scholarly journals Realizing the Effective Detection of Tumor in Magnetic Resonance Imaging using Cluster-Sparse Assisted Super-Resolution

2021 ◽  
Vol 15 (1) ◽  
pp. 170-179
Author(s):  
Kathiravan Srinivasan ◽  
Ramaneswaran Selvakumar ◽  
Sivakumar Rajagopal ◽  
Dimiter Georgiev Velev ◽  
Branislav Vuksanovic
Keyword(s):  
Magnetic Resonance ◽  
Super Resolution ◽  
Mr Images ◽  
Self Similarity ◽  
Significant Research ◽  
Non Local ◽  
Brain Mr Images ◽  
Texture Detection ◽  
Sr Method ◽  
Robust To Noise

Recently, significant research has been done in Super-Resolution (SR) methods for augmenting the spatial resolution of the Magnetic Resonance (MR) images, which aids the physician in improved disease diagnoses. Single SR methods have drawbacks; they fail to capture self-similarity in non-local patches and are not robust to noise. To exploit the non-local self-similarity and intrinsic sparsity in MR images, this paper proposes the use of Cluster-Sparse Assisted Super-Resolution. This SR method effectively captures similarity in non-locally positioned patches by training on clusters of patches using a self-adaptive dictionary. This method of training also leads to better edge and texture detection. Experiments show that using Cluster-Sparse Assisted Super-Resolution for brain MR images results in enhanced detection of lesions leading to better diagnosis.

scholarly journals Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images

2016 ◽  
Vol 2016 ◽  
pp. 1-10
Author(s):  
Yunjie Chen ◽  
Tianming Zhan ◽  
Ji Zhang ◽  
Hongyuan Wang
Keyword(s):  
Magnetic Resonance ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Magnetic Resonance Images ◽  
Intensity Inhomogeneity ◽  
Mr Images ◽  
Proposed Model ◽  
Brain Mr Images ◽  
The Impact

We propose a novel segmentation method based on regional and nonlocal information to overcome the impact of image intensity inhomogeneities and noise in human brain magnetic resonance images. With the consideration of the spatial distribution of different tissues in brain images, our method does not need preestimation or precorrection procedures for intensity inhomogeneities and noise. A nonlocal information based Gaussian mixture model (NGMM) is proposed to reduce the effect of noise. To reduce the effect of intensity inhomogeneity, the multigrid nonlocal Gaussian mixture model (MNGMM) is proposed to segment brain MR images in each nonoverlapping multigrid generated by using a new multigrid generation method. Therefore the proposed model can simultaneously overcome the impact of noise and intensity inhomogeneity and automatically classify 2D and 3D MR data into tissues of white matter, gray matter, and cerebral spinal fluid. To maintain the statistical reliability and spatial continuity of the segmentation, a fusion strategy is adopted to integrate the clustering results from different grid. The experiments on synthetic and clinical brain MR images demonstrate the superior performance of the proposed model comparing with several state-of-the-art algorithms.

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.

A Modified Fuzzy C-Means Algorithm Brain MR Images Segmentation with Bias Field Compensation

2013 ◽  
Vol 756-759 ◽  
pp. 1349-1355 ◽  
Author(s):  
Xiao Li Liu ◽  
Yu Ting Guo ◽  
Jun Kong ◽  
Jian Zhong Wang
Keyword(s):  
Brain Mri ◽  
Bias Field ◽  
Local Information ◽  
Mr Images ◽  
Fcm Algorithm ◽  
Different Types ◽  
Field Estimation ◽  
Non Local ◽  
Brain Mr Images ◽  
Fuzzy C Means Algorithm

Segmentation of brain magnetic resonance (MR) images is always required as a preprocessing stage in many brain analysis tasks. Nevertheless, the bias field (BF, also called intensity in-homogeneities) and noise in the MRI images always make the accurate segmentation difficult. In this paper, we present a modified FCM algorithm for bias field estimation and segmentation of brain MRI. Our method is formulated by modifying the objective function of the standard FCM algorithm. It aims to compensate for bias field and incorporate both the local and non-local information into the distance function to restrain the noise of the image. We have conducted extensive experimental and have compared our method with different types of FCM extension methods using simulated MRI images. The results show that our proposed method can deal with the bias field and noise effectively and outperforms other methods.

Super-resolution Image Reconstruction from Projections Using Non-local and Local Regularizations

2020 ◽  
Author(s):  
Xue Ren ◽  
Soo-Jin Lee
Keyword(s):  
Image Reconstruction ◽  
Super Resolution ◽  
Weighting Factor ◽  
Image Resolution ◽  
Resolution Image ◽  
Advantages And Disadvantages ◽  
Wide Range ◽  
Non Local ◽  
Quality Assessments ◽  
Sr Method

This article presents a super-resolution (SR) method dedicated to tomographic imaging, where an image is reconstructed from projections obtained with low-resolution detectors. In this work, upscaling the image resolution is performed by backprojecting the projection measurements into the high-resolution image space modeled on a finer grid. Since this upscaling process often creates irregular pixels, it is important to employ regularizers that can reduce the irregular pixels while preserving fine details. Here we consider two different types of regularizers, non-local and local regularizers, each of which has been independently used for image reconstruction and is known to have its own advantages and disadvantages depending on the edge structures in the underlying image. To achieve a good compromise between the two types of regularizers, we selectively combine them using a space-variant weighting factor, which is systematically determined by our own criterion to classify edges. The experimental results show that our proposed SR method improves the reconstruction accuracy in various image quality assessments and has the potential to be useful in a wide range of imaging applications.

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

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.

A New Super-Resolution Reconstruction Algorithm Based on Block Sparse Representation

2013 ◽  
Vol 710 ◽  
pp. 603-607
Author(s):  
Xiao Dong Zhao ◽  
Jian Zhong Cao ◽  
Hui Zhang ◽  
Guang Sen Liu ◽  
Hua Wang ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Training Data ◽  
Self Similarity ◽  
Image Block ◽  
Non Local ◽  
Simulation Results ◽  
Sr Reconstruction ◽  
Suppress Noise

In this paper, we propose a new single super-resolution (SR) reconstruction algorithm via block sparse representation and regularization constraint. Firstly, discrete K-L transform is used to learn compression sub-dictionary according to the specific image block. Combined with threshold choice of training data, the transform bases are generated adaptively corresponding to the sparse domain. Secondly, Non-local Self-similarity (NLSS) regularization term is introduced into sparse reconstruction objective function as a prior knowledge to optimize reconstruction result. Simulation results validate that the proposed algorithm achieves much better results in PSNR and SSIM. It can both enhance edge and suppress noise effectively, which proves better robustness.

Sign in / Sign up

Export Citation Format

Share Document