MRI denoising using progressively distribution-based neural network

Magnetic Resonance (MR) images often suffer from noise pollution during image acquisition and transmission, which limits the accuracy of quantitative measurements from the data. Noise in magnitude MR images is usually governed by Rician distribution, due to the existence of uncorrelated Gaussian noise with zero-mean and equal variance in both the real and imaginary parts of the complex K-space data. Different from the existing MRI denoising methods that utilizing the spatial neighbor information around the pixels or patches, this work turns to capture the pixel-level distribution information by means of supervised network learning. A progressive network learning strategy is proposed via fitting the distribution of pixel-level and feature-level intensities. The proposed network consists of two residual blocks, one is used for fitting pixel domain without batch normalization layer and another one is applied for matching feature domain with batch normalization layer. Experimental results under synthetic, complex-valued and clinical MR brain images demonstrate great potential of the proposed network with substantially improved quantitative measures and visual inspections.     

基于K-SVD和残差比的低信噪比图像稀疏表示去噪算法

针对低信噪比图像去噪问题,提出了一种基于K-SVD(Singular Value Decomposition)和残差比(Residual Ratio Iteration Termination)的正交匹配追踪(Orthogonal Matching Pursuit,OMP)图像稀疏分解去噪算法。该算法利用K-SVD算法将离散余弦变换(Discrete cosine transform,DCT)框架产生的冗余字典训练成能够有效反映图像结构特征的超完备字典,以实现图像的有效表示。然后以残差比作为OMP算法迭代的终止条件来实现图像的去噪。实验表明,该算法相对于传统基于Symlets小波图像去噪、基于Contourlet变换的图像去噪,以及基于DCT冗余字典的稀疏表示图像去噪,能够更加有效地滤除低信噪比图像中的高斯白噪声,保留原图像的有用信息。     

去除乘性噪音的主成分分析算法

雷达成像系统的进一步应用依赖于对图像中噪音的有效抑制.在目前现有消除噪音方法的基础上,基于图像的局部相似性,结合主成分分析法,提出一种新的有效去除乘性噪音的滤波算法.乘性噪音经对数变换后可转化为加性噪音处理.分析了对数域中噪音的类型.首先在图像的对数域,通过非局部方法选取局部相似块作为训练样本,利用主成分分析法提取出信号的主要特征.然后基于统计理论中最小均方误差估计法给出了一种适用于图像信息的阈值原则.最后分析了变换过程引起的偏差,由对数域的偏估计得到滤波图像.数值实验验证了新算法的有效性.对比于目前提出的变分方法,新算法处理后的图像有更高的信噪比和更好的视觉效果,且具有一定的实用性.     

A novel denoising method based on Radon transform and filtered back-projection reconstruction algorithm

A novel denoising method based on Radon transform and filtered back-projection (FBP) image reconstruction algorithm was proposed. This method can be considered as a special mean filter on projection line, which is different from most of the traditional filters operated on adjacent templates that could bring serious blurs to images. The details of images processed by the proposed method can be preserved relatively complete and the denoising effect is satisfactory. To verify the denoising effect of the proposed method, the simulation was designed and carried out, and the image evaluation parameters were applied to analyze the denoising effect and the detail-preserving ability quantitatively. For further understanding of the proposed method, the basic denoising principle of this method was analyzed. Noise points and information points can be distinguished: the attenuation velocity of gray scale of noise points is faster than that of information points, which was verified by the experiment. The results of different parameters in the proposed method were compared and analyzed. Several kinds of traditional filters were compared with the proposed method, and the result shows that the proposed method is better than the traditional filters in the aspects of both denoising effect and detail-preserving ability. Apart from this, the proposed method is not particular about the kind of noise; therefore, it is a powerful method to deal with atypical noise, uncertain noise, and mixed noises.     

基于神经网络和小波变换的MRI图像去噪方法

过去10年中,小波变换在图像去噪中取得了很大的成功.人们提出了多种适用于小波去噪的阈值方法,而这些方法就是希望能够正确地反映有噪声小波系数与无噪声小波系数之间的映射关系.基于这种想法,我们提出一种在小波域中利用神经网络寻找这种映射关系的图像去噪新方法.我们把该方法应用于不同噪声分布的磁共振图像的去噪,取得了良好的效果.     

