MRI denoising by nonlocal means on multi-GPU

Granata, Donatella; Amato, Umberto; Alfano, Bruno

doi:10.1007/s11554-016-0566-2

Cited by 7 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, both steps are implemented in parallel computing on the GPUs. As demonstrated previously, 37,42 caching of image data using the high-speed shared memory in the GPU is crucial for efficient GPU implementations. In this work, a number of extra optimization steps have been implemented over the work by Granata et al 37 to further improve the computational efficiency.…”

Section: Gpu-accelerated Adaptive Nonlocal Means Algorithm and Optimimentioning

confidence: 98%

“…The original CPU-based ANLM filter 34 contains a number of key features, such as calculation of the weighted averages of nonlocal patches, preselection of nonlocal patches 38 for better image quality, spatial noise adaptivity, and wavelet sub-band mixing. 38,41 A comparison between the CPU-based ANLM, 34 the previously published GPU-ANLM filter, 37 and the GPU-ANLM filter developed in this work is shown in Table 1.…”

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

“…In both Ref. 37 and this work, the voxel-based update scheme is used. Second, the nonlocal patches with low similarities to the local patch can be ignored, referred to as "preselection," 34 to improve image quality and accelerate computation.…”

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

“…Second, the nonlocal patches with low similarities to the local patch can be ignored, referred to as "preselection," 34 to improve image quality and accelerate computation. Preselection is not considered in the previously published GPU-ANLM work 37 but is fully implemented in this work. Third, a wavelet transformation combining two different patch sizes can be used to improve filtering performance.…”

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

“…35 GPU-accelerated 3-D adaptive filters can potentially bring excellent computational efficiency (C4) to the state-of-the-art 3-D filters and make them suitable for denoising GPU MC simulations. Granata et al 37 reported significant speed improvements using a GPU-based ANLM filter. However, a number of simplifications were found when comparing it with the original ANLM filter, 34 including removal of the preselection of nonlocal patches, 2-D instead of 3-D estimation of noise variance, 34,38 and reduced data precision (2-byte integers for MRI data).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Graphics processing units-accelerated adaptive nonlocal means filter for denoising three-dimensional Monte Carlo photon transport simulations

Yuan

Dogan

et al. 2018

J. Biomed. Opt.

View full text Add to dashboard Cite

The Monte Carlo (MC) method is widely recognized as the gold standard for modeling light propagation inside turbid media. Due to the stochastic nature of this method, MC simulations suffer from inherent stochastic noise. Launching large numbers of photons can reduce noise but results in significantly greater computation times, even with graphics processing units (GPU)-based acceleration. We develop a GPU-accelerated adaptive nonlocal means (ANLM) filter to denoise MC simulation outputs. This filter can effectively suppress the spatially varying stochastic noise present in low-photon MC simulations and improve the image signal-to-noise ratio (SNR) by over 5 dB. This is equivalent to the SNR improvement of running nearly 3.5× more photons. We validate this denoising approach using both homogeneous and heterogeneous domains at various photon counts. The ability to preserve rapid optical fluence changes is also demonstrated using domains with inclusions. We demonstrate that this GPU-ANLM filter can shorten simulation runtimes in most photon counts and domain settings even combined with our highly accelerated GPU MC simulations. We also compare this GPU-ANLM filter with the CPU version and report a threefold to fourfold speedup. The developed GPU-ANLM filter not only can enhance three-dimensional MC photon simulation results but also be a valuable tool for noise reduction in other volumetric images such as MRI and CT scans.

show abstract

Section: Gpu-accelerated Adaptive Nonlocal Means Algorithm and Optimimentioning

confidence: 98%

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

Section: Adaptive Nonlocal Means Filters and Feature Comparisonsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Graphics processing units-accelerated adaptive nonlocal means filter for denoising three-dimensional Monte Carlo photon transport simulations

Yuan

Dogan

et al. 2018

J. Biomed. Opt.

View full text Add to dashboard Cite

show abstract

Dictionary adaptation and variational mode decomposition for gyroscope signal enhancement

Brzostowski

Świątek

2020

Appl Intell

View full text Add to dashboard Cite

The paper proposes an approach to signal denoising based on a combination of Variational Mode Decomposition with the Split Augmented Lagrangian Shrinkage Algorithm. In our research, we found that the proposed approach gives a great improvement of denoising gyroscopic signals. In turn, the results for the synthetic signals are not straightforward. For the bumps synthetic signals, the proposed algorithm gives the best results for different levels of signal degradation. While for the Doppler and blocks synthetic signals the reference methods give better results. However, for heavisine test signal the proposed algorithm gives better results in almost all cases. A weak point of the presented algorithm is its time complexity. The proposed approach is based on the Split Augmented Lagrangian Shrinkage Algorithm, which is the iterative optimization method since the time of computation strongly depends on the number of iterations. The presented results show that the proposed approach gives a great improvement in signal denoising and it is a promising direction of future research.

show abstract

Integrating Taylor–Krill herd‐based SVM to fuzzy‐based adaptive filter for medical image denoising

Narasimha

Rao

2020

IET Image Processing

View full text Add to dashboard Cite

MRI denoising by nonlocal means on multi-GPU

Cited by 7 publications

References 23 publications

Graphics processing units-accelerated adaptive nonlocal means filter for denoising three-dimensional Monte Carlo photon transport simulations

Graphics processing units-accelerated adaptive nonlocal means filter for denoising three-dimensional Monte Carlo photon transport simulations

Dictionary adaptation and variational mode decomposition for gyroscope signal enhancement

Integrating Taylor–Krill herd‐based SVM to fuzzy‐based adaptive filter for medical image denoising

Contact Info

Product

Resources

About