Abstract
Background: Magnetic Resonance Imaging (MRI) plays an important role in the field of medical diagnostic imaging as it poses non-invasive acquisition and high soft-tissue contrast. However, a huge time is needed for the MRI scanning process that results in motion artifacts, degrades image quality, misinterprets the data, and may cause discomfort to the patient. Thus, the main goal of MRI research is to accelerate data acquisition processing without affecting the quality of the image.
Introduction: This paper presents a survey based on distinct conventional MRI reconstruction methodologies. In addition, a novel MRI reconstruction strategy is proposed based on weighted Compressive Sensing (CS), Penalty-aided minimization function, and Meta-heuristic optimization technique.
Methods: An illustrative analysis is done concerning adapted methods, datasets used, execution tools, performance measures, and values of evaluation metrics. Moreover, the issues of existing methods and the research gaps considering conventional MRI reconstruction schemes are elaborated to obtain improved contribution for devising significant MRI reconstruction techniques.
Results: The proposed method will reduce conventional aliasing artifact problems, may attain lower Mean Square Error (MSE), higher Peak Signal-to-Noise Ratio (PSNR), and Structural SIMilarity (SSIM) index.
Conclusion: The issues of existing methods and the research gaps considering conventional MRI reconstruction schemes are elaborated to devising an improved significant MRI reconstruction technique.
Keywords: Magnetic resonance imaging, reconstruction, compressive sensing, penalty-aided minimization function, meta- heuristic optimization.
Graphical Abstract
[1]
Schlemper J, Caballero J, Hajnal JV, Price AN, Rueckert D. A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging 2018; 37(2): 491-503.
[http://dx.doi.org/10.1109/TMI.2017.2760978] [PMID: 29035212]
[http://dx.doi.org/10.1109/TMI.2017.2760978] [PMID: 29035212]
[2]
Göçeri E, Ünlü MZ, Dicle O. A comparative performance evaluation of various approaches for liver segmentation from SPIR images. Turk J Electr Eng Co 2015; 23(3): 741-68.
[http://dx.doi.org/10.3906/elk-1304-36]
[http://dx.doi.org/10.3906/elk-1304-36]
[3]
Goceri E, Songul C. Biomedical information technology: Image based computer aided diagnosis systems. Proceeding of International Conference on Advanced Technologies. Antalya.. 2018 p. 132.
[4]
Goceri E, Unlu MZ, Guzelis C, Dicle O. An automatic level set based liver segmentation from MRI data sets. Proceeding of 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA). Istanbul, Turkey. 2012.
[http://dx.doi.org/10.1109/IPTA.2012.6469551]
[http://dx.doi.org/10.1109/IPTA.2012.6469551]
[5]
Goceri N, Goceri E. A neural network based kidney segmentation from MR images. Proceeding of IEEE 14th International Conference on Machine Learning and Applications (ICMLA). Miami, FL, USA. 2015; pp. 1195-8.
[6]
Göçeri E. A comparative evaluation for liver segmentation from SPIR images and a novel level set method using signed pressure force function 2013.
[7]
Goceri E. Automatic labeling of portal and hepatic veins from MR images prior to liver transplantation. Int J CARS 2016; 11(12): 2153-61.
[http://dx.doi.org/10.1007/s11548-016-1446-8] [PMID: 27338273]
[http://dx.doi.org/10.1007/s11548-016-1446-8] [PMID: 27338273]
[8]
Goceri E, Martinez E. Artificial neural network based abdominal organ segmentations: a review. proceeding of IEEE 14th International Conference on Machine Learning and Applications (ICMLA). Miami, FL, USA. 2015; pp. 1191-4.
[9]
Goceri E. Intensity normalization in brain MR images using spatially varying distribution matching. proceeding of Conferences Computer Graphics. Lisbon. Visualization, Computer Vision and Image Processing 2017; pp. 300-4.
[10]
Goceri E, Songül C. Computer-based segmentation, change detection and quantification for lesions in multiple sclerosis. proceeding of International Conference on Computer Science and Engineering (UBMK). Antalya, Turkey. 2017; pp. 177-82.
[http://dx.doi.org/10.1109/UBMK.2017.8093371]
[http://dx.doi.org/10.1109/UBMK.2017.8093371]
[11]
Goceri E, Songul C. Automated detection and extraction of skull from MR head images: preliminary results. Proceeding of 2nd International Conference on Computer Science and Engineering (UBMK'17). Antalya. 2017; pp. 171-6.
