计算机应用 ›› 2012, Vol. 32 ›› Issue (02): 541-544.DOI: 10.3724/SP.J.1087.2012.00541

• 图形图像技术 • 上一篇    下一篇

基于压缩感知的自适应正则化磁共振图像重构

李青,杨晓梅,李红   

  1. 四川大学 电气信息学院,成都 610065
  • 收稿日期:2011-07-28 修回日期:2011-09-27 发布日期:2012-02-23 出版日期:2012-02-01
  • 通讯作者: 李青
  • 作者简介:李青(1987-),女,河北泊头人,硕士研究生,主要研究方向:医学图像压缩感知重构;
    杨晓梅(1973-),女,四川乐山人,副教授,主要研究方向:医学图像处理、模式识别;
    李红(1986-),女,四川眉山人,硕士研究生,主要研究方向:压缩感知图像重构。

Compressed sensing-adaptive regularization for reconstruction of magnetic resonance image

LI Qing,YANG Xiao-mei,LI Hong   

  1. School of Electrical Engineering and Information, Sichuan University, Chengdu Sichuan 610065,China
  • Received:2011-07-28 Revised:2011-09-27 Online:2012-02-23 Published:2012-02-01
  • Contact: LI Qing

摘要: 当前基于压缩传感理论的正则化磁共振(CS-MR)图像重构算法普遍采用全局正则化参数,不能很好地在保持边缘和平滑噪声方面做出平衡。为此,提出一种自适应的正则化CS-MRI重构算法。结合图像稀疏性和其局部光滑性的先验知识,采用非线性共轭梯度下降算法求取最优化问题,并在迭代过程中自适应地改变局部正则化参数。新的正则化参数可以更好地恢复图像边缘,并且有利于平滑噪声,使代价函数在定义域内具有凸性;同时先验信息包含于正则化参数中,以提高图像的高频成分。实验结果表明该算法能有效权衡恢复图像边缘和平滑噪声两者的关系。

关键词: 磁共振成像, 压缩感知, 自适应正则化, 稀疏性, 非线性重构

Abstract: The current Magnetic Resonance (MR) image reconstruction algorithms based on compressed sensing (CS-MR) commonly use global regularization parameter, which results in the inferior reconstruction that cannot restore the image edges and smooth the noise at the same time. In order to solve this problem, based on adaptive regularization and compressed sensing, the reconstruction method that used the sparse priors and the local smooth priors of MR image in combination was proposed. Nonlinear conjugate gradient method was used for solving the optimized procedure, and the local regularization parameter was adaptively changed during the iterative process. The regularization parameter can recover the image's edge and simultaneously smooth the noise, making cost function convex within the definition region. The prior information is involved in the regularization parameter to improve the high frequency components of the image. Finally, the experimental results show that the proposed method can effectively restore the image edges and smooth the noise.

Key words: Magnetic Resonance Imaging (MRI), compressed sensing, adaptive regularization, sparsity, nonlinear reconstruction

中图分类号: