scholarly journals To Analyse the Effect of Relaxation Type on Magnetic Resonance Image Compression Using Compressive Sensing

2021 ◽  
Vol 17 (04) ◽  
pp. 21
Author(s):  
Vivek Upadhyaya ◽  
Mohammad Salim
Keyword(s):  
Magnetic Resonance ◽  
Compressive Sensing ◽  
Magnetic Resonance Image ◽  
Similarity Index ◽  
Structural Similarity ◽  
Scanning Speed ◽  
Proton Density ◽  
Body Parts ◽  
Mr Image ◽  
Reconstruction Process

<span>Medical Imaging and scanning technologies are used to provide better resolution of body and tissues. To achieve a better quality Magnetic Resonance (MR) image with a minimum duration of processing time is a tedious task. So our purpose in this paper is to find out a solution that can minimize the reconstruction time of an MRI signal. </span><span>Compressive sensing can be used to accelerate Magnetic Resonance Image (MRI) acquisition by acquiring fewer data through the under-sampling of k-space, so it can be used to minimize the time. But according to the relaxation time, we can further classify the MRI signal into T1, T2, and Proton Density (PD) weighted images. These weighted images represent different signal intensities for different types of tissues and body parts. It also affects the reconstruction process conducted by using the Compressive Sensing Approach. This study is based on finding out the effect of T1, T2, and Proton Density (PD) weighted images on the reconstruction process as well as various image quality parameters like MSE, PSNR, &amp; SSIM also calculated to analyze this effect. Meanwhile, we can analyze how many samples are enough to reconstruct the MR image so the problem associated with time and scanning speed can be reduced up to an extent. In this paper, we got the Structural Similarity Index Measure (SSIM) value up to 0.89 &amp; PSNR value 37.83451 dB at an 85 % compression ratio for the T2 weighted image. </span>

scholarly journals Compressive Sensing Magnetic Resonance Image Reconstruction and Denoising using Convolutional Neural Network

2022 ◽  
Vol 2161 (1) ◽  
pp. 012036
Author(s):  
Ram Singh ◽  
Lakhwinder Kaur
Keyword(s):  
Magnetic Resonance ◽  
Image Reconstruction ◽  
Image Quality ◽  
Data Acquisition ◽  
Compressive Sensing ◽  
Magnetic Resonance Image ◽  
Motion Artifacts ◽  
Acquisition Time ◽  
High Quality ◽  
Mr Image

Abstract Restoration of high-quality brain Magnetic Resonance Image (MRI) from the sparse under-sampled complex k-space signal is a widely studied ill-posed inverse transform problem. A deep learning-based data-adaptive and data-driven convolutional technique has been proposed for high-quality MRI recovery from its under-sampled complex domain k-space signal. The uniform subsampling process is very slow in phase-encoding to generate high-resolution images. The longer scan times degrade the perceptual image quality. Various factors contribute to image degradation during data acquisition such as the inception of body motion artifacts, the thermal energy effects of the body, and random noise artifacts due to voltage fluctuations. Keeping in view the patient’s critical condition and comfort, longer scan times are not preferred in practice. To reduce the image acquisition time, noise levels, and motion artifacts in the MR images, Compressive Sensing (CS) provides an accelerated way to reconstructs the high-quality MR image from very limited signal measurements acquired much below the Nyquist rate. However, such data acquisition strategies require advanced computer algorithms for the reconstruction of high-quality MRI from the undersampled MRI data. An improved CNN-based MRI reconstructed algorithm has been presented in this paper which shows better performance to reconstruct high-quality MRI than similar other MR image reconstruction algorithms. The performance of the proposed algorithm is measured by image quality checking tools such as normalized-MSE, PSNR, and SSIM.

Magnetic resonance image attributes of the bovine ovarian follicle antrum during development and regression

Reproduction ◽  
2000 ◽  
pp. 311-323 ◽  
Author(s):  
JL Hilton ◽  
GE Sarty ◽  
GP Adams ◽  
RA Pierson
Keyword(s):  
Magnetic Resonance ◽  
Relaxation Rate ◽  
Follicular Fluid ◽  
Magnetic Resonance Image ◽  
Follicular Development ◽  
Physiological Status ◽  
Proton Density ◽  
Dominant Follicle ◽  
Rate Heterogeneity ◽  
Pixel Value

