计算机科学 ›› 2019, Vol. 46 ›› Issue (1): 36-44.doi: 10.11896/j.issn.1002-137X.2019.01.006

• 综述 • 上一篇    下一篇

基于压缩感知的心脏磁共振快速成像的应用现状与发展趋势

衡阳1, 陈峰2, 徐剑峰3, 汤敏1,4,5   

  1. (南通大学电子信息学院 江苏 南通226007)1
    (南通大学电气工程学院 江苏 南通226007)2
    (南通大学附属医院医学影像科 江苏 南通226007)3
    (通科微电子学院 江苏 南通226007)4
    (南通大学-南通智能信息技术联合研究中心 江苏 南通226007)5
  • 收稿日期:2018-03-09 出版日期:2019-01-15 发布日期:2019-02-25
  • 作者简介:衡 阳(1993-),男,硕士生,主要研究方向为医学图像处理;陈 峰(1977-),男,博士,副教授,硕士生导师,主要研究方向为机器人及智能信息处理;徐剑峰(1970-),女,硕士,副教授,主要研究方向为MRI疾病诊断;汤 敏(1977-),女,博士,副教授,硕士生导师,主要研究方向为医学图像处理,E-mail:tangmnt@163.com(通信作者)。
  • 基金资助:
    国家自然科学基金项目(81371663),江苏省自然科学基金项目(BK20151273),江苏高校品牌专业建设工程资助项目(PPZY2015B135)资助

Application Status and Development Trends of Cardiac Magnetic Resonance Fast Imaging Based on Compressed Sensing Theory

HENG Yang1, CHEN Feng2, XU Jian-feng3, TANG Min1,4,5   

  1. (School of Electronics and Information Engineering,Nantong University,Nantong,Jiangsu 226007,China)1
    (School of Electrical Engineering,Nantong University,Nantong,Jiangsu 226007,China)2
    (Department of Medical Imaging,Affiliated Hospital of Nantong University,Nantong,Jiangsu 226007,China)3
    (Tongke School of Microelectronics,Nantong,Jiangsu 226007,China)4
    (Nantong University-Nantong Joint Research Center for Intelligent Information Technology,Nantong,Jiangsu 226007,China)5
  • Received:2018-03-09 Online:2019-01-15 Published:2019-02-25

摘要: 为了改善心脏磁共振成像(Cardiac Magnetic Resonance,CMR)在实际应用中成像时间长且存在运动伪影等不足,将压缩感知理论(Compressed Sensing,CS)引入其中,充分利用K空间信息冗余的特性,实现由部分K空间数据重构心脏组织影像,在减少伪影、保证精度的同时加快成像速度。结合近3年的国内外文献,首先对CMR现状、常用序列和技术以及采样模式、压缩感知理论框架分别进行阐述;其次对CMR的最新成果及应用现状进行综述和概括;然后介绍压缩感知图像重构的相关定量评价指标,给出作者在CS-CMR图像重构方面的研究进展;最后总结当前研究中的不足,并展望未来的发展方向。

关键词: 心脏磁共振成像, 压缩感知, 快速成像

Abstract: Cardiac Magnetic Resonance (CMR) has several shortcomings in practical application,such as slow imaging speed and inevitable artifacts.Compressed Sensing (CS) is applied to CMR to make full use of the redundancy of K space information,and the images are reconstructed from partial K space data to reduce artifacts and ensure image accuracy.This paper summarized a review according to the domestic and foreign literatures published in recent three years.Firstly,this paper described the current situation of CMR,the commonly used sequences,sampling mask and the compressed sensing theory,respectively.Then,it provided the latest fruits and applications of CMR with an introduction to objective quantitative indices and research progress of the authors in the CS-CMR field.Finally,it concluded the shortcomings of current researches and analyzed the further research trends.

