浏览全部资源
扫码关注微信
收稿：2017-06-08，
修回：2017-10-17，
纸质出版：2018-02-16
移动端阅览
目的
2
快速成像一直是磁共振成像（MRI）技术中的焦点之一，现有多通道并行成像和部分k空间数据重建都是通过减少梯度编码步数来降低数据的获取时间，两者结合起来更能有效地提高扫描速度。然而，在欠采样倍数加高的情况下，依然有很严重的混叠伪影，因此研究一种在保证成像精度的前提下加快成像速度的方法尤为重要。
方法
2
基于卷积神经网络的磁共振成像（CNN-MRI）方法利用大量现有的全采样多通道数据的先验信息，设计并线下训练一个深度卷积神经网络，学习待重建图像与全采样图像之间的映射关系，从而在线上成像时，欠采样所丢失数据能被训练好的网络进行预测。本文探讨了对于深度学习磁共振成像的可选择性欠采样方式，提出了一种新的欠采样轨迹方案。为了判断本文方法的性能，用峰值信噪比（PSNR）、结构相似度（SSIM）以及均方根差（RMSE）来作为衡量的指标。
结果
2
实验结果表明，所提出欠采样方案的综合性能要优于传统欠采样轨迹，PSNR要高出1~2 dB，SSIM高出近0.1，RMSE要降低0.02~0.04左右。此外重建结果还与经典的并行重建方法GRAPPA（geneRalized autocalibrating partially parallel acquisitions）、SPIRiT（iterative self-consistent parallel imaging reconstruction from arbitrary k-space）以及SAKE（simultaneous autocalibrating and k-space estimation）作比较，从视觉效果以及各项量化指标得出本文方法能重建出更准确的结果，并且重建速度要快5倍以上。
结论
2
深度学习方法能很好地在线下训练时从大量数据集中提取并学习到有价值的先验信息，所以在线上测试时能在较短时间内重建出优于经典算法的高质量结果；提出的1维低频汉明滤波欠采样方案则有利于提升该网络的性能。
Objective
2
Magnetic resonance imaging (MRI) with non-ionizing and non-radiating nature is capable of providing rich anatomical and functional information and is an indispensable tool for medical diagnosis
disease staging
and clinical research.However
many advanced applications
such as cardiovascular imaging
magnetic resonance (MR) spectroscopy
and functional MRI
have not been widely used in clinical practice given the extended scanning time of MRI. Thus
fast imaging has been constantly one of the emphases in the MRI technology. The existing multi-coil parallel imaging and partial k-space data reconstruction techniques decrease acquisition times by reducing the amount of phase encoding required. The parallel imaging based on utilizing the spatial sensitivity of multiple coils with gradient encoding has been an essential technique for accelerating MRI scan. In addition to exploring the physical properties of multiple coils
an increasing number of researchers have been using signal processing in MR image reconstruction. Specifically
diverse prior information as regularizations is incorporated into the reconstruction equation inside. One of the representative efforts focuses on compressed sensing
which utilizes image sparsity and incoherent undersampling for fast MRI. The benefit of the combination compared with the individual techniques is the significantly increased scanning rate. However
serious aliasing artifacts may still occur in case of a high acceleration factor. Therefore
a means of accelerating the imaging rate while ensuring imaging accuracy should be devised.