The magnetic resonance images and maps of bovine ovaries acquired at defined phases of follicular development and regression were studied to determine whether magnetic resonance image attributes of the follicular antrum reflect the physiological status of dominant and subordinate ovarian follicles. Ovariectomies were performed at day 3 of wave one, day 6 of wave one, day 1 of wave two and at >/= day 17 after ovulation. The timings of ovariectomies were selected to acquire growing, early static, late static and regressing follicles of the first wave and preovulatory follicles of the ovulatory wave. Pre-selection and subordinate follicles were also available for analysis. Serum samples were taken on the day of ovariectomy and follicular fluid samples were taken after imaging. Numerical pixel value and pixel heterogeneity in a spot representing approximately 95% of the follicular antrum were quantified in T(1)- and T(2)-weighted images. T(1) and T(2) relaxation rates (T(1) and T(2)), proton density, apparent diffusion coefficients and their heterogeneities were determined from the computed magnetic resonance maps. The antra of early atretic dominant follicles showed higher T(2)-weighted mean pixel value (P < 0.008) and heterogeneity (P < 0. 01) and lower T(2) heterogeneity (P < 0.008) than growing follicles. Subordinate follicles in the presence of a preovulatory dominant follicle had higher T(1), T(1) heterogeneity, proton density, proton density heterogeneity, and lower mean pixel value in T(1)-weighted images than subordinate follicles of the anovulatory wave (P < 0.04). T(1) relaxation rate heterogeneity and proton density heterogeneity were positively correlated with follicular fluid oestradiol concentration (r = 0.4 and 0.3; P < 0.04). T(2) relaxation rate heterogeneity was positively correlated with follicular fluid progesterone concentration (r = 0.4; P < 0.008). Quantitative differences in magnetic resonance image attributes of the antrum observed among phases of follicular development and regression coincided with changes in the ability of the dominant follicle to produce steroid hormones and ovulate, and thus were indicative of physiological status and follicular health.

scholarly journals Implementation of Iterative bilateral filtering for removal of Rician noise in MR images using FPGA

2020 ◽  
Vol 9 (3) ◽  
pp. 279-284
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Visual Analysis ◽  
Similarity Index ◽  
Structural Similarity ◽  
Bilateral Filter ◽  
Magnetic Resonance Images ◽  
Rician Noise ◽  
Diagnostic Quality ◽  
Index Matrix

Magnetic resonance image noise reduction is important to process further and visual analysis. Bilateral filter is denoises image and also preserves edge. It proposes Iterative bilateral filter which reduces Rician noise in the magnitude magnetic resonance images and retains the fine structures, edges and it also reduces the bias caused by Rician noise. The visual and diagnostic quality of the image is retained. The quantitative analysis is based on analysis of standard quality metrics parameters like peak signal-to-noise ratio and mean structural similarity index matrix reveals that these methods yields better results than the other proposed denoising methods for MRI. Problem associated with the method is that it is computationally complex hence time consuming. It is not recommended for real time applications. To use in real time application a parallel implantation of the same using FPGA is proposed.

scholarly journals A Soft-Threshold Filtering Approach for Tomography Reconstruction from a Limited Number of Projections with Bilateral Edge Preservation

Sensors ◽  
2019 ◽  
Vol 19 (10) ◽  
pp. 2346
Author(s):  
Tiago Wirtti ◽  
Evandro Salles
Keyword(s):  
Objective Function ◽  
Total Variation ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Edge Preservation ◽  
Edge Preserving ◽  
Reconstruction Process ◽  
Regularization Term ◽  
Computational Performance

In X-ray tomography image reconstruction, one of the most successful approaches involves a statistical approach with l 2 norm for fidelity function and some regularization function with l p norm, 1 < p < 2 . Among them stands out, both for its results and the computational performance, a technique that involves the alternating minimization of an objective function with l 2 norm for fidelity and a regularization term that uses discrete gradient transform (DGT) sparse transformation minimized by total variation (TV). This work proposes an improvement to the reconstruction process by adding a bilateral edge-preserving (BEP) regularization term to the objective function. BEP is a noise reduction method and has the purpose of adaptively eliminating noise in the initial phase of reconstruction. The addition of BEP improves optimization of the fidelity term and, as a consequence, improves the result of DGT minimization by total variation. For reconstructions with a limited number of projections (low-dose reconstruction), the proposed method can achieve higher peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) results because it can better control the noise in the initial processing phase.

scholarly journals Lifting Wavelet Transform in Compressive Sensing for MRI Reconstruction