[12]
Goceri E. Automated measurement of changes in cortical thickness from MR images. Proceeding of 7th International Conference on Applied Analysis and Mathematical Modeling. Istanbul, Turkey. 2018; p. 78.
[13]
Goceri E. Fully Automated and Adaptive Intensity Normalization Using Statistical Features for Brain MR Images Celal Bayar University. J Sci 2018; 14(1): 125-34.
[14]
Huang J, Zhang S, Metaxas D. Efficient MR image reconstruction for compressed MR imaging. Med Image Anal 2011; 15(5): 670-9.
[http://dx.doi.org/10.1016/j.media.2011.06.001] [PMID: 21742542]
[http://dx.doi.org/10.1016/j.media.2011.06.001] [PMID: 21742542]
[15]
Aviles-Rivero AI, Williams G, Graves MJ, Schonlieb CB. Compressed sensing plus motion (CS+ M): a new perspective for improving undersampled MR image reconstruction. arXiv preprint 2018.
[16]
Zhou B, Yang YF, Xie WS. A novel model and ADMM algorithm for MR image reconstruction. Math Probl Eng 2018; 2018: Article ID 5490458.
[http://dx.doi.org/10.1155/2018/5490458]
[http://dx.doi.org/10.1155/2018/5490458]
[17]
Majumdar A, Ward RK. Exploiting rank deficiency and transform domain sparsity for MR image reconstruction. Magn Reson Imaging 2012; 30(1): 9-18.
[http://dx.doi.org/10.1016/j.mri.2011.07.021] [PMID: 21937179]
[http://dx.doi.org/10.1016/j.mri.2011.07.021] [PMID: 21937179]
[18]
Ikram S, Zubair S, Shah JA, Qureshi IM, Wahid A, Enhancing MR. Image Reconstruction Using Block Dictionary Learning. IEEE Access 2019.
[http://dx.doi.org/10.1109/ACCESS.2019.2949917]
[http://dx.doi.org/10.1109/ACCESS.2019.2949917]
[19]
Sun L, Fan Z, Fu X, Huang Y, Ding X, Paisley J. Ding X and Paisley J. A deep information sharing network for multi-contrast compressed sensing MRI reconstruction. IEEE Trans Image Process 2019; 28(12): 6141-53.
[http://dx.doi.org/10.1109/TIP.2019.2925288] [PMID: 31295112]
[http://dx.doi.org/10.1109/TIP.2019.2925288] [PMID: 31295112]
[20]
Yang G, Yu S, Dong H, et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging 2018; 37(6): 1310-21.
[http://dx.doi.org/10.1109/TMI.2017.2785879] [PMID: 29870361]
[http://dx.doi.org/10.1109/TMI.2017.2785879] [PMID: 29870361]
[21]
Manimala MVR, Naidu CD, Prasad MG. Dictionary Learning-Based MR Image Reconstruction in the Presence of Speckle Noise: Greedy Versus Convex. Soft Computing and Signal Processing 2019; 537-46.
[22]
Bao L, Ye F, Cai C, et al. Undersampled MR image reconstruction using an enhanced recursive residual network. J Magn Reson 2019; 305: 232-46.
[http://dx.doi.org/10.1016/j.jmr.2019.07.020] [PMID: 31323504]
[http://dx.doi.org/10.1016/j.jmr.2019.07.020] [PMID: 31323504]
[23]
Liu S, Cao J, Liu H, Zhou X, Zhang K, Li Z. MRI reconstruction via enhanced group sparsity and nonconvex regularization. Neurocomputing 2018; 272: 108-21.
[http://dx.doi.org/10.1016/j.neucom.2017.06.062]
[http://dx.doi.org/10.1016/j.neucom.2017.06.062]
[24]
Kaldate A, Patre BM, Harsh R, Verma D. MR image reconstruction based on compressed sensing using Poisson sampling pattern. Proceedings of Second International Conference on Cognitive Computing and Information Processing (CCIP). 2016; 1-4.
[http://dx.doi.org/10.1109/CCIP.2016.7802884]
[http://dx.doi.org/10.1109/CCIP.2016.7802884]
[25]
Quan TM, Nguyen-Duc T, Jeong WK. Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss. IEEE Trans Med Imaging 2018; 37(6): 1488-97.
[http://dx.doi.org/10.1109/TMI.2018.2820120] [PMID: 29870376]
[http://dx.doi.org/10.1109/TMI.2018.2820120] [PMID: 29870376]
[26]
Schlemper J, Duan J, Ouyang C, et al. Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction. arXiv preprint 2019.
