Noise Removal in Magnetic Resonance Images based on Non-Local Means and Guided Image Filtering

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.

Download Full-text

Rician noise reduction in magnetic resonance images using adaptive non-local mean and guided image filtering

Optical Review ◽

10.1007/s10043-016-0220-z ◽

2016 ◽

Vol 23 (3) ◽

pp. 460-469 ◽

Cited By ~ 4

Author(s):

Muhammad Tariq Mahmood ◽

Yeon-Ho Chu ◽

Young-Kyu Choi

Keyword(s):

Magnetic Resonance ◽

Noise Reduction ◽

Image Filtering ◽

Magnetic Resonance Images ◽

Rician Noise ◽

Local Mean ◽

Non Local ◽

Guided Image Filtering

Download Full-text

Collaborative non-local means denoising of magnetic resonance images

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI) ◽

10.1109/isbi.2015.7163936 ◽

2015 ◽

Cited By ~ 5

Author(s):

Geng Chen ◽

Pei Zhang ◽

Yafeng Wu ◽

Dinggang Shen ◽

Pew-Thian Yap

Keyword(s):

Magnetic Resonance ◽

Magnetic Resonance Images ◽

Local Means ◽

Non Local

Download Full-text

Noise reduction in magnetic resonance images using adaptive non‐local means filtering

Electronics Letters ◽

10.1049/el.2012.3602 ◽

2013 ◽

Vol 49 (5) ◽

pp. 324-326 ◽

Cited By ~ 7

Author(s):

B. Kang ◽

O. Choi ◽

J.D. Kim ◽

D. Hwang

Keyword(s):

Magnetic Resonance ◽

Noise Reduction ◽

Magnetic Resonance Images ◽

Local Means ◽

Non Local

Download Full-text

Denoising magnetic resonance images using collaborative non-local means

Neurocomputing ◽

10.1016/j.neucom.2015.11.031 ◽

2016 ◽

Vol 177 ◽

pp. 215-227 ◽

Cited By ~ 21

Author(s):

Geng Chen ◽

Pei Zhang ◽

Yafeng Wu ◽

Dinggang Shen ◽

Pew-Thian Yap

Keyword(s):

Magnetic Resonance ◽

Magnetic Resonance Images ◽

Local Means ◽

Non Local

Download Full-text

Despeckling Algorithm for Removing Speckle Noise from Ultrasound Images

Symmetry ◽

10.3390/sym12060938 ◽

2020 ◽

Vol 12 (6) ◽

pp. 938

Author(s):

Hyunho Choi ◽

Jechang Jeong

Keyword(s):

Additive Noise ◽

Low Frequency ◽

Speckle Noise ◽

Image Filtering ◽

Noise Removal ◽

Discrete Wavelet ◽

Ultrasound Images ◽

Noise Elimination ◽

Residual Noise ◽

Guided Image Filtering

Ultrasound (US) imaging can examine human bodies of various ages; however, in the process of obtaining a US image, speckle noise is generated. The speckle noise inhibits physicians from accurately examining lesions; thus, a speckle noise removal method is essential technology. To enhance speckle noise elimination, we propose a novel algorithm using the characteristics of speckle noise and filtering methods based on speckle reducing anisotropic diffusion (SRAD) filtering, discrete wavelet transform (DWT) using symmetry characteristics, weighted guided image filtering (WGIF), and gradient domain guided image filtering (GDGIF). The SRAD filter is exploited as a preprocessing filter because it can be directly applied to a medical US image containing speckle noise without a log-compression. The wavelet domain has the advantage of suppressing the additive noise. Therefore, a homomorphic transformation is utilized to convert the multiplicative noise into additive noise. After two-level DWT decomposition is applied, to suppress the residual noise of an SRAD filtered image, GDGIF and WGIF are exploited to reduce noise from seven high-frequency sub-band images and one low-frequency sub-band image, respectively. Finally, a noise-free image is attained through inverse DWT and an exponential transform. The proposed algorithm exhibits excellent speckle noise elimination and edge conservation as compared with conventional denoising methods.

Download Full-text