2020 ◽  
Vol 55 (5) ◽  
Author(s):  
Indrarini Dyah Irawati ◽  
Sugondo Hadiyoso ◽  
Gelar Budiman ◽  
Asep Mulyana
Keyword(s):  
Wavelet Transform ◽  
Magnetic Resonance ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Reconstruction Algorithm ◽  
Structural Similarity ◽  
Lifting Wavelet Transform ◽  
Structural Similarity Index ◽  
Compressed Sampling ◽  
Lifting Wavelet

Compressed sampling in the application of magnetic resonance imaging compression requires high accuracy when reconstructing from a small number of samples. Sparsity in magnetic resonance images is a fundamental requirement in compressed sampling. In this paper, we proposed the lifting wavelet transform sparsity technique by taking wavelet coefficients on the low pass sub-band that contains meaningful information. The application of novel methods useful for compressing data with the highest compression ratio at the sender but still maintaining high accuracy at the receiver. These wavelet coefficient values are arranged to form a sparse vector. We explore the performance of the proposed method by testing at several levels of lifting wavelet transform decomposition, include Levels 2, 3, 4, 5, and 6. The second requirement for compressed sampling is the acquisition technique. The data sampled sparse vectors using a normal distributed random measurement matrix. This matrix is normalized to the average energy of the image pixel block. The last compressed sampling requirement is a reconstruction algorithm. In this study, we analyze three reconstruction algorithms, namely Level 1 magic, iteratively reweighted least squares, and orthogonal matching pursuit, based on structural similarity index measured and peak signal to noise ratio metrics. Experimental results show that magnetic resonance imaging can be reconstructed with higher structural similarity index measured and peak signal to noise ratio using the lifting wavelet transform sparsity technique at a minimum decomposition level of 4. The proposed lifting wavelet transforms and Level 1 magic reconstruction algorithm has the best performance compared to the others at the measurement rate range between 10 to 70. This method also outperforms the techniques in previous studies.

scholarly journals Brain Tissue Evaluation Based on Skeleton Shape and Similarity Analysis between Hemispheres

Computation ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 31
Author(s):  
Lenuta Pana ◽  
Simona Moldovanu ◽  
Nilanjan Dey ◽  
Amira S. Ashour ◽  
Luminita Moraru
Keyword(s):  
Brain Tissue ◽  
Right Hemisphere ◽  
Similarity Index ◽  
Region Of Interest ◽  
Structural Similarity ◽  
Noise Removal ◽  
Mirror Reflection ◽  
Proton Density ◽  
Rician Noise ◽  
Evaluation Tool

Background: The purpose of this article is to provide a new evaluation tool based on skeleton maps to assess the tumoral and non-tumoral regions of the 2D MRI in PD-weighted (proton density) and T2w (T2-weighted type) brain images. Methods: The proposed method investigated inter-hemisphere brain tissue similarity using a mask in the right hemisphere and its mirror reflection in the left one. At the hemisphere level and for each ROI (region of interest), a morphological skeleton algorithm was used to efficiently investigate the similarity between hemispheres. Two datasets with 88 T2w and PD images belonging to healthy patients and patients diagnosed with glioma were investigated: D1 contains the original raw images affected by Rician noise and D2 consists of the same images pre-processed for noise removal. Results: The investigation was based on structural similarity assessment by using the Structural Similarity Index (SSIM) and a modified Jaccard metrics. A novel S-Jaccard (Skeleton Jaccard) metric was proposed. Cluster accuracy was estimated based on the Silhouette method (SV). The Silhouette coefficient (SC) indicates the quality of the clustering process for the SSIM and S-Jaccard. To assess the overall classification accuracy an ROC curve implementation was carried out. Conclusions: Consistent results were obtained for healthy patients and for PD images of glioma. We demonstrated that the S-Jaccard metric based on skeletal similarity is an efficient tool for an inter-hemisphere brain similarity evaluation. The accuracy of the proposed skeletonization method was smaller for the original images affected by Rician noise (AUC = 0.883 (T2w) and 0.904 (PD)) but increased for denoised images (AUC = 0.951 (T2w) and 0.969 (PD)).