[27]
Liu S, Cao J, Liu H, Tan X, Zhou X. Group sparsity with orthogonal dictionary and nonconvex regularization for exact MRI reconstruction. Inf Sci 2018; 451: 161-79.
[http://dx.doi.org/10.1016/j.ins.2018.03.064]
[http://dx.doi.org/10.1016/j.ins.2018.03.064]
[28]
Sun L, Fan Z, Ding X, Huang Y, Paisley J. Region-of-interest undersampled MRI reconstruction: A deep convolutional neural network approach. Magn Reson Imaging 2019; 63: 185-92.
[http://dx.doi.org/10.1016/j.mri.2019.07.010] [PMID: 31352015]
[http://dx.doi.org/10.1016/j.mri.2019.07.010] [PMID: 31352015]
[29]
Zhuang P, Zhu X, Ding X. MRI reconstruction with an edge-preserving filtering prior. Signal Processing 2019; 155: 346-57.
[http://dx.doi.org/10.1016/j.sigpro.2018.10.005]
[http://dx.doi.org/10.1016/j.sigpro.2018.10.005]
[30]
Cao J, Liu S, Liu H, Tan X, Zhou X. Sparse representation of classified patches for CS-MRI reconstruction. Neurocomputing 2019; 339: 255-69.
[http://dx.doi.org/10.1016/j.neucom.2019.01.107]
[http://dx.doi.org/10.1016/j.neucom.2019.01.107]
[31]
Zhang D, He J, Zhao Y, Du M. MR image super-resolution reconstruction using sparse representation, nonlocal similarity and sparse derivative prior. Comput Biol Med 2015; 58: 130-45.
[http://dx.doi.org/10.1016/j.compbiomed.2014.12.023] [PMID: 25638262]
[http://dx.doi.org/10.1016/j.compbiomed.2014.12.023] [PMID: 25638262]
[32]
Elahi S, Kaleem M, Omer H. Compressively sampled MR image reconstruction using generalized thresholding iterative algorithm. J Magn Reson 2018; 286: 91-8.
[http://dx.doi.org/10.1016/j.jmr.2017.11.008] [PMID: 29223565]
[http://dx.doi.org/10.1016/j.jmr.2017.11.008] [PMID: 29223565]
[33]
Zhan Z, Cai JF, Guo D, Liu Y, Chen Z, Qu X. Fast multiclass dictionaries learning with geometrical directions in MRI reconstruction. IEEE T Bio-Med Eng 2015; 63(9): 1850-61.
[34]
Joy A, Paul JS. Multichannel compressed sensing MR image reconstruction using statistically optimized nonlinear diffusion. Magn Reson Med 2017; 78(2): 754-62.
[http://dx.doi.org/10.1002/mrm.26774] [PMID: 28593635]
[http://dx.doi.org/10.1002/mrm.26774] [PMID: 28593635]
[35]
Lu T, Zhang X, Huang Y, et al. pISTA-SENSE-ResNet for Parallel MRI Reconstruction. arXiv preprint 2019.
[36]
Qu X, Hou Y, Lam F, Guo D, Zhong J, Chen Z. Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator. Med Image Anal 2014; 18(6): 843-56.
[http://dx.doi.org/10.1016/j.media.2013.09.007] [PMID: 24176973]
[http://dx.doi.org/10.1016/j.media.2013.09.007] [PMID: 24176973]
[37]
Ma S, Du H, Mei W. A two-step low rank matrices approach for constrained MR image reconstruction. Magn Reson Imaging 2019; 60: 20-31.
[http://dx.doi.org/10.1016/j.mri.2019.03.019] [PMID: 30930307]
[http://dx.doi.org/10.1016/j.mri.2019.03.019] [PMID: 30930307]
[38]
Jin J, Du H, Qiu B, Xu J. Constrained higher degree total p-variation minimization for MRI reconstruction from undersampled K-Space data. Curr Med Imaging Rev 2018; 14(6): 995-1005.
[http://dx.doi.org/10.2174/1573405614666180425124008]
[http://dx.doi.org/10.2174/1573405614666180425124008]
[39]
Xue H, Inati S, Sørensen TS, Kellman P, Hansen MS. Distributed MRI reconstruction using Gadgetron-based cloud computing. Magn Reson Med 2015; 73(3): 1015-25.
[http://dx.doi.org/10.1002/mrm.25213] [PMID: 24687458]
[http://dx.doi.org/10.1002/mrm.25213] [PMID: 24687458]
[40]
Feng L, Axel L, Chandarana H, Block KT, Sodickson DK, Otazo R. XD-GRASP: Golden-angle radial MRI with reconstruction of extra motion-state dimensions using compressed sensing. Magn Reson Med 2016; 75(2): 775-88.