基于Cycle Spinning Contourlet变换和总变分最小化的遥感图像去噪算法

针对很多已有的遥感图像去噪算法去噪的同时存在不能有效的保留细节和增强边缘的问题,提出了一种基于Cycle Spinning Contourlet变换和总变分最小化的图像去噪新算法。该算法依据了Cycle Spinning Contourlet变换能够很好的保留原始图像的细节和纹理信息,而总变分最小化方法具有在去噪的同时增强图像边缘的特性,因此使用所提出的融合规则对两种算法去噪后的图像进行融合能够取得更好的增强效果。通过对比,实验结果表明该算法不仅能在很大程度上削弱分别由平移不变Contourlet变换和总变分最小化的图像去噪方法产生的伪吉布斯现象和阶梯效应,而且视觉效果和PSNR值均优于其它方法,同时该算法能够保留更多的光谱信息,因此该算法是一种有效的遥感图像去噪算法。     

基于Cycle Spinning Contourlet变换和总变分最小化的遥感图像去噪算法(英文)

针对大部分已有的遥感图像去噪算法在去噪的同时不能有效的保留细节和增强边缘,提出了一种基于Cycle Spinning Contourlet变换和总变分最小化的图像去噪新算法.该算法依据了Cycle Spinning Contourlet变换能够很好的保留原始图像的细节和纹理信息,而总变分最小化方法具有在去噪的同时增强图像边缘的特性,因此使用所提出的融合规则对两种算法去噪后的图像进行融合能够取得更好的增强效果.通过对比,实验结果表明该算法不仅能在很大程度上削弱分别由平移不变Contourlet变换和总变分最小化的图像去噪方法产生的伪吉布斯现象和阶梯效应,而且视觉效果和PSNR值均优于其它方法,同时该算法能够保留更多的光谱信息,因此该算法是一种有效的遥感图像去噪算法.     

Nonlocal maximum likelihood estimation method for denoising multiple-coil magnetic resonance images

Effective denoising is vital for proper analysis and accurate quantitative measurements from magnetic resonance (MR) images. Even though many methods were proposed to denoise MR images, only few deal with the estimation of true signal from MR images acquired with phased-array coils. If the magnitude data from phased array coils are reconstructed as the root sum of squares, in the absence of noise correlations and subsampling, the data is assumed to follow a non central-χ distribution. However, when the k-space is subsampled to increase the acquisition speed (as in GRAPPA like methods), noise becomes spatially varying. In this note, we propose a method to denoise multiple-coil acquired MR images. Both the non central-χ distribution and the spatially varying nature of the noise is taken into account in the proposed method. Experiments were conducted on both simulated and real data sets to validate and to demonstrate the effectiveness of the proposed method.     

多尺度条件卷积的OCT视网膜图像降噪研究

散斑噪声存在于光学相干层析成像(OCT)中,影响OCT图像质量.在使用OCT设备诊断各种常见眼科疾病时,高质量的OCT图像是极为重要的.利用深度神经网络对OCT图像进行降噪处理,使图像在保留空间结构细节的基础上能展示更多的信息.提出了一种基于残差学习网络的新型OCT图像降噪网络-CMCNN,其具有多尺度、多权重和多层次...     

Bendlet Transform Based Adaptive Denoising Method for Microsection Images

Magnetic resonance imaging (MRI) plays an important role in disease diagnosis. The noise that appears in MRI images is commonly governed by a Rician distribution. The bendlets system is a second-order shearlet transform with bent elements. Thus, the bendlets system is a powerful tool with which to represent images with curve contours, such as the brain MRI images, sparsely. By means of the characteristic of bendlets, an adaptive denoising method for microsection images with Rician noise is proposed. In this method, the curve contour and texture can be identified as low-frequency components, which is not the case with other methods, such as the wavelet, shearlet, and so on. It is well known that the Rician noise belongs to a high-frequency channel, so it can be easily removed without blurring the clarity of the contour. Compared with other algorithms, such as the shearlet transform, block matching 3D, bilateral filtering, and Wiener filtering, the values of Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) obtained by the proposed method are better than those of other methods.     