Key words: Cardiac magnetic resonance, Compressed sensing, Fast imaging techniques

中图分类号: 

  • TP391
[1]LI S T,WEI D.A Survey on Compressive Sensing [J].Acta Automatica Sinica,2009,35(11):1369-1377.(in Chinese)<br /> 李树涛,魏丹.压缩传感综述[J].自动化学报,2009,35(11):1369-1377.<br /> [2]YIN H P,LIU Z D,CHAI Y,et al.Survey of Compressed Sensing [J].Control & Decision,2013,28(10):1441-1445.(in Chinese)<br /> 尹宏鹏,刘兆栋,柴毅,等.压缩感知综述[J].控制与决策,2013,28(10):1441-1445.<br /> [3]JIAO P F,LI L,ZHAO J.New Advances of Compressed Sensing in Medical Image Reconstruction [J].CT Theory and Applications,2012,21(1):133-147.(in Chinese)<br /> 焦鹏飞,李亮,赵骥.压缩感知在医学图像重建中的最新进展[J].CT理论与应用研究,2012,21(1):133-147.<br /> [4]GEETHANATH S,REDDY R,KONAR A S,et al.Compressed Sensing MRI:a review [J].Critical Reviews<sup>TM</sup> in Biomedical Engineering,2013,41(3):213-235.<br /> [5]DONOHO D.Compressed Sensing [J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.<br /> [6]LUSTIG M,DONOHO D,PAULY J M.Sparse MRI:the Application of Compressed Sensing for Rapid MR Imaging [J].Magnetic Resonance in Medicine,2007,58(6):l182-1195.<br /> [7]TANG Y,YAMASHITA Y,NAMIMOTO T,et al.Characterization of Focal Liver Lesions with Half-fourier Acquisition Single-Shot Turbo-Spin-Echo (HASTE) and Inversion Recovery(IR)-HASTE Sequences [J].Journal of Magnetic Resonance Imaging,1998,8(2):438-445.<br /> [8]BIGLAND J D,RADJENOVIC A,RIDGWAY J P.Cardiovascular Magnetic Resonance Physics for Clinicians:Part II [J].Journal of Cardiovascular Magnetic Resonance,2012,20(14):66.<br /> [9]COELHO-FILHO O R,RICKERS C,KWONG R Y,et al.Myocardial Perfusion Imaging [J].Radiology,2013,266(3):701-715.<br /> [10]GOMORI J M,HOLLAND G A,GROSSMAN R I,et al.Fat Suppression by Section-select Gradient Reversal on Spin-Echo MR Imaging,Work in progress [J].Radiology,1988,168(2):493-495.<br /> [11]WINKELMANN S,SCHAEFFTER T,KOEHLER T,et al.An Optimal Radial Profile Order Based on the Golden Ratio for Time-Resolved MRI [J].IEEE Transactions on Medical Imaging,2007,26(1):68-76.<br /> [12]WANG J.Coil Compression for Accelerated Imaging with Radial Acquisition [D].Hangzhou:Zhejiang University,2016.(in Chinese)<br /> 王晶.磁共振线圈通道压缩算法在径向快速采集中的应用[D].杭州:浙江大学,2016.<br /> [13]WUNDRAK S,PAUL J,ULRICI J,et al.A Small Surrogate for the Golden Angle in Time-Resolved Radial MRI Based on Ge-neralized Fibonacci Sequences [J].IEEE Transactions on Medical Imaging,2015,34(6):1262-1269.<br /> [14]WUNDRAK S,PAUL J,ULRICI J,et al.Golden Ratio Sparse MRI Using Tiny Golden Angles [J].Magnetic Resonance in Medicine,2016,75(6):2372-2378.<br /> [15]DONOHO D.For Most Large Underdetermined Systems of Linear Equations,the Minimal L1-norm Solution is Also the Sparsest Solution [J].Communications on Pure and Applied Mathematics,2006,59(6):797-829.