scholarly journals Improved least squares MR image reconstruction using estimates of k-Space data consistency

2011 ◽  
Vol 67 (6) ◽  
pp. 1600-1608 ◽  
Author(s):  
Kevin M. Johnson ◽  
Walter F. Block ◽  
Scott. B. Reeder ◽  
Alexey Samsonov
Keyword(s):  
Image Reconstruction ◽  
Least Squares ◽  
Data Consistency ◽  
Mr Image ◽  
Space Data ◽  
Mr Image Reconstruction

An Efficient Light-Weight Network for Fast Reconstruction on MR Images

2021 ◽  
Vol 17 ◽  
Author(s):  
Bowen Zhen ◽  
Yingjie Zheng ◽  
Bensheng Qiu
Keyword(s):  
Feature Extraction ◽  
Image Reconstruction ◽  
Data Consistency ◽  
Training Procedure ◽  
Light Weight ◽  
Mr Images ◽  
High Quality ◽  
Mr Image ◽  
Generalization Ability ◽  
Mr Image Reconstruction

Background: In recent years, deep learning (DL) algorithms have emerged in endlessly and achieved impressive performance, which makes it possible to accelerate magnetic resonance (MR) image reconstruction with DL instead of compressed sensing (CS) methods. However, a DL-based MR image reconstruction method has always suffered from its heavy learning parameters and poor generalization ability so far. Therefore, an efficient light-weight network is still in desperate need of fast MR image reconstruction. Methods: We propose an efficient and light-weight MR reconstruction network (named RecNet) that uses a Convolutional Neural Network (CNN) to fast reconstruct high-quality MR images. Specifically, the network is composed of cascade modules, and each cascade module is further divided into feature extraction blocks and a data consistency layer. The feature extraction block can not only effectively extract the features of MR images, but also do not introduce too many parameters for the whole network. To stabilize the training procedure, the correction information of image frequency is adopted in the data consistency (DC) layer. Results: We have evaluated RecNet on a public dataset and the results show that the image quality reconstructed by RecNet is the best on the peak a signal-to-noise ratio (PSNR) and structural similarity index (SSIM) evaluation standards. In addition, the pre-trained RecNet can also reconstruct high-quality MR images on an unseen dataset. Conclusion: The results demonstrate that the RecNet has superior reconstruction ability in various metrics than comparative methods. The RecNet can quickly generate high-quality MR images in fewer parameters. Furthermore, the RecNet has an excellent generalization ability on pathological images and different sampling rates data.

scholarly journals MR Image Reconstruction Based on Iterative Split Bregman Algorithm and Nonlocal Total Variation

2013 ◽  
Vol 2013 ◽  
pp. 1-16 ◽  
Author(s):  
Varun P. Gopi ◽  
P. Palanisamy ◽  
Khan A. Wahid ◽  
Paul Babyn
Keyword(s):  
Image Reconstruction ◽  
Total Variation ◽  
Least Square ◽  
Split Bregman ◽  
Mr Image ◽  
Split Bregman Iteration ◽  
Nonlocal Total Variation ◽  
Comparison Results ◽  
Space Data ◽  
Mr Image Reconstruction

This paper introduces an efficient algorithm for magnetic resonance (MR) image reconstruction. The proposed method minimizes a linear combination of nonlocal total variation and least-square data-fitting term to reconstruct the MR images from undersampledk-space data. The nonlocal total variation is taken as theL1-regularization functional and solved using Split Bregman iteration. The proposed algorithm is compared with previous methods in terms of the reconstruction accuracy and computational complexity. The comparison results demonstrate the superiority of the proposed algorithm for compressed MR image reconstruction.

MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning

2011 ◽  
Vol 30 (5) ◽  
pp. 1028-1041 ◽  
Author(s):  
Saiprasad Ravishankar ◽  
Yoram Bresler
Keyword(s):  
Image Reconstruction ◽  
Dictionary Learning ◽  
Mr Image ◽  
Space Data ◽  
Mr Image Reconstruction

scholarly journals Reference-Driven Compressed Sensing MR Image Reconstruction Using Deep Convolutional Neural Networks without Pre-Training

Sensors ◽  
2020 ◽  
Vol 20 (1) ◽  
pp. 308 ◽  
Author(s):  
Di Zhao ◽  
Feng Zhao ◽  
Yongjin Gan
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Compressed Sensing ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Training Procedure ◽  
Deep Convolutional Neural Networks ◽  
Mr Image ◽  
Space Data ◽  
Mr Image Reconstruction