[http://dx.doi.org/10.1002/mrm.25665] [PMID: 25809847]
[http://dx.doi.org/10.1002/mrm.25665] [PMID: 25809847]
[41]
Küstner T, Würslin C, Gatidis S, et al. MR image reconstruction using a combination of compressed sensing and partial Fourier acquisition: ESPReSSo. IEEE Trans Med Imaging 2016; 35(11): 2447-58.
[http://dx.doi.org/10.1109/TMI.2016.2577642] [PMID: 27295659]
[http://dx.doi.org/10.1109/TMI.2016.2577642] [PMID: 27295659]
[42]
Majumdar A, Ward RK. An algorithm for sparse MRI reconstruction by Schatten p-norm minimization. Magn Reson Imaging 2011; 29(3): 408-17.
[http://dx.doi.org/10.1016/j.mri.2010.09.001] [PMID: 20952139]
[http://dx.doi.org/10.1016/j.mri.2010.09.001] [PMID: 20952139]
[43]
Johnson KM, Block WF, Reeder SB, Samsonov A. Improved least squares MR image reconstruction using estimates of k-space data consistency. Magn Reson Med 2012; 67(6): 1600-8.
[http://dx.doi.org/10.1002/mrm.23144] [PMID: 22135155]
[http://dx.doi.org/10.1002/mrm.23144] [PMID: 22135155]
[44]
Majumdar A. Improving synthesis and analysis prior blind compressed sensing with low-rank constraints for dynamic MRI reconstruction. Magn Reson Imaging 2015; 33(1): 174-9.
[http://dx.doi.org/10.1016/j.mri.2014.08.031] [PMID: 25179137]
[http://dx.doi.org/10.1016/j.mri.2014.08.031] [PMID: 25179137]
[45]
He N, Wang R, Wang Y. Dynamic MRI reconstruction exploiting blind compressed sensing combined transform learning regularization. Neurocomputing 2020; 392: 160-7.
[46]
Murad M, Bilal M, Jalil A, Ali A, Mehmood K, Khan B. Efficient reconstruction technique for multi-slice CS-MRI using novel interpolation and 2D sampling scheme. IEEE Access 2020; 8: 117452-66.
[http://dx.doi.org/10.1109/ACCESS.2020.3004731]
[http://dx.doi.org/10.1109/ACCESS.2020.3004731]
[47]
Bustin A, Lima da Cruz G, Jaubert O, Lopez K, Botnar RM, Prieto C. High-dimensionality undersampled patch-based reconstruction (HD-PROST) for accelerated multi-contrast MRI. Magn Reson Med 2019; 81(6): 3705-19.
[http://dx.doi.org/10.1002/mrm.27694] [PMID: 30834594]
[http://dx.doi.org/10.1002/mrm.27694] [PMID: 30834594]
[48]
Lønning K, Putzky P, Sonke JJ, Reneman L, Caan MWA, Welling M. Recurrent inference machines for reconstructing heterogeneous MRI data. Med Image Anal 2019; 53: 64-78.
[http://dx.doi.org/10.1016/j.media.2019.01.005] [PMID: 30703579]
[http://dx.doi.org/10.1016/j.media.2019.01.005] [PMID: 30703579]
[49]
Deka B, Datta S, Handique S. Wavelet tree support detection for compressed sensing MRI reconstruction. IEEE Signal Proc Let ters 2018; 25(5): 730-4.
[http://dx.doi.org/10.1109/LSP.2018.2824251]
[http://dx.doi.org/10.1109/LSP.2018.2824251]
[50]
Tezcan KC, Baumgartner CF, Luechinger R, Pruessmann KP, Konukoglu E. MR image reconstruction using deep density priors. IEEE T Med Imaging. 2018: 1-9.
[51]
Ghodrati V, Shao J, Bydder M, et al. MR image reconstruction using deep learning: evaluation of network structure and loss functions. Quant Imaging Med Surg 2019; 9(9): 1516-27.
[http://dx.doi.org/10.21037/qims.2019.08.10] [PMID: 31667138]
[http://dx.doi.org/10.21037/qims.2019.08.10] [PMID: 31667138]
[52]
Falvo A, Comminiello D, Scardapane S, Finesi G, Scarpiniti M, Uncini A. A Multimodal Deep Network for the Reconstruction of T2W MR Images. arXiv preprint 2019.
