Denoising Of Magnetic Resonance Images Research Articles

Magnetic Resonance Image Denoising Algorithm Based on Cartoon, Texture, and Residual Parts.

Magnetic resonance (MR) images are often contaminated by Gaussian noise, an electronic noise caused by the random thermal motion of electronic components, which reduces the quality and reliability of the images. This paper puts forward a hybrid denoising algorithm for MR images based on two sparsely represented morphological components and one residual part. To begin with, decompose a noisy MR image into the cartoon, texture, and residual parts by MCA, and then each part is denoised by using Wiener filter, wavelet hard threshold, and wavelet soft threshold, respectively. Finally, stack up all the denoised subimages to obtain the denoised MR image. The experimental results show that the proposed method has significantly better performance in terms of mean square error and peak signal-to-noise ratio than each method alone.

Non-Local SVD Denoising of MRI Based on Sparse Representations.

Magnetic Resonance (MR) Imaging is a diagnostic technique that produces noisy images, which must be filtered before processing to prevent diagnostic errors. However, filtering the noise while keeping fine details is a difficult task. This paper presents a method, based on sparse representations and singular value decomposition (SVD), for non-locally denoising MR images. The proposed method prevents blurring, artifacts, and residual noise. Our method is composed of three stages. The first stage divides the image into sub-volumes, to obtain its sparse representation, by using the KSVD algorithm. Then, the global influence of the dictionary atoms is computed to upgrade the dictionary and obtain a better reconstruction of the sub-volumes. In the second stage, based on the sparse representation, the noise-free sub-volume is estimated using a non-local approach and SVD. The noise-free voxel is reconstructed by aggregating the overlapped voxels according to the rarity of the sub-volumes it belongs, which is computed from the global influence of the atoms. The third stage repeats the process using a different sub-volume size for producing a new filtered image, which is averaged with the previously filtered images. The results provided show that our method outperforms several state-of-the-art methods in both simulated and real data.

MRI denoising using BM3D equipped with noise invalidation denoising technique and VST for improved contrast

Denoising of medical scanned images such as X-ray, MRI etc. is important stage in the medical use. To remove the noise from “magnetic resonance images” (MRI) is the attention of researchers to generate the MR images with high “signal-to-noise ratio” as well as with high spatial resolution. In this denoising technique, block-matching and 3-dimensional filtering (BM3D) method is used to denoise the MR images. Main steps used in BM3D are grouping, 3-dimensional discrete wavelet transformation and wavelet shrinkage. In the proposed method, noise invalidation denoising technique (NIDe) is used rather than hard thresholding. NIDe gives the threshold value automatically based on the data and noise characteristics and threshold value changes according to the characteristics of data i.e. wavelet coefficient of image. Before denoising MR images, variance stabilization transform (VST) discard the noise variance dependency of the MRI intensities. Combining block-matching and 3-dimensional filtering technique and VST make able the use of the BM3D technique for Magnetic Resonance Image denoising. After BM3D i.e. final denoised MR image, “contrast limited adaptive histogram equalization” technique is applied to increase the contrast of MR images which are denoised. Performance metrics such as “Peak Signal to Noise ratio”, “Root Mean Square Error”, “Mutual Information”, “Edge Entropy” and “Structural Similarity Index Method” are found out for “T1 weighted”, “T2 weighted” and “PD weighted” magnetic resonance images.

Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel

Upsampling and denoising of magnetic resonance images are conventionally performed separately, which would introduce unwanted artifacts such as blurring. To address this problem, we propose an innovative adaptive interpolation framework to achieve simultaneous image upsampling, denoising, and detail enhancement. First, local steering kernel (LSK) function is leveraged to adapt the interpolation weights according to geometric structures in the magnetic resonance (MR) images. An adaptive sharpening of the LSK weight matrix and a Rician bias correction are then adopted to remove Rician noise and enhance fine details. In this regard, the adaptive LSK extends the zero-order point estimation framework to higher orders of regression, and therefore facilitates edge preservation and detail reconstruction. The post-processing Rician correction avoids the bias caused by the asymmetry of Rician noise distributions. Experimental results using both real and synthetic clinical MR cranial images (with and without noise) demonstrated that our algorithm produced better reconstruction results than several traditional interpolation-based upsampling methods, including nearest neighbor (NN), non-local means (NLM), self-learning super resolution (SLSR), Gaussian process regression (GPR), and even comparable to four deep-learning-based methods but with less data requirements and computational complexity. The proposed technique resulted in PSNR and SSIM values were ~3%-16% higher than any of the other traditional algorithms tested, and our method recovered more clear textures from noisy images compared with deep-learning-based methods. As such, the presented technique is a viable new approach to MR upsampling, particularly for noisy images.

A magnetic resonance imaging denoising technique using non-local means and unsupervised learning

We propose a new non-local mean (NLM) algorithm using unsupervised learning and k-means clustering for denoising magnetic resonance (MR) images. Our technique improves image processing speeds with enhanced denoising performance on multiple types of images. The calculation of similarity weights at the cluster level improves computational efficiency. We conducted experiments with brain MR images of various sizes, including three T1- and T2-weighted images. Three quality metrics show that our algorithm achieves moderate improvements in denoising accuracy with significant reductions in execution time. The proposed method processed the sample data in one-fifth of the time of the original NLM method. Compared to several state-of-the-art methods, our method offers improved peak signal-to-noise ratios (PSNRs) for samples with large amounts of noise.

A magnetic resonance imaging denoising technique using non-local means and unsupervised learning

A magnetic resonance imaging denoising technique using non-local means and unsupervised learning

Noise Removal of MRI Images with Different Similarities using Advance NLM Filtering

In modern world, medical imaging has versatile application worldwide. It is very popular in the field of research and innovation. Medical image processing include the study of internal body structure like organs, tissues, etc., which provides much clear information of inner body structure using the digitalized data of human organs and help doctors to detect disease. Magnetic Resonance Imaging (MRI) is most effective and safe method for internal structure diagnosis. MRI images are generally magnitude images and they are follows by Rician distribution. In last few decades, many denoising techniques have been proposed like wavelet based techniques, Maximum likelihood (ML), bilateral filtering etc. But all those algorithms have some shortcomings and limitations. The purpose of our study is to propose a simple but effective advance Non-Local Means filtering approach for MRI denoising. Different distance matrix calculations have been introduced like Euclidean distance, Minkowski distance, Manhattan distance etc. These all are tested and identified best similarity measurement which preserves the image edges information and other information more effectively. The analysis is done on both the quality and quantity basis such as Peak Signal to Noise Ratio (PSNR) which shows the efficiency of noise removal technique and Mean Square Error (MSE) which represents the average of difference between pixels value of original image and denoised images.

Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising.

Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

Denoising of MR images with Rician noise using a wider neural network and noise range division

Magnetic resonance (MR) images denoising is important in medical image analysis. Denoising methods based on deep learning have shown great promise and outperform all of the other conventional methods. However, deep-learning methods are limited by the number of training samples. In this article, using a small sample size, we applied a wider denoising neural network to MR images with Rician noise and trained several denoising models. The first model is specific to a certain noise, while the other applies to a wide range of noise levels. We considered the noise range as one interval, two sub-intervals, three sub-intervals, or even more sub-intervals to train the corresponding models. Experimental results demonstrate that for MR images, the proposed deep-learning models are efficient in terms of peak-signal-to-noise ratio, structure-similarity-index metrics and normalized mutual information. In addition, for blind noise, the effect of the three sub-intervals is better than that of the other sub-intervals.