Wavelet domain non-linear filtering for MRI denoising

Feature-preserved denoising is of great interest in medical image processing. This article presents a wavelet-based bilateral filtering scheme for noise reduction in magnetic resonance images. Undecimated wavelet transform is employed to provide effective representation of the noisy coefficients. Bilateral filtering of the approximate coefficients improves the denoising efficiency and effectively preserves the edge features. Denoising is done in the square magnitude domain, where the noise tends to be signal independent and is additive. The proposed method has been adapted specifically to Rician noise. The visual and the diagnostic quality of the denoised image is well preserved. The quantitative and the qualitative measures used as the quality metrics demonstrate the ability of the proposed method for noise suppression.     

基于噪声辅助非均匀采样复数据经验模态分解的混沌信号降噪

鉴于非均匀采样复数据经验模态分解(NSBEMD)相对传统分解方法的优势和噪声的NSBEMD特性,提出了一种基于噪声辅助NSBEMD的混沌信号自适应降噪方法.该方法首先以含噪混沌信号和高斯白噪声分别为实、虚部来构造复数据并进行NSBEMD,然后根据虚部各IMF的能量来估算实部各IMF中包含的噪声能量,最后根据噪声能量的估计值对实部IMF进行奇异值分解(SVD)降噪.噪声估计实验验证了噪声能量估计方法的可行性,而Lorenz信号和太阳黑子月平均数的降噪实验则表明,相对于现有EMD降噪方法,本文方法能够进一步消除噪声,更清晰地恢复出混沌吸引子的拓扑结构.     

A general strategy for anisotropic diffusion in MR image denoising and enhancement

Anisotropic diffusion (AD) has proven to be very effective in the denoising of magnetic resonance (MR) images. The result of AD filtering is highly dependent on several parameters, especially the conductance parameter. However, there is no automatic method to select the optimal parameter values. This paper presents a general strategy for AD filtering of MR images using an automatic parameter selection method. The basic idea is to estimate the parameters through an optimization step on a synthetic image model, which is different from traditional analytical methods. This approach can be easily applied to more sophisticated diffusion models for better denoising results. We conducted a systematic study of parameter selection for the AD filter, including the dynamic parameter decreasing rate, the parameter selection range for different noise levels and the influence of the image contrast on parameter selection. The proposed approach was validated using both simulated and real MR images. The model image generated using our approach was shown to be highly suitable for the purpose of parameter optimization. The results confirm that our method outperforms most state-of-the-art methods in both quantitative measurement and visual evaluation. By testing on real images with different noise levels, we demonstrated that our method is sufficiently general to be applied to a variety of MR images.     

关联成像目标重构的伪逆迭代降噪方法

结合伪逆关联成像和迭代去噪关联成像,提出了关联成像目标重构的伪逆迭代方法.该方法以伪逆关联成像重构结果为初始值,选取合适的与噪声干扰相关的阈值,通过迭代运算逼近实际的噪声干扰,最终抑制噪声并提高重构图像的峰值信噪比.以峰值信噪比和相关系数为衡量标准,将伪逆迭代关联成像的重构结果与差分关联成像、伪逆关联成像进行对比分析.仿真实验结果表明,伪逆迭代方法的峰值信噪比较伪逆关联成像方法、差分关联成像方法分别高出约1.0dB、3.1dB,同时其相关系数、视觉效果也有所改善,验证了该方法的有效性.     

扫描电镜图像去噪的研究与实现

扫描电镜能直观观察样品的表面结构,但其高分辨形貌成像图固有的噪声不利于图像分析。针对集成电路器件扫描电镜成像图的去噪声问题,采用了通过滑动条方式自适应设置图像二值化阈值,将数学形态学处理方法与图像二值化相结合,实现了对图像噪声的自动去除处理;同时还设计了通过手动勾勒图像中的多边形区域实现去除噪声的功能;为使图像达到更好的效果,系统还可允许针对自动去噪后的图像自行选择是否进行手动去噪,并设计实现了风格直观简洁,易于操作的交互式用户界面。对多幅集成电路器件扫描电镜成像图进行去噪声处理的结果和对去噪前后的图像进行无参考图像质量评价的数据表明,该方法有效地改善了扫描电镜图的信噪比,获得了突出前景等有用信息。     

