Denoising of diffusion MRI using random matrix theory

  title={Denoising of diffusion MRI using random matrix theory},
  author={Jelle Veraart and Dmitry S. Novikov and Daan Christiaens and Benjamin Ades-aron and Jan Sijbers and Els Fieremans},

Tensor denoising of high-dimensional MRI data

Rather than combining dimensions in matrices, tMPPCA utilizes each dimension of the multidimensional data’s inherent tensor-structure to better characterize noise, and to recursively estimate signal components.

Multi-channel framelet denoising of diffusion-weighted images

A tight wavelet frame based approach for edge-preserving denoising of diffusion-weighted (DW) images using the unitary extension principle (UEP) to generate frames that are discrete analogues to differential operators of various orders, which will help avoid stair-casing effects.

Supervised Denoising of Diffusion-Weighted Magnetic Resonance Images Using a Convolutional Neural Network and Transfer Learning

Visual comparisons made in the acquired brain images indicate that the denoised single-repetition images are less noisy than multi-rePETition averaged images.

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

A self-supervised learning method for denoising DWI data, Patch2Self, which uses the entire volume to learn a full-rank locally linear denoiser for that volume, and demonstrates the effectiveness via quantitative and qualitative improvements in microstructure modeling, tracking and model estimation relative to other unsupervised methods on real and simulated data.

Denoising High-Field Multi-Dimensional MRI With Local Complex PCA

This work proposes a Denoising technique for multi-parametric quantitative MRI, combining a highly popular denoising method from diffusion imaging, over-complete local PCA, with a reconstruction of the complex-valued MR signal in order to define stable estimates of the noise in the decomposition.

MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion

This work proposes a new denoising method based on score-based reverse diffusion sampling, which overcomes all the aforementioned drawbacks and establishes state-of-the-art performance, while having desirable properties which prior MMSE denoisers did not have.



Diffusion Weighted Image Denoising Using Overcomplete Local PCA

This new filter reduces random noise in multicomponent DWI by locally shrinking less significant Principal Components using an overcomplete approach and is compared with state-of-the-art methods using synthetic and real clinical MR images, showing improved performance in terms of denoising quality and estimation of diffusion parameters.

MRI denoising using Non-Local Means

Random Matrix Theory-based noise reduction for dynamic imaging : Application to DCE-MRI

1.Purpose: How to denoise dynamic MRI maps? If the maps are static, e.g. a diffusion or relaxation scan, averaging over a large number T of independent acquisitions can reduce noise standard

MRI noise estimation and denoising using non-local PCA

Statistical artifacts in diffusion tensor MRI (DT‐MRI) caused by background noise

This work helps elucidate how background noise introduces statistical artifacts in the distribution of the sorted eigenvalues and eigenvectors in diffusion tensor MRI (DT‐MRI) data and develops a statistical framework to enhance the ability to characterize microstructure and architecture of healthy tissue.

RESTORE: Robust estimation of tensors by outlier rejection

Results from both simulated and clinical diffusion data sets indicate that the RESTORE method improves tensor estimation compared to the commonly used linear and nonlinear least‐squares tensor fitting methods and a recently proposed method based on the Geman–McClure M‐estimator.

Experimental considerations for fast kurtosis imaging

The effects of noise and nonideal diffusion encoding are analyzed and a new correction strategy is proposed, and a 1‐9‐9 protocol is presented with increased robustness to experimental imperfections and minimal additional scan time.

Optimal strategies for measuring diffusion in anisotropic systems by magnetic resonance imaging

An algorithm is presented that minimizes the bias inherent in making measurements with a fixed set of gradient vector directions by spreading out measurements in 3‐dimensional gradient vector space and this results in reduced scan times, increased precision, or improved resolution in diffusion tensor images.