Method
2
The wide application of convolutional neural network (CNN) has revealed its powerful capability incorrelation exploration
automatic feature extraction
and nonlinear correlation description. Therefore
we apply CNN to medical MR image reconstruction and design a multi-coil CNN to exploit the local correlation in multi-channel images. The proposed MRI based on the convolutional neural network (CNN-MRI) method utilizes prior knowledge from numerous existing fully-sampled multi-coil data. The proposed method designs and trains an off-line deep CNN to describe the mapping relationship between zero-filled and fully sampled MR images. The trained network is then used for the online prediction of images from the undersampled multi-channel data. The entire research contents include two main parts as follows:off-line training and online imaging. The two important components in the off-line training are the preprocessing of big datasets for training samples and the network design. We directly predict images online with the trained network parameter model in the online imaging. This paper discusses the undersampling methods for MRI based on deep learning. Unlike the popular parallel imaging or compressed sensing technique
which exploits sensitivity and sparsity for fast MRI
CNN-MRI learns the end-to-end mapping between the MR images reconstructed from the undersampled and fully-sampled k-space data from huge offline acquisitions
and then aids in exacting online fast imaging with the learned mapping prior. Therefore
conventional sampling methods may not be the optimal undersampling trajectory for CNN-MRI
in which uniform and incoherent undersampling are required for parallel and compressed sensing MRI
respectively. Furthermore
three 1D undersampling patterns
namely
1D random undersampling with variable density
1D uniform undersampling
and 1D low frequency
have been investigated with the proposed CNN-MRI framework.Specifically
we proposed a new trajectory scheme
namely
hamming filtered asymmetrical 1D partial Fourier sampling. The reconstruction results were quantitatively evaluated in terms of peak signal-to-noise ratio (PSNR)
structural similarity (SSIM)
and root-mean-square error (RMSE) to determine the performance of the proposed scheme.
Result
2
Experimental results show that the proposed undersampling pattern performs better than the traditional sampling trajectory. The PSNR improved by 1 dB to 2 dB
the SSIM ratio improved by approximately 0.1
and the RMSE decreased by approximately 0.02~0.04. In addition
we compared the proposed method to the classical parallel imaging methods
GRAPPA
SPIRiT
and SAKE
at an acceleration factor of 4. GRAPPA
SPIRiT
and SAKE has used their typical uniform undersampling patterns with autocalibration lines and parameter settings. For CNN-MRI
we adopted the hamming filtered 1D low-frequency trajectory
with a shifting distance of 18. For a quantitative comparison
four MRI images were tested with the different methods
which mean index values in PSNR
SSIM
and RMSE are summarized. The images reconstructed through the proposed method were closer to the ground truth image
while aliasing artifacts were observed in the images reconstructed using GRAPPA/SPIRiT/SAKE. The mean PSNR of the proposed method improved by 0.5~4 dB
the mean SSIM ratio improved by 0.15~0.27
and the mean RMSE decreased by approximately 0.01~0.07. Synthetically
the mean quantitative and visual comparisons show that the proposed method produces superior quality with the least time
with a reconstruction rate of faster than five times.
Conclusion
2
Deep learning can learn valuable prior knowledge from big off-line datasets
and then perform high-quality online image reconstruction from undersampled MR data with a low computational cost. The hamming filtered 1D low-frequency undersampling pattern was developed to improve the performance of the proposed CNN. Future work will further optimize the undersampling trajectories
which can also be extended to non-Cartesian sampling design
and include additional big data in the proposed framework to extract further valuable prior information for fast MRI.