<br /> [16]CANDES E,TAO T.Decoding by Linear Programming [J].IEEE Transactions on Information Theory,2005,51(12):4203-4215.<br /> [17]BARANIUK R G.Compressive Sensing [J].IEEE Signal Processing Magazine,2007,24(4):118-121.<br /> [18]XU Z Q.Compressed Sensing:A Survey [J].Science China:Math,2012,42(9):865-877.(in Chinese)<br /> 许志强.压缩感知[J].中国科学:数学,2012,42(9):865-877.<br /> [19]SHAO W Z,WEI Z H.Advances and Perspectives on Compressed Sensing Theory [J].Journal of Image & Graphics,2012,17(1):4-15.(in Chinese)<br /> 邵文泽,韦志辉.压缩感知基本理论:回顾与展望[J].中国图像图形学报,2012,17(1):4-15.<br /> [20]FANG H,YANG H R.Greedy Algorithms and Compressed Sensing [J].Acta Automatica Sinica,2011,37(12):1413-1421.(in Chinese)<br /> 方红,杨海蓉.贪婪算法与压缩感知理论[J].自动化学报,201l,37(12):1413-l421.<br /> [21]LI S,MA C W,LI Y,et al.Survey on Reconstruction Algorithm Based on Compressive Sensing [J].Infrared & Laser Enginee-ring,2013,42(s1):225-232.(in Chinese)<br /> 李珅,马彩文,李艳,等.压缩感知重构算法综述[J].红外与激光工程,2013,42(s1):225-232.<br /> [22]SUN L H,YANG Z.Compressed Sensing of Noisy Speech Signal Based on Adaptive Basis Pursuit De-noising [J].Journal of Nanjing University of Posts & Telecommunications,2011,31(5):l-6.(in Chinese)<br /> 孙林慧,杨震.基于自适应基追踪去噪的含噪语音压缩感知[J].南京邮电大学学报(自然科学版),201l,31(5):1-6.<br /> [23]LV C L.Rapid Dynamic Magnetic Resonance Imaging Based on Compressed Sensing [D].Jinan:Shandong University,2012.(in Chinese)<br /> 吕成林.基于压缩感知的快速动态磁共振成像[D].济南:山东大学,2012.<br /> [24]ZAMANI J,MOGHADDAM A N,RAD H S.Compressed Sensing Cardiac MRI Exploiting Spatio-Temporal Sparsity [J].Journal of Cardiovascular Magnetic Resonance,2013,15(1):1-3.<br /> [25]USMAN M,ATKINSON D,ODILLE F,et al.Motion Corrected Compressed Sensing for Free-breathing Dynamic Cardiac MRI [J].Magnetic Resonance in Medicine,2013,70(2):504-516.<br /> [26]OTAZO R,LI F,CHANDARANA H,et al.Combination of Compressed Sensing and Parallel Imaging for Highly-Accele-rated Dynamic MRI[C]//International Symposium onBiomedi-cal Imaging.Barcelona:IEEE Press,2012:980-983.<br /> [27]OTAZO R,KIM D L,SODICKSON D K.Combination of Compressed Sensing and Parallel Imaging for Highly Accelerated First-pass Cardiac Perfusion MRI [J].Magnetic Resonance in Medicine,2010,64(3):767-776.<br /> [28]CHEN Z W.Real Time Cardiac Magnetic Resonance Imaging Based on Compressed Sensing [D].Shenyang:North Eastern University,2015.(in Chinese)<br /> 陈兆文.基于压缩感知的心脏实时磁共振成像[D].沈阳:东北大学,2015.<br /> [29]ZHANG H,HU L W,WANG Q,et al.Application of Radial K-pace Acquisition in Fetal Cardiac MRI [J].Chinese Journal of Medical Physics,2016,33(6):580-583.(in Chinese)<br /> 张弘,胡立伟,王谦,等.径向K空间采样技术在胎儿心脏磁共振成像中的应用[J].中国医学物理学杂志,2016,33(6):580-583.