Intensity image denoising for laser active imaging system using nonsubsampled contourlet transform and SURE approach

This paper presents an algorithm based on nonsubsampled contourlet transform (NSCT) and Stein's unbiased risk estimate with a linear expansion of thresholds (SURE-LET) approach for intensity image denoising. First, we analyzed the multiplicative noise model of intensity image and make the non-logarithmic transform on the noisy signal. Then, as a multiscale geometric representation tool with multi-directivity and shift-invariance, NSCT was performed to capture the geometric information of images. Finally, SURE-LET strategy was modified to minimize the estimation of the mean square error between the clean image and the denoised one in the NSCT domain. Experiments on real intensity images show that the algorithm has excellent denoising performance in terms of the peak signal-to-noise ratio (PSNR), the computation time and the visual quality.     

基于Rician分布的散斑噪声的超声图像模拟算法*

为了衡量各种去噪算法的性能,在干净无噪声的图像上添加接近真实且可控的散斑噪声是非常重要的,提出一种基于Rician分布的不完全发育的斑点噪声的超声图像模拟算法。该算法考虑到了声波区域中包含孤立的强散射体的情况,同时结合了超声成像的扫描过程。以合成图像和肾脏图像为体模进行了模拟实验,并对最终生成的伪超声图像进行了噪声分布统计及拟合检验。实验结果表明该算法生成的伪超声图像在视觉上和理论上都接近真实的超声图像。     

Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters

Magnetic resonance imaging (MRI) is an outstanding medical imaging modality but the quality often suffers from noise pollution during image acquisition and transmission. The purpose of this study is to enhance image quality using feature-preserving denoising method. In current literature, most existing MRI denoising methods did not simultaneously take the global image prior and local image features into account. The denoising method proposed in this paper is implemented based on an assumption of spatially varying Rician noise map. A two-step wavelet-domain estimation method is developed to extract the noise map. Following a Bayesian modeling approach, a generalized total variation-based MRI denoising model is proposed based on global hyper-Laplacian prior and Rician noise assumption. The proposed model has the properties of backward diffusion in local normal directions and forward diffusion in local tangent directions. To further improve the denoising performance, a local variance estimator-based method is introduced to calculate the spatially adaptive regularization parameters related to local image features and spatially varying noise map. The main benefit of the proposed method is that it takes full advantage of the global MR image prior and local image features. Numerous experiments have been conducted on both synthetic and real MR data sets to compare our proposed model with some state-of-the-art denoising methods. The experimental results have demonstrated the superior performance of our proposed model in terms of quantitative and qualitative image quality evaluations.     

一种改进的图像组合滤波方法

利用小波阈值去噪和Wiener滤波的特点,在文献［7］的基础上提出了一种改进的组合滤波方法,在进行空域自适应滤波之前,先对经BayesShrink处理过的预去噪图像重新估计其噪声方差,通过数值计算给出了该噪声方差的一种近似最优估计公式.实验结果表明该方法在去噪图像的均方误差和对不同图像的适应性方面都得到了改善.     

A sparse Bayesian representation for super-resolution of cardiac MR images

High-quality cardiac magnetic resonance (CMR) images can be hardly obtained when intrinsic noise sources are present, namely heart and breathing movements. Yet heart images may be acquired in real time, the image quality is really limited and most sequences use ECG gating to capture images at each stage of the cardiac cycle during several heart beats. This paper presents a novel super-resolution algorithm that improves the cardiac image quality using a sparse Bayesian approach. The high-resolution version of the cardiac image is constructed by combining the information of the low-resolution series –observations from different non-orthogonal series composed of anisotropic voxels – with a prior distribution of the high-resolution local coefficients that enforces sparsity. In addition, a global prior, extracted from the observed data, regularizes the solution. Quantitative and qualitative validations were performed in synthetic and real images w.r.t to a baseline, showing an average increment between 2.8 and 3.2 dB in the Peak Signal-to-Noise Ratio (PSNR), between 1.8% and 2.6% in the Structural Similarity Index (SSIM) and 2.% to 4% in quality assessment (IL-NIQE). The obtained results demonstrated that the proposed method is able to accurately reconstruct a cardiac image, recovering the original shape with less artifacts and low noise.