Deep learning has proven itself to be able to reduce the scanning time of Magnetic Resonance Imaging (MRI) and to improve the image reconstruction quality since it was introduced into Compressed Sensing MRI (CS-MRI). However, the requirement of using large, high-quality, and patient-based datasets for network training procedures is always a challenge in clinical applications. In this paper, we propose a novel deep learning based compressed sensing MR image reconstruction method that does not require any pre-training procedure or training dataset, thereby largely reducing clinician dependence on patient-based datasets. The proposed method is based on the Deep Image Prior (DIP) framework and uses a high-resolution reference MR image as the input of the convolutional neural network in order to induce the structural prior in the learning procedure. This reference-driven strategy improves the efficiency and effect of network learning. We then add the k-space data correction step to enforce the consistency of the k-space data with the measurements, which further improve the image reconstruction accuracy. Experiments on in vivo MR datasets showed that the proposed method can achieve more accurate reconstruction results from undersampled k-space data.

scholarly journals Approximate Sparsity and Nonlocal Total Variation Based Compressive MR Image Reconstruction

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Chengzhi Deng ◽  
Shengqian Wang ◽  
Wei Tian ◽  
Zhaoming Wu ◽  
Saifeng Hu
Keyword(s):  
Image Reconstruction ◽  
Total Variation ◽  
Optimization Problems ◽  
Reconstruction Method ◽  
Mr Image ◽  
Scanning Time ◽  
Reconstruction Methods ◽  
Nonlocal Total Variation ◽  
Space Data ◽  
Mr Image Reconstruction

Recent developments in compressive sensing (CS) show that it is possible to accurately reconstruct the magnetic resonance (MR) image from undersampledk-space data by solving nonsmooth convex optimization problems, which therefore significantly reduce the scanning time. In this paper, we propose a new MR image reconstruction method based on a compound regularization model associated with the nonlocal total variation (NLTV) and the wavelet approximate sparsity. Nonlocal total variation can restore periodic textures and local geometric information better than total variation. The wavelet approximate sparsity achieves more accurate sparse reconstruction than fixed waveletl0andl1norm. Furthermore, a variable splitting and augmented Lagrangian algorithm is presented to solve the proposed minimization problem. Experimental results on MR image reconstruction demonstrate that the proposed method outperforms many existing MR image reconstruction methods both in quantitative and in visual quality assessment.

An Algorithm for the Proximity Operator in Hybrid TV-Wavelet Regularization, with Application to MR Image Reconstruction

2014 ◽  
Vol 4 (1) ◽  
pp. 21-34 ◽  
Author(s):  
Yu-Wen Fang ◽  
Xiao-Mei Huo ◽  
You-Wei Wen
Keyword(s):  
Image Reconstruction ◽  
Optimization Procedure ◽  
Mr Image ◽  
Ringing Artifacts ◽  
Tv Regularization ◽  
Efficiency And Effectiveness ◽  
Wavelet Regularization ◽  
Space Data ◽  
Numerical Difficulty ◽  
Mr Image Reconstruction

AbstractTotal variation (TV) and waveletL1norms have often been used as regularization terms in image restoration and reconstruction problems. However, TV regularization can introduce staircase effects and wavelet regularization some ringing artifacts, but hybrid TV and wavelet regularization can reduce or remove these drawbacks in the reconstructed images. We need to compute the proximal operator of hybrid regularizations, which is generally a sub-problem in the optimization procedure. Both TV and waveletL1regularisers are nonlinear and non-smooth, causing numerical difficulty. We propose a dual iterative approach to solve the minimization problem for hybrid regularizations and also prove the convergence of our proposed method, which we then apply to the problem of MR image reconstruction from highly random under-sampled k-space data. Numerical results show the efficiency and effectiveness of this proposed method.

Bregman Iteration Based Efficient Algorithm for MR Image Reconstruction From Undersampled K-Space Data

2013 ◽  
Vol 20 (8) ◽  
pp. 831-834 ◽  
Author(s):  
Jizhong Duan ◽  
Yu Liu ◽  
Liyi Zhang
Keyword(s):  
Image Reconstruction ◽  
Efficient Algorithm ◽  
Bregman Iteration ◽  
Mr Image ◽  
Space Data ◽  
Mr Image Reconstruction

scholarly journals Dynamic MR Image Reconstruction From Highly Undersampled (k, t)-Space Data Exploiting Low Tensor Train Rank and Sparse Prior

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 28690-28703
Author(s):  
Shuli Ma ◽  
Huiqian Du ◽  
Wenbo Mei
Keyword(s):  
Image Reconstruction ◽  
Mr Image ◽  
Sparse Prior ◽  
Space Data ◽  
Dynamic Mr ◽  
Mr Image Reconstruction

MR image reconstruction of sparsely sampled 3D k-space data by projection-onto-convex sets

2006 ◽  
Vol 24 (6) ◽  
pp. 761-773 ◽  
Author(s):  
Haidong Peng ◽  
Mohammad Sabati ◽  
Louis Lauzon ◽  
Richard Frayne
Keyword(s):  
Image Reconstruction ◽  
Convex Sets ◽  
Mr Image ◽  
Projection Onto Convex Sets ◽  
Space Data ◽  
Mr Image Reconstruction
Sign in / Sign up

Export Citation Format

Share Document