Rician noise removal from MR images using novel adapted selective non-local means filter

2012 ◽  
Vol 72 (1) ◽  
pp. 1-19 ◽  
Author(s):  
Sultan Zia ◽  
M. Arfan Jaffar ◽  
Anwar M. Mirza ◽  
Tae-Sun Choi
Keyword(s):  
Noise Removal ◽  
Rician Noise ◽  
Mr Images ◽  
Local Means ◽  
Non Local

Fuzzy similarity based non local means filter for Rician noise removal

2014 ◽  
Vol 74 (15) ◽  
pp. 5533-5556 ◽  
Author(s):  
Muhammad Sharif ◽  
Ayyaz Hussain ◽  
Muhammad Arfan Jaffar ◽  
Tae-Sun Choi
Keyword(s):  
Noise Removal ◽  
Rician Noise ◽  
Local Means ◽  
Fuzzy Similarity ◽  
Non Local

Laplacian based non-local means denoising of MR images with Rician noise

2013 ◽  
Vol 31 (9) ◽  
pp. 1599-1610 ◽  
Author(s):  
Hemalata V. Bhujle ◽  
Subhasis Chaudhuri
Keyword(s):  
Rician Noise ◽  
Mr Images ◽  
Local Means ◽  
Non Local

Discrete Total Variation-Based Non-Local Means Filter for Denoising Magnetic Resonance Images

2020 ◽  
Vol 13 (4) ◽  
pp. 14-31
Author(s):  
Nikita Joshi ◽  
Sarika Jain ◽  
Amit Agarwal
Keyword(s):  
Magnetic Resonance ◽  
Total Variation ◽  
Similarity Index ◽  
Noise Removal ◽  
Magnetic Resonance Images ◽  
Variation Method ◽  
Mr Images ◽  
Denoising Method ◽  
Local Means ◽  
Non Local

Magnetic resonance (MR) images suffer from noise introduced by various sources. Due to this noise, diagnosis remains inaccurate. Thus, removal of noise becomes a very important task when dealing with MR images. In this paper, a denoising method has been discussed that makes use of non-local means filter and discrete total variation method. The proposed approach has been compared with other noise removal techniques like non-local means filter, anisotropic diffusion, total variation, and discrete total variation method, and it proves to be effective in reducing noise. The performance of various denoising methods is compared on basis of metrics such as peak signal-to-noise ratio (PSNR), mean square error (MSE), universal image quality index (UQI), and structure similarity index (SSIM) values. This method has been tested for various noise levels, and it outperformed other existing noise removal techniques, without blurring the image.

Denoising 3D MR images by the enhanced non-local means filter for Rician noise

2010 ◽  
Vol 28 (10) ◽  
pp. 1485-1496 ◽  
Author(s):  
Hong Liu ◽  
Cihui Yang ◽  
Ning Pan ◽  
Enmin Song ◽  
Richard Green
Keyword(s):  
Rician Noise ◽  
Mr Images ◽  
Local Means ◽  
Non Local

scholarly journals Brain MR image denoising for Rician noise using pre-smooth non-local means filter

2015 ◽  
Vol 14 (1) ◽  
pp. 2 ◽  
Author(s):  
Jian Yang ◽  
Jingfan Fan ◽  
Danni Ai ◽  
Shoujun Zhou ◽  
Songyuan Tang ◽  
...  
Keyword(s):  
Image Denoising ◽  
Rician Noise ◽  
Mr Image ◽  
Local Means ◽  
Non Local

scholarly journals Adaptive non-local means denoising of MR images with spatially varying noise levels

2009 ◽  
Vol 31 (1) ◽  
pp. 192-203 ◽  
Author(s):  
José V. Manjón ◽  
Pierrick Coupé ◽  
Luis Martí-Bonmatí ◽  
D. Louis Collins ◽  
Montserrat Robles
Keyword(s):  
Mr Images ◽  
Noise Levels ◽  
Local Means ◽  
Non Local ◽  
Spatially Varying

scholarly journals Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2918 ◽  
Author(s):  
Houqiang Yu ◽  
Mingyue Ding ◽  
Xuming Zhang
Keyword(s):  
Similarity Index ◽  
Similarity Measures ◽  
Noise Removal ◽  
Human Vision ◽  
Rician Noise ◽  
Mr Images ◽  
Laplacian Eigenmaps ◽  
Nonlocal Means ◽  
Output Layer ◽  
Denoised Image

Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

Sign in / Sign up

Export Citation Format

Share Document