Deep Convolutional Neural Network for Compressive Sensing of Magnetic Resonance Images

2021 ◽  
Author(s):  
Hong Lu ◽  
Xiaofei Zou ◽  
Longlong Liao ◽  
Kenli Li ◽  
Jie Liu
Keyword(s):  
Neural Network ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Compressive Sensing ◽  
Network Architecture ◽  
Structural Similarity ◽  
Magnetic Resonance Images ◽  
Deep Convolutional Neural Network ◽  
Mr Images ◽  
Under Sampling

Compressive Sensing for Magnetic Resonance Imaging (CS-MRI) aims to reconstruct Magnetic Resonance (MR) images from under-sampled raw data. There are two challenges to improve CS-MRI methods, i.e. designing an under-sampling algorithm to achieve optimal sampling, as well as designing fast and small deep neural networks to obtain reconstructed MR images with superior quality. To improve the reconstruction quality of MR images, we propose a novel deep convolutional neural network architecture for CS-MRI named MRCSNet. The MRCSNet consists of three sub-networks, a compressive sensing sampling sub-network, an initial reconstruction sub-network, and a refined reconstruction sub-network. Experimental results demonstrate that MRCSNet generates high-quality reconstructed MR images at various under-sampling ratios, and also meets the requirements of real-time CS-MRI applications. Compared to state-of-the-art CS-MRI approaches, MRCSNet offers a significant improvement in reconstruction accuracies, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). Besides, it reduces the reconstruction error evaluated by the Normalized Root-Mean-Square Error (NRMSE). The source codes are available at https://github.com/TaihuLight/MRCSNet .

Implementation and Performance Assessment of Biomedical Image Compression and Reconstruction Algorithms for Telemedicine Applications

2019 ◽  
pp. 52-80
Author(s):  
Charu Bhardwaj ◽  
Urvashi Sharma ◽  
Shruti Jain ◽  
Meenakshi Sood
Keyword(s):  
Compressive Sensing ◽  
Performance Metrics ◽  
Matching Pursuit ◽  
Similarity Index ◽  
Structural Similarity ◽  
Least Square ◽  
Reconstruction Method ◽  
Reconstruction Algorithms ◽  
Biomedical Image ◽  
And Performance

Compression serves as a significant feature for efficient storage and transmission of medical, satellite, and natural images. Transmission speed is a key challenge in transmitting a large amount of data especially for magnetic resonance imaging and computed tomography scan images. Compressive sensing is an optimization-based option to acquire sparse signal using sub-Nyquist criteria exploiting only the signal of interest. This chapter explores compressive sensing for correct sensing, acquisition, and reconstruction of clinical images. In this chapter, distinctive overall performance metrics like peak signal to noise ratio, root mean square error, structural similarity index, compression ratio, etc. are assessed for medical image evaluation by utilizing best three reconstruction algorithms: basic pursuit, least square, and orthogonal matching pursuit. Basic pursuit establishes a well-renowned reconstruction method among the examined recovery techniques. At distinct measurement samples, on increasing the number of measurement samples, PSNR increases significantly and RMSE decreases.

scholarly journals Compressed-Sensing Magnetic Resonance Image Reconstruction Using an Iterative Convolutional Neural Network Approach

2020 ◽  
Vol 10 (6) ◽  
pp. 1902
Author(s):  
Fumio Hashimoto ◽  
Kibo Ote ◽  
Takenori Oida ◽  
Atsushi Teramoto ◽  
Yasuomi Ouchi
Keyword(s):  
Magnetic Resonance ◽  
Image Quality ◽  
Compressed Sensing ◽  
Signal To Noise Ratio ◽  
A Priori ◽  
Similarity Index ◽  
Structural Similarity ◽  
Neural Network Approach ◽  
Priori Information ◽  
Space Data

Convolutional neural networks (CNNs) demonstrate excellent performance when employed to reconstruct the images obtained by compressed-sensing magnetic resonance imaging (CS-MRI). Our study aimed to enhance image quality by developing a novel iterative reconstruction approach that utilizes image-based CNNs and k-space correction to preserve original k-space data. In the proposed method, CNNs represent a priori information concerning image spaces. First, the CNNs are trained to map zero-filling images onto corresponding full-sampled images. Then, they recover the zero-filled part of the k-space data. Subsequently, k-space corrections, which involve the replacement of unfilled regions by original k-space data, are implemented to preserve the original k-space data. The above-mentioned processes are used iteratively. The performance of the proposed method was validated using a T2-weighted brain-image dataset, and experiments were conducted with several sampling masks. Finally, the proposed method was compared with other noniterative approaches to demonstrate its effectiveness. The aliasing artifacts in the reconstructed images obtained using the proposed approach were reduced compared to those using other state-of-the-art techniques. In addition, the quantitative results obtained in the form of the peak signal-to-noise ratio and structural similarity index demonstrated the effectiveness of the proposed method. The proposed CS-MRI method enhanced MR image quality with high-throughput examinations.

Sign in / Sign up

Export Citation Format

Share Document