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

Brain Tumor is the abnormal development of tissues in the brain. According to survey report Times of India, 2019 around 5, 00,000 people are diagnosed with brain tumor in India. Among 5, 00,000 people 20 percent are children. Magnetic resonance image (MRI) used for clinical analysis of human body are sensitive to redundant Rician noise. Rician is the type of noise added during the acquisition of MRI. The removal of noise variance can be performed by constructing many filters. Among those filters, non-local means filter is used for denoising the Rician noise. In this project simulated MRI data and real time clinical data of T1, T2 and Proton Density weighted MRI images are de-noised and the performance metrics is analyzed using PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index Metric). The de-noised image is then subjected to thresholding and morphological operators and the tumor region is segmented.

Download Full-text

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

Journal of Information Technology Research ◽

10.4018/jitr.2020100102 ◽

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.

Download Full-text

Image Denoising Using Non-Local Means (NLM) Approach in Magnetic Resonance (MR) Imaging: A Systematic Review

Applied Sciences ◽

10.3390/app10207028 ◽

2020 ◽

Vol 10 (20) ◽

pp. 7028

Author(s):

Yeong-Cheol Heo ◽

Kyuseok Kim ◽

Youngjin Lee

Keyword(s):

Systematic Review ◽

Magnetic Resonance ◽

Mr Imaging ◽

Noise Reduction ◽

Research Result ◽

Reduction Algorithm ◽

Mr Images ◽

Local Means ◽

Non Local ◽

Noise Reduction Algorithm

The non-local means (NLM) noise reduction algorithm is well known as an excellent technique for removing noise from a magnetic resonance (MR) image to improve the diagnostic accuracy. In this study, we undertook a systematic review to determine the effectiveness of the NLM noise reduction algorithm in MR imaging. A systematic literature search was conducted of three databases of publications dating from January 2000 to March 2020; of the 82 publications reviewed, 25 were included in this study. The subjects were categorized into four major frameworks and analyzed for each research result. Research in NLM noise reduction for MR images has been increasing worldwide; however, it was found to have slightly decreased since 2016. It was found that the NLM technique was most frequently used on brain images taken using the general MR imaging technique; these were most frequently performed during simultaneous real and simulated experimental studies. In particular, comparison parameters were frequently used to evaluate the effectiveness of the algorithm on MR images. The ultimate goal is to provide an accurate method for the diagnosis of disease, and our conclusion is that the NLM noise reduction algorithm is a promising method of achieving this goal.

Download Full-text

Bayesian approach for Rician non-local means denoising in MR images

The Imaging Science Journal ◽

10.1179/1743131x15y.0000000008 ◽

2015 ◽

Vol 63 (6) ◽

pp. 303-314

Author(s):

D. W. Kim ◽

C. Kim ◽

D. H. Lim

Keyword(s):

Bayesian Approach ◽

Mr Images ◽

Local Means ◽

Non Local

Download Full-text