用于压缩感知磁共振成像的分割字典学习算法

doi:10.11938/cjmr20160405

波谱学杂志 ›› 2016, Vol. 33 ›› Issue (4): 559-569.doi: 10.11938/cjmr20160405

用于压缩感知磁共振成像的分割字典学习算法

宋阳¹, 谢海滨¹, 杨光^1,2

1. 华东师范大学物理系, 上海市磁共振重点实验室, 上海 200062;
2. 上海卡勒幅磁共振技术有限公司, 上海 201614

收稿日期:2015-12-31 修回日期:2016-10-24 出版日期:2016-12-05 发布日期:2016-12-05
通讯作者: 谢海滨,电话:021-62233873,E-mail:hbxie@phy.ecnu.edu.cn E-mail:hbxie@phy.ecnu.edu.cn
作者简介:宋阳(1991-),男,山东泰安人,硕士研究生,无线电物理专业
基金资助:
国家高技术研究发展计划资助项目（2014AA123400）.

Dictionary Learning with Segmentation for Compressed-Sensing Magnetic Resonance Imaging

SONG Yang¹, XIE Hai-bin¹, YANG Guang^1,2

1. Shanghai Key laboratory of Magnetic Resonance, Department of Physics, East China Normal University, Shanghai 200062, China;
2. Shanghai Colorful Magnetic Resonance Technology Co. Ltd., Shanghai 201614, China

Received:2015-12-31 Revised:2016-10-24 Online:2016-12-05 Published:2016-12-05

摘要/Abstract

摘要： 字典学习算法可以根据数据本身的特点构建稀疏域中的基，从而使数据的表示更加稀疏．该文在传统的字典学习算法基础上提出了分割字典学习算法，由于部分磁共振图像组织结构简单、可以进行图像分割，因此可根据此特点来优化字典中基函数的构建，使磁共振图像的表达更为稀疏，从而获得更高的重建图像质量．该文利用模拟数据和真实数据进行了重建实验，结果表明与传统的字典学习算法相比，分割字典学习算法能进一步改善重建图像质量．

关键词: 磁共振成像(MRI), 压缩感知, 字典学习, 图像分割

Abstract: Dictionary learning (DL) builds a set of basis functions from the input data, such that the data can be represented more sparsely. Based on the fact that certain magnetic resonance (MR) images can be easily segmented, we propose an algorithm named dictionary learning with segmentation (DLS). The algorithm achieves better image reconstruction quality by optimizing construction of the dictionary and to making representation of the MR images sparser though incorporating image segmentation into dictionary learning. The experimental results on simulated datasets and in vivo images demonstrated that the proposed algorithm can yield better reconstruction relative to the traditional dictionary learning algorithm.

Key words: segmentation, compressed sensing, dictionary learning, magnetic resonance imaging(MRI)

中图分类号:

O482.53

宋阳, 谢海滨, 杨光. 用于压缩感知磁共振成像的分割字典学习算法[J]. 波谱学杂志, 2016, 33(4): 559-569.

SONG Yang, XIE Hai-bin, YANG Guang. Dictionary Learning with Segmentation for Compressed-Sensing Magnetic Resonance Imaging[J]. Chinese Journal of Magnetic Resonance, 2016, 33(4): 559-569.