Multiple-Coil Magnetic Resonance Image Denoising and Deblurring With Nonlocal Total Bounded Variation

One of the complex tasks in image restoration is to restore images under data correlated noise contaminations. In real-time medical imaging scenarios, such as Magnetic Resonance (MR), Ultrasound, Computed Tomography(CT) etc, it is observed that, the data of interest is severely degraded with data dependent noise interventions. A Nonlocal Total Bounded Variation (NLTBV) approach is being proposed in this paper to denoise as well as deblur multiple-coil MR images corrupted by non-central Chi distributed noise and linear Gaussian blur. The energy functional for the restoration model is derived by applying the Maximum A Posteriori (MAP) estimator on the Probability Density Function (PDF) of the non-central Chi distribution. The numerical implementation is performed using the split-Bregman iterative scheme to improve the convergence rate. The proposed model is compared with the other state of the art models in terms of both visual and statistical quantifications to demonstrate it's performance.

Denoising of 3D magnetic resonance images using a residual encoder-decoder Wasserstein generative adversarial network.

Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis. Over the past few years, many algorithms with impressive performances have been proposed. In this paper, inspired by the idea of deep learning, we introduce an MRI denoising method based on the residual encoder-decoder Wasserstein generative adversarial network (RED-WGAN). Specifically, to explore the structure similarity between neighboring slices, a 3D configuration is utilized as the basic processing unit. Residual autoencoders combined with deconvolution operations are introduced into the generator network. Furthermore, to alleviate the oversmoothing shortcoming of the traditional mean squared error (MSE) loss function, the perceptual similarity, which is implemented by calculating the distances in the feature space extracted by a pretrained VGG-19 network, is incorporated with the MSE and adversarial losses to form the new loss function. Extensive experiments are implemented to assess the performance of the proposed method. The experimental results show that the proposed RED-WGAN achieves performance superior to several state-of-the-art methods in both simulated and real clinical data. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation.

Local Complexity Estimation Based Filtering Method in Wavelet Domain for Magnetic Resonance Imaging Denoising.

In this paper, we propose the local complexity estimation based filtering method in wavelet domain for MRI (magnetic resonance imaging) denoising. A threshold selection methodology is proposed in which the edge and detail preservation properties for each pixel are determined by the local complexity of the input image. In the proposed filtering method, the current wavelet kernel is compared with a threshold to identify the signal- or noise-dominant pixels in a scale providing a good visual quality avoiding blurred and over smoothened processed images. We present a comparative performance analysis with different wavelets to find the optimal wavelet for MRI denoising. Numerical experiments and visual results in simulated MR images degraded with Rician noise demonstrate that the proposed algorithm consistently outperforms other denoising methods by balancing the tradeoff between noise suppression and fine detail preservation. The proposed algorithm can enhance the contrast between regions allowing the delineation of the regions of interest between different textures or tissues in the processed images. The proposed approach produces a satisfactory result in the case of real MRI denoising by balancing the detail preservation and noise removal, by enhancing the contrast between the regions of the image. Additionally, the proposed algorithm is compared with other approaches in the case of Additive White Gaussian Noise (AWGN) using standard images to demonstrate that the proposed approach does not need to be adapted specifically to Rician or AWGN noise; it is an advantage of the proposed approach in comparison with other methods. Finally, the proposed scheme is simple, efficient and feasible for MRI denoising.

Scalable algorithms for locally low-rank matrix modeling

We consider the problem of modeling data matrices with locally low-rank (LLR) structure, a generalization of the popular low-rank structure widely used in a variety of real-world application domains ranging from medical imaging to recommendation systems. While LLR modeling has been found to be promising in real-world application domains, limited progress has been made on the design of scalable algorithms for such structures. In this paper, we consider a convex relaxation of LLR structure and propose an efficient algorithm based on dual projected gradient descent (D-PGD) for computing the proximal operator. While the original problem is non-smooth, so that primal (sub)gradient algorithms will be slow, we show that the proposed D-PGD algorithm has geometrical convergence rate. We present several practical ways to further speed up the computations, including acceleration and approximate SVD computations. With experiments on both synthetic and real data from MRI (magnetic resonance imaging) denoising, we illustrate the superior performance of the proposed D-PGD algorithm compared to several baselines.

