Noise removal from MR images via iterative regularization based on higher-order singular value decomposition

Yeganli, S. Faegheh; Demirel, Hasan; Yu, Runyi

doi:10.1007/s11760-017-1110-y

Cited by 10 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to image completion methods, the denoising methods can be divided into two groups: decomposition based[ 18 20 ] and low-rank-based methods. [ 85 89 94 95 96 ] The low-rank-based methods use the following cost function for denosing.…”

Section: Tensor-based Biomedical Image Analysismentioning

confidence: 99%

Tensor Methods in Biomedical Image Analysis

Sedighin

2024

Journal of Medical Signals &Amp; Sensors

View full text Add to dashboard Cite

In the past decade, tensors have become increasingly attractive in different aspects of signal and image processing areas. The main reason is the inefficiency of matrices in representing and analyzing multimodal and multidimensional datasets. Matrices cannot preserve the multidimensional correlation of elements in higher-order datasets and this highly reduces the effectiveness of matrix-based approaches in analyzing multidimensional datasets. Besides this, tensor-based approaches have demonstrated promising performances. These together, encouraged researchers to move from matrices to tensors. Among different signal and image processing applications, analyzing biomedical signals and images is of particular importance. This is due to the need for extracting accurate information from biomedical datasets which directly affects patient’s health. In addition, in many cases, several datasets have been recorded simultaneously from a patient. A common example is recording electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) of a patient with schizophrenia. In such a situation, tensors seem to be among the most effective methods for the simultaneous exploitation of two (or more) datasets. Therefore, several tensor-based methods have been developed for analyzing biomedical datasets. Considering this reality, in this paper, we aim to have a comprehensive review on tensor-based methods in biomedical image analysis. The presented study and classification between different methods and applications can show the importance of tensors in biomedical image enhancement and open new ways for future studies.

show abstract

Section: Tensor-based Biomedical Image Analysismentioning

confidence: 99%

Tensor Methods in Biomedical Image Analysis

Sedighin

2024

Journal of Medical Signals &Amp; Sensors

View full text Add to dashboard Cite

show abstract

“…As we have reviewed above, most image denoising approaches are developed based on the assumption of a known noise variance [3]- [8], [10]- [16]. This largely restricts them in terms of practical use.…”

Section: Related Workmentioning

confidence: 99%

“…Since the algorithms in [8], [9] consider the relative importance of different SVs, the quality of the recovered image is very competitive in terms of the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Several variants of SAIST and WNNM have been developed [10]- [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Denoising Based on Nonlocal Bayesian Singular Value Thresholding and Stein’s Unbiased Risk Estimator

Xie

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Singular value thresholding (SVT) or nuclear norm minimization (NNM)-based nonlocal image denoising methods often rely on the precise estimation of the noise variance. However, most existing methods either assume the noise variance is known or require an extra step to estimate it. Under the iterative regularization framework, the error in the noise variance estimate propagates and accumulates with each iteration, ultimately degrading the overall denoising performance. In addition, the essence of these methods is still least squares estimation, which can cause a very high Mean Squared Error (MSE) and is inadequate for handling missing data or outliers. In order to address these deficiencies, we present a hybrid denoising model based on variational Bayesian inference and Stein's unbiased risk estimator (SURE), which consists of two complementary steps. In the first step, the variational Bayesian singular value thresholding performs a low-rank approximation of the nonlocal image patch matrix to simultaneously remove the noise and estimate the noise variance. In the second step, we modify the conventional SURE full rank SVT and its divergence formulas for rank-reduced eigen-triplets to remove the residual artefacts. The proposed hybrid BSSVT method achieves better performance in recovering the true image compared with state-of-the-art methods.

show abstract

“…In recent years, signal sparse representation has become a hot topic in the field of signal processing. The redundant sparse de-noising methods are represented by K-Singular Value Decomposition (K-SVD) [18]- [24] and Multiscale K-SVD (MK-SVD) [25], [26] and Learned Simultaneous Sparse Coding (LSSC) [27]. They can satisfy with the sparsity, feature retention and separability of signal noise, and has been successfully applied to the image de-noising [28], [29] and seismic data de-noising [30].…”

Section: Introductionmentioning

confidence: 99%

Blocked and Accelerated Wavelet De-noising Algorithm Based on Data Splitting and Wavelet Analysis in Large Data Environment for Aero-Engine Health Monitoring

Zhang¹

2018

IJOEE

View full text Add to dashboard Cite

Data de-noising is a necessary part of health management, and it is the premise and foundation of effective feature extraction, condition monitoring and fault diagnosis for aero-engine. Random noise can cause serious interference to effective signals, and even lead to signal distortion and misdiagnosis of health condition. In view of the contradiction between the limited computing power of aircraft airborne system and the large amount of data processing, an blocked wavelet de-noising algorithm for large data is proposed based on the principle of data splitting theory and the wavelet theory under the multiple constraints of large data, high de-noising precision and fast processing speed. The algorithm used data splitting principle to split large data into small data sets, reduced the computational requirements of large data, and accelerated the speed of wavelet de-noising. The processing results of the theoretical data and the actual airborne aero-engine monitoring data showed that, compared with the traditional algorithms, the algorithm can protect the effective information and maintain the same de-noising accuracy, and the data de-noising time in the aero engine health monitoring data environment was accelerated by 4 times at least.

show abstract

Noise removal from MR images via iterative regularization based on higher-order singular value decomposition

Cited by 10 publications

References 41 publications

Tensor Methods in Biomedical Image Analysis

Tensor Methods in Biomedical Image Analysis

Image Denoising Based on Nonlocal Bayesian Singular Value Thresholding and Stein’s Unbiased Risk Estimator

Blocked and Accelerated Wavelet De-noising Algorithm Based on Data Splitting and Wavelet Analysis in Large Data Environment for Aero-Engine Health Monitoring

Contact Info

Product

Resources

About