<br /> [30]KIDO T,NAKAMURA M,WATANABE K,et al.Compressed Sensing Real-time Cine Cardiovascular Magnetic Resonance:Accurate Assessment of Left Ventricular Function in A Single-Breath-Hold [J].Journal of Cardiovascular Magnetic Resonance,2016,18(1):50.<br /> [31]OTAZO R,CANDES E,SODICKSON D K.Low-rank and Sparse Matrix Decomposition for Accelerated Dynamic MRI with Separation of Background and Dynamic Components [J].Magnetic Resonance in Medicine,2015,73(3):1125-1136.<br /> [32]ROOHI S F,ZONOOBI D,KASSIM A A,et al.Dynamic MRI Reconstruction Using Low Rank plus Sparse Tensor Decomposition[C]//International Conference on Image Processing.Phoenix:IEEE Press,2016:1769-1773.<br /> [33]ROOHI S F,ZONOOBI D,KASSIM A A,et al.Multi-dimensional Low Rank plus Sparse Decomposition for Reconstruction of Under-Sampled Dynamic MRI [J].Pattern Recognition,2017(63):667-679.<br /> [34]CHEN C W,ZHU J.Compressed Sensing Image Reconstruction Based on Low-rank and Sparse Prior [J].Applications Research of Computers,2017,34(3):949-952.(in Chinese)<br /> 陈长伟,朱俊.基于低秩和稀疏性先验知识的压缩感知图像重构[J].计算机应用研究,2017,34(3):949-952.<br /> [35]CHEN S J,YANG X M,LV X S.Fast Dynamic MRI Reconstruction Based on Separation via Sparse Pluse Low-rank Prior [J].Applications Research of Computers,2016,33(10):3196-3200.(in Chinese)<br /> 陈思吉,杨晓梅,吕雪霜.基于稀疏和低秩先验分离的快速动态MRI重建[J].计算机应用研究,2016,33(10):3196-3200.<br /> [36]FRANK O,LUSTIG M.Beyond Low Rank+Sparse:Multiscale Low Rank Matrix Decomposition [J].IEEE Journal of Selected Topics in Signal Processing,2016,10(4):672-687.<br /> [37]NAKARMI U,WANG Y H,LYU J Y,et al.A Kernel-based Low-rank (KLR) Model for Low-dimensional Manifold Reco-very in Highly Accelerated Dynamic MRI [J].IEEE Transactions on Medical Imaging,2017,36(11):2297-2307.<br /> [38]LEVINEE,STEVENSK,BEAULIEU C,et al.Accelerated Three-Dimensional Multispectral MRI with Robust Principal Component Analysis for Separation of On- and Off-Resonance Signals [J].Magnetic Resonance in Medicine,2018,79(3):1495-1505.<br /> [39]VALVANO G,MARTINI N,HUBER A,et al.Accelerating 4D Flow MRI by Exploiting Low-Rank Matrix Structure and Ha-damard Sparsity [J].Magnetic Resonance in Medicine,2017,78(4):1330-1341.<br /> [40]LUGAUER F,NICKEL D,WETZL J,et al.Accelerating Multi-Echo Water-Fat MRI with a Joint Locally Low-Rank and Spatial Sparsity-Promoting Reconstruction [J].Magnetic Resonance Materials in Physics,Biology and Medicine,2017,30(2):189-202.<br /> [41]RAVISHANKAR S,MOORE B,NADAKUDITI R,et al.Low-rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging [J].IEEE Transactions on Medical Imaging,2017,36(5):1116-1128.<br /> [42]CHEN J B,LIU S Y,HUANG M.Low-Rank and Sparse Decomposition Model for Accelerating Dynamic MRI Reconstruction [J].Journal of Healthcare Engineering,2017(12):1-9.