MRI denoising by NeighShrink based on chi-square unbiased risk estimation.

NeighShrink is an efficient image denoising algorithm for the reduction of additive white Gaussian noise. However, it does not perform well in terms of Rician noise removal for MRI (Magnetic Resonance Imaging). Allowing for the characteristics of squared-magnitude MR (Magnetic Resonance) images, which follow a non-central chi-square distribution, the CURE (Chi-Square Unbiased Risk Estimation) is used to determine an optimal threshold for NeighShrink. Therefore, we propose the NeighShrinkCURE denoising algorithm. Bilateral filtering and cycle spinning are used to further improve denoising performance. Experimental results show that the proposed algorithm is simple and efficient, and provides good noise reduction while preserving edges and details well. Compared with some similar MRI denoising algorithms, the proposed algorithm has improvements in PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity). Although running time of the proposed algorithm has some increment compared with some current MRI denoising algorithms, the comprehensive performance of the proposed algorithm is superior to several current MRI denoising algorithms.

Analysis and implementation of MRI denoising methods using statistical filtering approach

Magnetic Resonance (MR) images are mostly corrupted with white Gaussian noise called as Rician noise. Due to its dependency on signal this noise is multiplicative in nature. Because of this noise contrast quality of MR images degrades significantly. That leads to lot of difficulties have to analysts in order to extract the useful information from images for proper diagnosis of disease. Various authors have proposed different statistical techniques for MR image denoising. Our main goal is to preserve such useful details like texture information, thin edges, and structural content of useful information when denoising. Methods are applied to the Rician noise corrupted images. In this work, we analyze the various statistical techniques like Average, Median and Gaussian filters. These techniques have ability to preserve the edges of fine structures and also to perform efficient denoising.

A local Zernike moment-based unbiased nonlocal means fuzzy C-Means algorithm for segmentation of brain magnetic resonance images

Clustering based unsupervised segmentation approaches have become important tools to model data and infer knowledge. Such approaches are often used in various biomedical applications to assist experts in analyzing the data. Segmentation of brain magnetic resonance (MR) images has become a very challenging task due to the presence of Rician noise and intensity inhomogeneity. The existing methods dealing with such issues work in the spatial domain. These methods are prone to losing image details while reducing the effect of noise. The proposed method works in the moment domain, and for this purpose, we have selected Zernike moments (ZMs). The ZMs are orthogonal, rotation invariant and robust to image noise. The proposed method is based on our previous work on Zernike moments-based unbiased nonlocal means (ZM-UNLM) approach for denoising MR images affected by the Rician noise. The ZM-UNLM-based approach uses both the local and nonlocal information while eliminating Rician noise from brain MR images which have fine image details along with the noise components. Keeping in view the superior performance of the ZM-UNLM, we extend it to segment brain MR images and propose a method called local ZMs (LZM)-based unbiased nonlocal means fuzzy C-means (LZM-UNLM-FCM) approach which provides much-improved segmentation accuracy as compared to the existing spatial domain-based state-of-the-art techniques. It is shown how the LZMs based technique reduces the effect of the Rician noise while retaining the fine structures, edges, and other image details in the moment domain. The complete framework consists of an intelligent knowledge-driven approach that segments tissues from brain MR images using both the local and nonlocal information in the moment domain. The proposed approach has significance in developing future expert and intelligent systems that do not require any human intervention to manually annotate data and saves time for diagnostic related tasks. Detailed experimental results are provided to demonstrate the superior performance of the proposed method over the existing state-of-the-art methods.

A New 4-D Nonlocal Transform-Domain Filter for 3-D Magnetic Resonance Images Denoising.