Edelman R R, Warach S.Magnetic resonance imaging[J]. New England Journal of Medicine, 1993, 328(10):708-716.[DOI:10.1056/NEJM199303183281109]
Lustig M, Pauly J M. SPIRi T:iterative self-consistent parallel imaging reconstruction from arbitrary k-space[J]. Magnetic Resonance in Medicine, 2010, 64(2):457-471.[DOI:10.1002/mrm.22428]
Knoll F, Clason C, Bredies K, et al. Parallel imaging with nonlinear reconstruction using variational penalties[J]. Magnetic Resonance in Medicine, 2012, 67(1):34-41.[DOI:10.1002/mrm.22964]
Pruessmann K P, Weiger M, Scheidegger M B, et al. SENSE:sensitivity encoding for fast MRI[J]. Magnetic Resonance in Medicine, 1999, 42(5):952-962.[DOI:10.1002/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S]
Sodickson D K, Manning W J.Simultaneous acquisition of spatial harmonics (SMASH):fast imaging with radiofrequency coil arrays[J]. Magnetic Resonance in Medicine, 1997, 38(4):591-603.[DOI:10.1002/mrm.1910380414]
Jakob P M, Grisowld M A, Edelman R R, et al. AUTO-SMASH:a self-calibrating technique for SMASH imaging[J]. Magnetic Resonance Materials in Physics, Biology and Medicine, 1998, 7(1):42-54.[DOI:10.1016/S1352-8661(98)00015-5]
Heidemann R M, Griswold M A, Haase A, et al. VD-AUTO-SMASH imaging[J]. Magnetic Resonance in Medicine, 2001, 45(6):1066-1074.[DOI:10.1002/mrm.1141]
Griswold M A, Jakob P M, Heidemann R M, et al. Generalized autocalibrating partially parallel acquisitions (GRAPPA)[J]. Magnetic Resonance in Medicine, 2002, 47(6):1202-1210.[DOI:10.1002/mrm.10171]
Uecker M, Lai P, Murphy M J, et al. ESPIRiT-an eigenvalue approach to autocalibrating parallel MRI:where SENSE meets GRAPPA[J]. Magnetic Resonance in Medicine, 2014, 71(3):990-1001.[DOI:10.1002/mrm.24751]
Shin P J, Larson P E Z, Ohliger M A, et al. Calibrationless parallel imaging reconstruction based on structured low-rank matrix completion[J]. Magnetic Resonance in Medicine, 2014, 72(4):959-970.[DOI:10.1002/mrm.24997]
Weller D S, Polimeni J R, Grady L, et al. Sparsity-promoting calibration for GRAPPA accelerated parallel MRI reconstruction[J]. IEEE Transactions on Medical Imaging, 2013, 32(7):1325-1335.[DOI:10.1109/TMI.2013.2256923]
Park J, Zhang Q, Jellus V, et al. Artifact and noise suppression in GRAPPA imaging using improved k-space coil calibration and variable density sampling[J]. Magnetic Resonance in Medicine, 2005, 53(1):186-193.[DOI:10.1002/mrm.20328]
Ramani S, Fessler J A. Parallel MR image reconstruction using augmented Lagrangian methods[J]. IEEE Transactions on Medical Imaging, 2011, 30(3):694-706.[DOI:10.1109/TMI.2010.2093536]
Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4)1289-1306.[DOI:10.1109/TIT.2006.871582]
Chari L, Pesquet J C, Benazza-Benyahia A, et al. A wavelet-based regularized reconstruction algorithm for SENSE parallel MRI with applications to neuroimaging[J]. Medical Image Analysis, 2011, 15(2):185-201.[DOI:10.1016/j.media.2010.08.001]
Block K T, Uecker M, Frahm J. Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint[J]. Magnetic Resonance in Medicine, 2007, 57(6):1086-1098.[DOI:10.1002/mrm.21236]
Osher S, Burger M, Goldfarb D, et al. An iterative regularization method for total variation-based image restoration[J]. Multiscale Modeling&Simulation, 2005, 4(2):460-489.[DOI:10.1137/040605412]
Chen C, Li Y Q, Huang J Z. Calibrationlessparallel MRI with joint total variation regularization[C]//Procedings of the16th International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Heidelberg: Springer, 2013: 106-114. [ DOI: 10.1007/978-3-642-40760-4_14 http://dx.doi.org/10.1007/978-3-642-40760-4_14 ]
