Improved visualization and quantification of 4D flow MRI data using divergence-freewavelet denoising

Ong, Frank; Uecker, Martin; Tariq, Umar; Hsiao, Albert; Alley, M. T.; Vasanawala, Shreyas S.; Lustig, Michael

doi:10.1109/isbi.2013.6556692

Cited by 5 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, different wavelet coefficients are analyzed and processed, and different denoising algorithms can be obtained. 21,25 Wavelet signal spectrum is shown in Figure 6.…”

Section: Image Denoising In Wavelet Domainmentioning

confidence: 99%

“…The image is a two‐dimensional signal, the wavelet transform is orthogonal wavelet transform to data has a strong correlation, can make the energy of image in the wavelet domain is concentrated in a few large wavelet coefficients, and the noise energy is distributed in the wavelet domain. Therefore, different wavelet coefficients are analyzed and processed, and different denoising algorithms can be obtained 21,25 …”

Section: Wavelet Transformmentioning

confidence: 99%

“…A basic idea of wavelet domain denoising is, according to the characteristics of wavelet coefficients of noisy image, to calculate out the wavelet coefficients of image denoising, the key issue here is to find the mapping relationship between the wavelet coefficients of image with noise and noise free image wavelet coefficients. The neural network can be trained by the sample extract the mapping relationship between input and output hidden in the sample data, so we can conceive of the neural network to determine the mapping between wavelet coefficients of images with noise and noise of wavelet coefficients of the image, so as to achieve the purpose of image denoising 25,29 …”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…The neural network can be trained by the sample extract the mapping relationship between input and output hidden in the sample data, so we can conceive of the neural network to determine the mapping between wavelet coefficients of images with noise and noise of wavelet coefficients of the image, so as to achieve the purpose of image denoising. 25,29 According to the characteristics of the neural network, the algorithm is divided into two processes, ie, training and simulation. A neural network is used to find the relation between the wavelet coefficients of the noisy image and the wavelet coefficients of the noiseless image.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

See 3 more Smart Citations

Retracted: Complex image denoising framework with CNN‐wavelet under concurrency scenarios for informatics systems

Wang

Huang

Zhang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Image denoising based on convolutional neural networks and wavelet transform is a novel approach for the applications. In the image acquisition process, images are often contaminated by noise, which affects the image quality; therefore, it is necessary to eliminate noise before analyzing and using images. Wavelet analysis is a local analysis method with multi-resolution characteristics, which is developed on the basis of short-time Fourier transform. It can be used for the multi-scale analysis of signals by means of expansion, translation and other operations, and extracting effective information from signals, which is a powerful tool for analyzing non-stationary signals. Wavelet has good time-frequency local characteristics, low entropy, and decorrelation. In this paper, we propose MRI image denoising framework based on convolutional neural networks and wavelet transform, and the experiment results show that the proposed method can keep the edge and curvature structure better while denoising. Compared with the other novel methodologies, the proposed algorithm can provide the higher robustness. In the future research, we will try the implementations of the methodologies.

show abstract

“…Therefore, different wavelet coefficients are analyzed and processed, and different denoising algorithms can be obtained. 21,25 Wavelet signal spectrum is shown in Figure 6.…”

Section: Image Denoising In Wavelet Domainmentioning

confidence: 99%

Section: Wavelet Transformmentioning

confidence: 99%

Section: Convolutional Neural Networkmentioning

confidence: 99%

Section: Convolutional Neural Networkmentioning

confidence: 99%

See 2 more Smart Citations

Retracted: Complex image denoising framework with CNN‐wavelet under concurrency scenarios for informatics systems

Wang

Huang

Zhang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In this work, we present a robust and effective noise reduction processing using the divergence‐free wavelet (DFW) transform . DFWs were first introduced by Lemarié‐Rieusset to the computational fluid dynamics (CFD) community in the 1980s.…”

Section: Introductionmentioning

confidence: 99%

Robust 4D flow denoising using divergence‐free wavelet transform

Ong

Uecker

Tariq

et al. 2014

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To investigate four-dimensional flow denoising using the divergence-free wavelet (DFW) transform and compare its performance with existing techniques. Theory and Methods DFW is a vector-wavelet that provides a sparse representation of flow in a generally divergence-free field and can be used to enforce “soft” divergence-free conditions when discretization and partial voluming result in numerical nondivergence-free components. Efficient denoising is achieved by appropriate shrinkage of divergence-free wavelet and nondivergence-free coefficients. SureShrink and cycle spinning are investigated to further improve denoising performance. Results DFW denoising was compared with existing methods on simulated and phantom data and was shown to yield better noise reduction overall while being robust to segmentation errors. The processing was applied to in vivo data and was demonstrated to improve visualization while preserving quantifications of flow data. Conclusion DFW denoising of four-dimensional flow data was shown to reduce noise levels in flow data both quantitatively and visually.

show abstract

Chemical shift–based prospective k‐space anonymization

Mattern

Knoll

Lüsebrink

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Publicly available data provision is an essential part of open science. However, open data can conflict with data privacy and data protection regulations. Head scans are particularly vulnerable because the subject’s face can be reconstructed from the acquired images. Although defacing can impede subject identification in reconstructed images, this approach is not applicable to k‐space raw data. To address this challenge and allow defacing of raw data for publication, we present chemical shift–based prospective k‐space anonymization (CHARISMA). Methods In spin‐warp imaging, fat shift occurs along the frequency‐encoding direction. By placing an oil‐filled mask onto the subject’s face, the shifted fat signal can overlap with the face to deface k‐space during the acquisition. The CHARISMA approach was tested for gradient‐echo sequences in a single subject wearing the oil‐filled mask at 7 T. Different fat shifts were compared by varying the readout bandwidth. Furthermore, intensity‐based segmentation was used to test whether the images could be unmasked retrospectively. Results To impede subject identification after retrospective unmasking, the signal of face and shifted oil should overlap. In this single‐subject study, a shift of 3.3 mm to 4.9 mm resulted in the most efficient masking. Independent of CHARISMA, long TEs induce signal decay and dephasing, which impeded unmasking. Conclusion To our best knowledge, CHARISMA is the first prospective k‐space defacing approach. With proper fat‐shift direction and amplitude, this easy‐to‐build, low‐cost solution impaired subject identification in gradient‐echo data considerably. Further sequences will be tested with CHARISMA in the future.

show abstract

Improved visualization and quantification of 4D flow MRI data using divergence-freewavelet denoising

Cited by 5 publications

References 6 publications

Retracted: Complex image denoising framework with CNN‐wavelet under concurrency scenarios for informatics systems

Retracted: Complex image denoising framework with CNN‐wavelet under concurrency scenarios for informatics systems

Robust 4D flow denoising using divergence‐free wavelet transform

Chemical shift–based prospective k‐space anonymization

Contact Info

Product

Resources

About