参考文献

[1] Pruessmann K P. Encoding and reconstruction in parallel MRI[J]. NMR Biomed, 2006, 19(3):288-299.
[2] McGibney G, Smith M R, Nichols S T, et al. Quantitative evaluation of several partial Fourier reconstruction algorithms used in MRI[J]. Magn Reson Med, 1993, 30(1):51-59.
[3] Donoho D L. Compressed sensing[J]. IEEE T Inform Theory, 2006, 52(4):1289-1306.
[4] Lustig M, Donoho D, Pauly J M. Sparse MRI:The application of compressed sensing for rapid MR imaging[J]. Magn Reson Med, 2007, 58(6):1182-1195.
[5] Ravishankar S, Bresler Y. MR image reconstruction from highly undersampled k-space data by dictionary learning[J]. IEEE T Med Imaging, 2011, 30(5):1028-1041.
[6] Toši? I, Frossard P. Dictionary learning[J]. IEEE Signal Proc Mag, 2011, 28(2):27-38.
[7] Griswold M A, Jakob P M, Heidemann R M, et al. Generalized autocalibrating partially parallel acquisitions (GRAPPA)[J]. Magn Reson Med, 2002, 47(6):1202-1210.
[8] Pruessmann K P, Weiger M, Scheidegger M B, et al. SENSE:sensitivity encoding for fast MRI[J]. Magn Reson Med, 1999, 42(5):952-962.
[9] Ma S, Yin W, Zhang Y, et al. Computer Vision and Pattern Recognition[C]. Anchorage Alarke:IEEE, 2008.
[10] Qu X B, Zhang W R, Guo D, et al. Iterative thresholding compressed sensing MRI based on contourlet transform[J]. Inverse Prob Sci Eng, 2010, 18(6):737-758.
[11] Zheng Hui(郑慧), Han Ming-yue(韩明月), Hu Bing-wei(胡炳文), et al. Comparison of different sampling schemes in compressed sensing reconstruction for DQ-SQ experiments(不同采样模式的固体DQ-SQ实验的压缩感应重建比较)[J]. Chinese J Magn Reson(波谱学杂志), 2014, 31(4):535-547.
[12] Han Ming-yue(韩明月), Zheng Hui(郑慧), Hu Bing-wei(胡炳文), et al. Compressed sensing reconstruction with iterative soft thresholding for two-dimension solid state NMR spectra with broad peaks(迭代软阈值法压缩感知重建谱峰较宽的二维固体谱)[J]. Chinese J Magn Reson(波谱学杂志), 2015, 32(4):551-562.
[13] Kim Y, Altbach M I, Trouard T P, et al. Compressed sensing using dual-tree complex wavelet transform[C]. Proc ISMRM, 2009.
[14] Aharon M, Elad M, Bruckstein A. K-SVD:An algorithm for designing overcompletedictionaries for sparse representation[J]. IEEE T Signal Process, 2006, 54(11):4311-4322.
[15] Zhan Z F, Cai J F, Guo D, et al. Fast multi-class dictionaries learning with geometrical directions in MRI reconstruction[J]. IEEE T Biomed Eng, DOI:10.1109/TBME.2015.2503756, 2015.
[16] Lai Z Y, Qu X B, Liu Y S, et al. Image reconstruction of compressed sensing MRI using graph-based redundant wavelet transform[J]. Med Imag Anal, 2016, 27:93-104.
[17] Qu X B, Guo D, Ning B D, et al. Undersampled MRI reconstruction with patch-based directional wavelets[J]. Magn Reson Imag, 2012, 30(7):964-977.
[18] Qu X B, Hou Y K, Lam F, et al. Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator[J]. Med Imag Anal, 2014, 18(6):843-856.
[19] Clarke L P, Velthuizen R P, Phuphanich S, et al. MRI:stability of three supervised segmentation techniques[J]. Magn Reson Imag, 1993, 11(1):95-106.
[20] Clarke L P, Velthuizen R P, Camacho M A, et al. MRI segmentation:methods and applications[J]. Magn Reson Imag, 1995, 13(3):343-368.
[21] Singh M, Patel P, Khosla D, et al. Segmentation of functional MRI by K-means clustering[J]. IEEE T Nucl Sci, 1996, 43(3):2030-2036.
[22] Tropp J A. Greed is good:Algorithmic results for sparse approximation[J]. IEEE T Inform Theory, 2004, 50(10):2231-2242.
[23] Hartigan J A, Wong M A. Algorithm AS 136:A k-means clustering algorithm[J]. J Appl Stat, 1979, 28(1):100-108.
[24] Brown R W, Cheng Y C N, Haacke E M, et al. Magnetic resonance imaging:physical principles and sequence design[M]. USA:John Wiley & Sons, 2014.
[25] Cocosco C A, Kollokian V, Kwan R K S, et al. BrainWeb:Online interface to a 3D MRI simulated brain database[J]. NeuroImage, 1997, 5(4):s425.
[26] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE T Image Process, 2004, 13(4):600-612.