<br /> [43]LIU S J,CAO J X,LIU H Q,et al.MRI Reconstruction Using a Joint Constraint in Patch-Based Total Variational Framework [J].Journal of Visual Communication and Image Representation,2017,46:150-164.<br /> [44]LIU R W,SHI L,YU S C,et al.Reconstruction of Undersampled Big Dynamic MRI Data Using Non-Convex Low-Rank and Sparsity Constraints [J].Sensors,2017,17(3):509.<br /> [45]CAO P,ZHU X C,TANG S Y,et al.Shuffled Magnetization-Prepared Multicontrast Rapid Gradient-Echo Imaging [J].Magnetic Resonance in Medicine,2018,79(1):62-70.<br /> [46]LIU Q G,WANG S S,LIANG D.Sparse and Dense Hybrid Representation via Subspace Modeling for Dynamic MRI [J].Computerized Medical Imaging and Graphics,2017,56:24-37.<br /> [47]ZHANG X,XIE G,FENG X,et al.Accelerating PS Model-Based Dynamic Cardiac MRI using Compressed Sensing [J].Magnetic Resonance Imaging,2016,34(2):81-90.<br /> [48]TOLOUEE A,ALIREZAIE J,BABYN P.Motion Compensated Data Decomposition Algorithm to Accelerate Dynamic Cardiac MRI [J].Magnetic Resonance Materials in Physics,Biology and Medicine,2017,30(1):1-15.<br /> [49]TOLOUEE A,ALIREZAIE J,BABYN P.Nonrigid Motion Compensation in Compressed Sensing Reconstruction of Cardiac Cine MRI [J].Magnetic Resonance Imaging,2018,46:114-120.<br /> [50]SCHLEMPER J,CABALLERO J,HAJNAL J V,et al.A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction [C]//Information Processing in Medical Imaging.Honolulu,USA,2017:647-658.<br /> [51]WANG S,SU Z,YING L,et al.Accelerating Magnetic Resonance Imaging via Deep Learning[C]//International Symposium on Biomedical Imaging.Prague,Czech Republic:IEEE Press,2016:514-517.<br /> [52]DAR S,CUKUR T.A Transfer-Learning Approach for Acceler-ated MRI using Deep Neural Networks[J].arXiv:1710.02615.<br /> [53]LEE D,YOO J,YE J C.Deep Residual Learning for Compressed Sensing MRI[C]//International Symposium on Biomedical Imaging.Melbourne,Australia:IEEE Press,2017:15-18.<br /> [54]SCHLEMPER J,CABALLERO J,HAJNAL J V,et al.A Deep Cascade of Convolutional Neural Networks for Dynamic MR Ima-ge Reconstruction [J].IEEE Transactions on Medical Imaging,2017,37(2):491-503.<br /> [55]CHEN Q,SCHLEMPER J,CABALLERO J,et al.Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction[J].arXiv:1712.01751.<br /> [56]SHITRIT O,RAVIV T R.Accelerated Magnetic Resonance Imaging by Adversarial Neural Network[M]//Cardoso M,et al.,eds.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Cham:Springer,2017:30-38.<br /> [57]QUAN T M,NGUYENDUC T,JEONG W K.Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks[J].arXiv:1709.00753v1.<br /> [58]YANG G,YU S,DONG H,et al.DAGAN:Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction [J].IEEE Transactions on Medical Imaging,2018,pp(99):1.