesis, with training data sets based on finite-element analyses of electric and magnetic fields. In particular, a concept of multi-fidelity model makes it possible to control both prediction accuracy and computational cost. The shape design of a MEMS design and the TEAM workshop problem 35 are considered as the case studies.
Generative adversarial network, in short GAN, is a new convolution neural network (CNN) based framework with the great potential to determine high dimensional data from its feedback. It is a generative model built using two CNN blocks named generator and discriminator. GAN is a recent and trending innovation in CNN with evident progress in applications like computer vision, cyber security, medical and many more. This paper presents a complete overview of GAN with its structure, variants, application and current existing work. Our primary focus is to review the growth of GAN in the computer vision domain, specifically on image enhancement techniques. In this paper, the review is carried out in a funnel approach, starting with a broad view of GAN in all domains and then narrowing down to GAN in computer vision and, finally, GAN in image enhancement. Since GAN has cleverly acquired its position in various disciplines, we are showing a comparative analysis of GAN v/s ML v/s MATLAB computer vision methods concerning image enhancement techniques in existing work. The primary objective of the paper is to showcase the systematic literature survey and execute a comparative analysis of GAN with various existing research works in different domains and understand how GAN is a better approach compared to existing models using PRISMA guidelines. In this paper, we have also studied the current GAN model for image enhancement techniques and compared it with other methods concerning PSNR and SSIM.
Citation: Akindele, R.G.; Yu, M.; Kanda, P.S.; Owoola, E.O.; Aribilola, I. Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm. Sensors 2023, 23, 7780. https:// These authors contributed equally to this work. Abstract: The recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denoising Nifti (magnetic resonance imaging (MRI)). The PixSimWave algorithm uses regularized pixel similarity detection to improve the accuracy of noise reduction by creating patches to analyze the intensity of pixels and locate matching pixels, as well as adaptive neighborhood filtering to estimate noisy pixel values by allocating each pixel a weight based on its similarity. The wavelet transform breaks down the image into scales and orientations, allowing a sparse image representation to allocate a soft threshold on its similarity to the original pixels. The proposed method was evaluated on simulated and raw T1w MRIs, outperforming other methods in terms of an SSIM value of 0.9908 for a low Rician noise level of 3% and 0.9881 for a high noise level of 17%. The addition of Gaussian noise improved PSNR and SSIM, with the results indicating that the proposed method outperformed other models while preserving edges and textures. In summary, the PixSimWave algorithm is a viable noise-elimination approach that employs both sparse wavelet coefficients and regularized similarity with decreased computation time, improving the accuracy of noise reduction in images.
Background:
Deep learning (DL) is one of the latest approaches to artificial intelligence. As an unsupervised DL method, a generative adversarial network (GAN) can be used to synthesize new data.
Purpose:
To explore GAN applications in medicine and point out the significance of its existence for clinical medical research, as well as to provide a visual bibliometric analysis of GAN applications in the medical field in combination with the scientometric software Citespace and statistical analysis methods.
Material and methods:
PubMed, MEDLINE, Web of Science, and Google Scholar were searched to identify studies of GAN in medical applications between 2017 and 2022. This study was performed and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Citespace was used to analyze the number of publications, authors, institutions, and keywords of articles related to GAN in medical applications.
Results:
The applications of GAN in medicine are not limited to medical image processing, but will also penetrate wider and more complex fields, or may be applied to clinical medicine. Eligibility criteria were the full texts of peer-reviewed journals reporting the application of GANs in medicine. Research selections included material published in English between 1 January 2017 and 1 December 2022.
Conclusion:
GAN has been fully applied to the medical field and will be more deeply and widely used in clinical medicine, especially in the field of privacy protection and medical diagnosis. However, clinical applications of GAN require consideration of ethical and legal issues. GAN-based applications should be well validated by expert radiologists.
