Deep Shrinkage Convolutional Neural Network for Adaptive Noise Reduction

Isogawa, Kenzo; Ida, Takashi; Shiodera, Taichiro; Takeguchi, Tomoyuki

doi:10.1109/lsp.2017.2782270

Cited by 153 publications

(83 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As is the case with SCNN, the use of a soft-shrinkage activation function provides adaptive denoising at various noise levels using a single CNN without a requirement to train a unique CNN for each noise level. 10,11 Soft shrinkage has a threshold T which is calculated by multiplying the noise level σ of the input noisy image and a coefficient a which is one of the training Fig. 1 Convolutional neural network (CNN) architecture of (a) denoising convolutional neural network (DnCNN), (b) shrinkage convolutional neural network (SCNN) and (c) deep learning-based reconstruction (dDLR).…”

Section: Deep-cnn Architecture Of Ddlrmentioning

confidence: 99%

“…[4][5][6] Recently, deep learning approaches for image noise reduction have been reported. [7][8][9] We have previously presented a MR image denoising method called the shrinkage convolutional neural network MAJOR PAPER (SCNN), 10,11 based on the denoising CNN (DnCNN) 8 approach. Unlike the DnCNN, the SCNN can be tuned to the noise power of the input image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers

Kidoh

Shinoda

Kitajima

et al. 2020

MRMS

Self Cite

161

119

View full text Add to dashboard Cite

Purpose:To test whether our proposed denoising approach with deep learning-based reconstruction (dDLR) can effectively denoise brain MR images. Methods:In an initial experimental study, we obtained brain images from five volunteers and added different artificial noise levels. Denoising was applied to the modified images using a denoising convolutional neural network (DnCNN), a shrinkage convolutional neural network (SCNN), and dDLR. Using these brain MR images, we compared the structural similarity (SSIM) index and peak signal-to-noise ratio (PSNR) between the three denoising methods. Two neuroradiologists assessed the image quality of the three types of images. In the clinical study, we evaluated the denoising effect of dDLR in brain images with different levels of actual noise such as thermal noise. Specifically, we obtained 2D-T 2 -weighted image, 2D-fluid-attenuated inversion recovery (FLAIR) and 3D-magnetization-prepared rapid acquisition with gradient echo (MPRAGE) from 15 healthy volunteers at two different settings for the number of image acquisitions (NAQ): NAQ2 and NAQ5. We reconstructed dDLR-processed NAQ2 from NAQ2, then compared with SSIM and PSNR. Two neuroradiologists separately assessed the image quality of NAQ5, NAQ2 and dDLR-NAQ2. Statistical analysis was performed in the experimental and clinical study. In the clinical study, the inter-observer agreement was also assessed. Results:In the experimental study, PSNR and SSIM for dDLR were statistically higher than those of DnCNN and SCNN (P < 0.001). The image quality of dDLR was also superior to DnCNN and SCNN. In the clinical study, dDLR-NAQ2 was significantly better than NAQ2 images for SSIM and PSNR in all three sequences (P < 0.05), except for PSNR in FLAIR. For all qualitative items, dDLR-NAQ2 had equivalent or better image quality than NAQ5, and superior quality to that of NAQ2 (P < 0.05), for all criteria except artifact. The inter-observer agreement ranged from substantial to near perfect.Conclusion: dDLR reduces image noise while preserving image quality on brain MR images.

show abstract

Section: Deep-cnn Architecture Of Ddlrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers

Kidoh

Shinoda

Kitajima

et al. 2020

MRMS

Self Cite

161

119

View full text Add to dashboard Cite

show abstract

“…Trajectory design of k-space sampling method is the first step of the image acquisition acceleration strategy and it is closely related with the subsequent reconstruction strategy. Cartesian k-space sampling is the most widely used trajectory design in current MRI image and in coronary MRA [108,109] No generally accepted standard for clinical use for any commercial filter DL denoising [19,20,[113][114][115][116]140] Better preservation of the edge Potentially works well with specific situation such as coronary MRA-dedicated denoising as well. The conversion from k-space domain to the image domain is simple with the inverse fast Fourier transform (FFT).…”

Section: Image Acquisition Acceleration Technique (1): Trajectory Desmentioning

confidence: 99%

Non-contrast coronary magnetic resonance angiography: current frontiers and future horizons

Kato

Ambale-Venkatesh

Kassai

et al. 2020

Magn Reson Mater Phy

View full text Add to dashboard Cite

Coronary magnetic resonance angiography (coronary MRA) is advantageous in its ability to assess coronary artery morphology and function without ionizing radiation or contrast media. However, technical limitations including reduced spatial resolution, long acquisition times, and low signal-to-noise ratios prevent it from clinical routine utilization. Nonetheless, each of these limitations can be specifically addressed by a combination of novel technologies including super-resolution imaging, compressed sensing, and deep-learning reconstruction. In this paper, we first review the current clinical use and motivations for non-contrast coronary MRA, discuss currently available coronary MRA techniques, and highlight current technical developments that hold unique potential to optimize coronary MRA image acquisition and post-processing. In the final section, we examine the various research-based coronary MRA methods and metrics that can be leveraged to assess coronary stenosis severity, physiological function, and atherosclerotic plaque characterization. We specifically discuss how such technologies may contribute to the clinical translation of coronary MRA into a robust modality for routine clinical use.

show abstract

“…1) Feature Representation: Feature representation is constructed on the basis of Convolutional Neural Networks (CNNs) [5], [6], [8], [10], [12], [13], [19], [20], [23], which can be considered as a feature extractor. It contains two convolutional blocks.…”

Section: A Generative Networkmentioning

confidence: 99%

Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network

Wang

Zhu

Tang

2019

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Recent face completion works have achieved significant improvement using generative adversarial networks (GANs). There are still two important issues in this challenging task: first, semantic understanding; and second, high-frequency details prediction. In this letter, we propose a unified model by introducing multicontext structures within GANs. Our model, named multi-context generative adversarial networks (MCGAN), automatically learns the hierarchical appearances of a corrupted image and predicted the missing regions from different perspectives. In this model, semantic understanding and high-frequency details are both taken into account and modeled with two parallel networks, respectively. While one learns the semantic understanding of the input face image at a high level, the other extracts low-level features for highfrequency details prediction. Our MCGAN takes full advantage of multi-scale features learned from two complementary networks and generates semantically new pixels for the missing region with fine details. Extensive quantitative and qualitative experiments on benchmark datasets show that the proposed model outperforms several state-of-the-art models.

show abstract

Deep Shrinkage Convolutional Neural Network for Adaptive Noise Reduction

Cited by 153 publications

References 13 publications

Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers

Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers

Non-contrast coronary magnetic resonance angiography: current frontiers and future horizons

Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network

Contact Info

Product

Resources

About