<br /> [59]YU S M,DONG H,YANG G,et al.Deep De-Aliasing for Fast Compressive Sensing MRI[J].arXiv:1705.07137.<br /> [60]MARDANI M,GONG E,JOSEPH Y,et al.Deep Generative Adversarial Networks for Compressed Sensing (GANCS) Automates MRI[J].arXiv:1706.00051.<br /> [61]YANG Y,SUN Y,LI H,et al.Deep ADMM-net for Compressive Sensing MRI[C]//Advances in Neural Information Processing Systems.Barcelona,Spain:MIT Press,2016:10-18.<br /> [62]YANG Y,SUN Y,LI H,et al.A Deep Learning Approach for Compressive Sensing MRI[C]//Advances in Neural Information Processing Systems.Barcelona,Spain:MIT Press,2016:10-18.<br /> [63]CHANG M H,KIM H P,LEE S M,et al.Deep Learning for Undersampled MRI Reconstruction[J].arXiv:1709.02576.<br /> [64]HAMMERNIK K,KLATZER T,KOBLER E,et al.Learning a Variational Network for Reconstruction of Accelerated MRI Data[J].arXiv:1704.00447.
[1] 蒋敏, 孟志青, 沈瑞. 压缩感知问题的目标罚函数交替随机搜索方法[J]. 计算机科学, 2019, 46(6A): 133-137.
[2] 宋晓祥, 郭艳, 李宁, 王萌. 基于压缩感知的时间序列缺失数据预测算法[J]. 计算机科学, 2019, 46(6): 35-40.
[3] 李秀琴, 王天荆, 白光伟, 沈航. 基于压缩感知的两阶段多目标定位算法[J]. 计算机科学, 2019, 46(5): 50-56.
[4] 吴健, 孙保明. 无线传感器网络中基于字典优化的压缩感知定位方法[J]. 计算机科学, 2019, 46(4): 118-122.
[5] 王鹏飞, 张杭. 欠定条件下基于主成分的亚采样信号重构[J]. 计算机科学, 2019, 46(10): 103-108.
[6] 杜秀丽, 胡兴, 陈波, 邱少明. 基于加权非局部相似性的视频压缩感知多假设重构算法[J]. 计算机科学, 2019, 46(1): 291-296.
[7] 杨思星, 郭艳, 李宁, 孙保明, 钱鹏. 基于数据融合的压缩感知多目标定位算法[J]. 计算机科学, 2018, 45(9): 161-165.
[8] 杜秀丽, 张薇, 顾斌斌, 陈波, 邱少明. 基于灰度共生矩阵的图像自适应分块压缩感知方法[J]. 计算机科学, 2018, 45(8): 277-282.
[9] 郭艳,杨思星,李宁,孙保明,钱鹏. 非基于测距的压缩感知多测量向量目标定位[J]. 计算机科学, 2018, 45(7): 99-103.
[10] 王福驰,赵志刚,刘馨月,吕慧显,王国栋,解昊. 一种改进的稀疏度自适应匹配追踪算法[J]. 计算机科学, 2018, 45(6A): 234-238.
[11] 杜秀丽,顾斌斌,胡兴,邱少明,陈波. 用于图像重构的基于行间支撑集相似度的CoSaMP算法[J]. 计算机科学, 2018, 45(4): 306-311.
[12] 蔡体健,樊晓平,陈志杰,廖志芳. 非共享多测量向量的稀疏表示分类模型[J]. 计算机科学, 2018, 45(3): 258-262.
[13] 黄志清, 李梦佳, 田锐, 张严心, 王伟东. 基于车联网的数据动态压缩采集策略[J]. 计算机科学, 2018, 45(11): 304-311.
[14] 杨思星,郭艳,刘杰,孙保明. 基于动态格点的压缩感知目标计数和定位算法[J]. 计算机科学, 2018, 45(1): 223-227.
[15] 刘馨月,赵志刚,吕慧显,王福驰,解昊. 双阈值正交匹配追踪算法[J]. 计算机科学, 2017, 44(Z6): 212-215, 228.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 编辑部. 新网站开通,欢迎大家订阅![J]. 计算机科学, 2018, 1(1): 1 .
[2] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75, 88 .
[3] 夏庆勋,庄毅. 一种基于局部性原理的远程验证机制[J]. 计算机科学, 2018, 45(4): 148 -151, 162 .
[4] 厉柏伸,李领治,孙涌,朱艳琴. 基于伪梯度提升决策树的内网防御算法[J]. 计算机科学, 2018, 45(4): 157 -162 .
[5] 王欢,张云峰,张艳. 一种基于CFDs规则的修复序列快速判定方法[J]. 计算机科学, 2018, 45(3): 311 -316 .
[6] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[7] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[8] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[9] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[10] 钟菲,杨斌. 基于主成分分析网络的车牌检测方法[J]. 计算机科学, 2018, 45(3): 268 -273 .