[53]
Dedmari MA, Conjeti S, Estrada S, Ehses P, Stöcker T, Reuter M. Complex Fully Convolutional Neural Networks for MR Image Reconstruction. Workshop on Machine Learning for Medical Image Reconstruction. 30-8.
[http://dx.doi.org/10.1007/978-3-030-00129-2_4]
[http://dx.doi.org/10.1007/978-3-030-00129-2_4]
[54]
Wu Y, Ma Y, Capaldi DP, et al. Incorporating prior knowledge via volumetric deep residual network to optimize the reconstruction of sparsely sampled MRI. Magn Reson Imaging 2020; 66: 93-103.
[PMID: 30880112]
[PMID: 30880112]
[55]
Küstner T, Fuin N, Hammernik K, et al. CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions. Sci Rep 2020; 10(1): 13710.
[http://dx.doi.org/10.1038/s41598-020-70551-8] [PMID: 32792507]
[http://dx.doi.org/10.1038/s41598-020-70551-8] [PMID: 32792507]
[56]
Xu Z, Li Y, Axel L, Huang J. Efficient preconditioning in joint total variation regularized parallel MRI reconstruction. proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. 563-70.
[http://dx.doi.org/10.1007/978-3-319-24571-3_67]
[http://dx.doi.org/10.1007/978-3-319-24571-3_67]
[57]
Sadiq MU, Simmons JP, Bouman CA. Model based image reconstruction with physics based priors. proceedings of IEEE Image Proc 2016; 3176-9.
[58]
Xu Z, Wang S, Li Y, Zhu F, Huang J. Prim: An efficient preconditioning iterative reweighted least squares method for parallel brain mri reconstruction. Neuroinformatics 2018; 16(3-4): 425-30.
[http://dx.doi.org/10.1007/s12021-017-9354-9] [PMID: 29423650]
[http://dx.doi.org/10.1007/s12021-017-9354-9] [PMID: 29423650]
[59]
Hammernik K, Klatzer T, Kobler E, et al. Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 2018; 79(6): 3055-71.
[http://dx.doi.org/10.1002/mrm.26977] [PMID: 29115689]
[http://dx.doi.org/10.1002/mrm.26977] [PMID: 29115689]
[60]
Yang X, Xu W, Luo R, Zheng X, Liu K. Robustly reconstructing magnetic resonance images via structure decomposition. Magn Reson Imaging 2019; 57: 165-75.
[http://dx.doi.org/10.1016/j.mri.2018.11.020] [PMID: 30500348]
[http://dx.doi.org/10.1016/j.mri.2018.11.020] [PMID: 30500348]
[61]
Lyu J, Nakarmi U, Liang D, Sheng J, Ying L, Ker NL. KerNL: Kernel-based nonlinear approach to parallel MRI reconstruction. IEEE Trans Med Imaging 2019; 38(1): 312-21.
[http://dx.doi.org/10.1109/TMI.2018.2864197] [PMID: 30106676]
[http://dx.doi.org/10.1109/TMI.2018.2864197] [PMID: 30106676]
[62]
Eksioglu EM. Decoupled algorithm for MRI reconstruction using nonlocal block matching model: BM3D-MRI. J Math Imaging Vis 2016; 56(3): 430-40.
[http://dx.doi.org/10.1007/s10851-016-0647-7]
[http://dx.doi.org/10.1007/s10851-016-0647-7]
[63]
Ravishankar S, Bresler Y. MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans Med Imaging 2011; 30(5): 1028-41.
[http://dx.doi.org/10.1109/TMI.2010.2090538] [PMID: 21047708]
[http://dx.doi.org/10.1109/TMI.2010.2090538] [PMID: 21047708]
[64]
Weller DS, Ramani S, Fessler JA. Augmented Lagrangian with variable splitting for faster non-Cartesian L1-SPIRiT MR image reconstruction. IEEE Trans Med Imaging 2014; 33(2): 351-61.
[http://dx.doi.org/10.1109/TMI.2013.2285046] [PMID: 24122551]
[http://dx.doi.org/10.1109/TMI.2013.2285046] [PMID: 24122551]
[65]
Ye X, Chen Y, Lin W, Huang F. Fast MR image reconstruction for partially parallel imaging with arbitrary k-space trajectories. IEEE Trans Med Imaging 2011; 30(3): 575-85.
[http://dx.doi.org/10.1109/TMI.2010.2088133] [PMID: 21356608]
[http://dx.doi.org/10.1109/TMI.2010.2088133] [PMID: 21356608]
Article Metrics
29
1