Liang D, Wang H F, Chang Y C, et al. Sensitivity encoding reconstruction with nonlocal total variation regularization[J]. Magnetic Resonance in Medicine, 2011, 65(5):1384-1392.[DOI:10.1002/mrm.22736]
Weller D. Reconstruction with dictionary learning for accelerated parallel magnetic resonance imaging[C]//IEEE Southwest Symposium on Image Analysis and Interpretation. Santa Fe, NM, USA: IEEE, 2016: 105-108. [ DOI: 10.1109/SSIAI.2016.7459186 http://dx.doi.org/10.1109/SSIAI.2016.7459186 ]
Liang Z P, Madore B, Glover G H, et al. Fast algorithms for GS-model-based image reconstruction in data-sharing Fourier imaging[J]. IEEE Transactions on Medical Imaging, 2003, 22(8):1026-1030.[DOI:10.1109/TMI.2003.815896]
Wu J, Liu F, Jiao L C, et al. Multivariate compressive sensing for image reconstruction in the wavelet domain:using scale mixture models[J]. IEEE Transactions on Image Processing, 2011, 20(12):3483-3494.[DOI:10.1109/TIP.2011.2150231]
Wachinger C, Yigitsoy M, Rijkhorst E J, et al. Manifold learning for image-based breathing gating in ultrasound and MRI[J]. Medical Image Analysis, 2012, 16(4):806-818.[DOI:10.1016/j.media.2011.11.008]
Haldar J P, Zhuo J W. P-LORAKS:low-rankmodeling of local k-space neighborhood swith parallel imaging data[J]. Magnetic Resonance in Medicine, 2016, 75(4):1499-1514.[DOI:10.1002/mrm.25717]
Kim T H, Setsompop K, Haldar J P. LORAKS makes better SENSE:phase-constrained partial fourier SENSE reconstruction without phase calibration[J]. Magnetic Resonance in Medicine, 2017, 77(3):1021-1035.[DOI:10.1002/mrm.26182]
Samsonov A A, Kholmovski E G, Parker D L, et al. POCSENSE:POCS-based reconstruction for sensitivity encoded magnetic resonance imaging[J]. Magnetic Resonance in Medicine, 2004, 52(6):1397-1406.[DOI:10.1002/mrm.20285]
Chang Y C, Liang D, Ying L. Nonlinear GRAPPA:a kernel approach to parallel MRI reconstruction[J]. Magnetic Resonance in Medicine, 2012, 68(3):730-740.[DOI:10.1002/mrm.23279]
Wang S S, Su Z H, Ying L, et al. Accelerating magnetic resonance imaging via deep learning[C]//2016IEEE 13th International Symposium on Biomedical Imaging. Prague, Czech Republic: IEEE, 2016: 514-517. [DOI: 10.1109/ISBI.2016.7493320 http://dx.doi.org/10.1109/ISBI.2016.7493320 ]
Anthimopoulos M, Christodoulidis S, Ebner L, et al. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1207-1216.[DOI:10.1109/TMI.2016.2535865]
Ouyang W L, Wang X G, Zeng X Y, et al. Deepid-net: deformable deep convolutional neural networks for object detection[C]//Proceedings of IEEE Computer Vision and Pattern Recognition. Boston, Massachusetts, USA: IEEE, 2015: 2403-2412.
Dong C, Loy C C, He K M, et al. Learning a deep convolutional network for image super-resolution[C]//Proceedings of the 13th European Conference on Computer Vision-European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 184-199. [ DOI: 10.1007/978-3-319-10593-2_13 http://dx.doi.org/10.1007/978-3-319-10593-2_13 ]
Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.[DOI:10.1109/5.726791]
Krizhevsky A, Sutskever L, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25. Lake Tahoe, Nevada, USA: Curran Associates, Inc., 2012: 1097-1105.
Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, Georgia, USA: International Machine Learning Society, 2013.
He K M, Zhang X Y, Ren S Q, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 1026-1034.
Bengio Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1):1-127.[DOI:10.1561/2200000006]
Jia Y Q, Shelhamer E, Donahue J, et al. Caffe: convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, Florida, USA: ACM, 2014: 675-678. [ DOI: 10.1145/2647868.2654889 http://dx.doi.org/10.1145/2647868.2654889 ]
相关作者
相关机构
京公网安备11010802024621