The simultaneous removal of noise and preservation of the integrity of 3-D magnetic resonance (MR) images is a difficult and important task. In this paper, we consider characterizing MR images with 3-D operators, and present a novel 4-D transform-domain method termed 'modified nonlocal tensor-SVD (MNL-tSVD)' for MR image denoising. The proposed method is based on the grouping, hard-thresholding and aggregation paradigms, and can be viewed as a generalized nonlocal extension of tensor-SVD (t-SVD). By keeping MR images in its natural three-dimensional form, and collaboratively filtering similar patches, MNL-tSVD utilizes both the self-similarity property and 3-D structure of MR images to preserve more actual details and minimize the introduction of new artifacts. We show the adaptability of MNL-tSVD by incorporating it into a two-stage denoising strategy with a few adjustments. In addition, analysis of the relationship between MNL-tSVD and current the state-of-the-art 4-D transforms is given. Experimental comparisons over simulated and real brain data sets at different Rician noise levels show that MNL-tSVD can produce competitive performance compared with related approaches.

GPU implementation of non-local maximum likelihood estimation method for denoising magnetic resonance images

Magnetic resonance imaging (MRI) is a widely deployed medical imaging technique used for various applications such as neuroimaging, cardiovascular imaging and musculoskeletal imaging. However, MR images degrade in quality due to noise. The magnitude MRI data in the presence of noise generally follows a Rician distribution if acquired with single-coil systems. Several methods are proposed in the literature for denoising MR images corrupted with Rician noise. Amongst the methods proposed in literature for denoising MR images corrupted with Rician noise, the non-local maximum likelihood methods (NLML) and its variants are popular. In spite of the performance and denoising quality, NLML algorithm suffers from a tremendous time complexity $$O\left( {m^{3} N^{3} } \right)$$Om3N3, where $$m^{3}$$m3 and $$N^{3}$$N3 represent the search window and image size, respectively, for a 3D image. This makes the algorithm challenging for deployment in the real-time applications where fast and prompt results are required. A viable solution to this shortcoming would be the application of a data parallel processing framework such as Nvidia CUDA so as to utilize the mutually exclusive and computationally intensive calculations to our advantage. The GPU-based implementation of NLML-based image denoising achieves significant speedup compared to the serial implementation. This research paper describes the first successful attempt to implement a GPU-accelerated version of the NLML algorithm. The main focus of the research was on the parallelization and acceleration of one computationally intensive section of the algorithm so as to demonstrate the execution time improvement through the application of parallel processing concepts on a GPU. Our results suggest the possibility of practical deployment of NLML and its variants for MRI denoising.

An Adaptive Hierarchical Method Based on Wavelet and Adaptive Filtering for Magnetic Resonance Imaging Denoising

An Adaptive Hierarchical Method Based on Wavelet and Adaptive Filtering for Magnetic Resonance Imaging Denoising

Magnetic resonance image denoising using nonlocal maximum likelihood paradigm in DCT-framework

The data acquired by magnetic resonance (MR) imaging system are inherently degraded by noise that has its origin in the thermal Brownian motion of electrons. Denoising can enhance the quality (by improving the SNR) of the acquired MR image, which is important for both visual analysis and other post processing operations. Recent works on maximum likelihood (ML) based denoising shows that ML methods are very effective in denoising MR images and has an edge over the other state-of-the-art methods for MRI denoising. Among the ML based approaches, the Nonlocal maximum likelihood (NLML) method is commonly used. In the conventional NLML method, the samples for the ML estimation of the unknown true pixel are chosen in a nonlocal fashion based on the intensity similarity of the pixel neighborhoods. Euclidean distance is generally used to measure this similarity. It has been recently shown that computing similarity measure is more robust in discrete cosine transform (DCT) subspace, compared with Euclidean image subspace. Motivated by this observation, we integrated DCT into NLML to produce an improved MRI filtration process. Other than improving the SNR, the time complexity of the conventional NLML can also be significantly reduced through the proposed approach. On synthetic MR brain image, an average improvement of 5% in PSNR and 86%reduction in execution time is achieved with a search window size of 91 × 91 after incorporating the improvements in the existing NLML method. On an experimental kiwi fruit image an improvement of 10% in PSNR is achieved. We did experiments on both simulated and real data sets to validate and to demonstrate the effectiveness of the proposed method. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 256–264, 2015