用于压缩感知磁共振成像的分割字典学习算法

Dictionary Learning with Segmentation for Compressed-Sensing Magnetic Resonance Imaging

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	魏国境, 易佩伟, 陶泉, 冯衍秋. CEST成像不同量化方式在急性帕金森氏病小鼠模型研究中的应用比较[J]. 波谱学杂志, 2019, 36(2): 195-207.
[2]	黄朝晖, 张志, 陈黎, 陈俊飞, 张震, 陈方, 刘朝阳. MRI梯度预加重模块的分时复用设计[J]. 波谱学杂志, 2018, 35(4): 465-474.
[3]	柴青焕, 苏冠群, 聂生东. 双树小波变换与小波树稀疏联合的低场CS-MRI算法[J]. 波谱学杂志, 2018, 35(4): 486-497.
[4]	刘颖, 宋明辉, 王坤, 章浩伟. 基于全可编程SoC和LabVIEW的磁共振接收系统设计[J]. 波谱学杂志, 2018, 35(4): 475-485.
[5]	汪红志, 赵地, 杨丽琴, 夏天, 周皛月, 苗志英. 基于AI+MRI的影像诊断的样本增广与批量标注方法[J]. 波谱学杂志, 2018, 35(4): 447-456.
[6]	陈海燕, 赵世龙, 李晓南, 刘国强, 胡丽丽, 刘弢. 低场永磁体磁共振射频场映像[J]. 波谱学杂志, 2018, 35(4): 498-504.
[7]	陶泉, 易佩伟, 魏国境, 冯衍秋. 基于CEST机制的pH成像方法、原理和应用[J]. 波谱学杂志, 2018, 35(4): 505-519.
[8]	翟国强, 张苗, 薄斌仕, 王乙, 范明霞, 李建奇. 基于复值和模值的肝脏磁共振水脂分离组合算法[J]. 波谱学杂志, 2018, 35(4): 417-426.
[9]	张波, 谢海滨, 严序, 李文静, 杨光. 旋转不变的非局域均值算法在磁共振图像去噪中的应用[J]. 波谱学杂志, 2018, 35(2): 162-169.
[10]	崔妍, 肖亮. 磁共振成像谱仪B₀信号的高精度发生与测试[J]. 波谱学杂志, 2018, 35(2): 170-177.
[11]	孙炜航, 孙钰, 汪丰, 王超洪, 杨涛. 变延迟进动定制激发(DANTE)序列在工程中的优化设计[J]. 波谱学杂志, 2018, 35(2): 150-161.
[12]	马芸, 郭虹, 王秋实, 张伟国, 吴昊. 基于影像的形态学特征与胶质母细胞瘤特征分子表达的相关性研究[J]. 波谱学杂志, 2018, 35(1): 22-30.
[13]	黄丽洁, 宋阳, 赵献策, 谢海滨, 吴东梅, 杨光. 一种结合并行成像和压缩感知的快速磁共振成像新方法[J]. 波谱学杂志, 2018, 35(1): 31-39.
[14]	罗庆, 张成秀, 李文静, 郑慧, 谢海滨, 杨光. 一种新的磁共振图像处理流水线的设计与实现[J]. 波谱学杂志, 2018, 35(1): 40-51.
[15]	宋瑞, 何砚发, 张波. 一种永磁磁共振中磁体涡流场的测量方法[J]. 波谱学杂志, 2018, 35(1): 52-59.