《计算机应用研究》|Application Research of Computers

基于多层P样条和稀疏编码的非刚性医学图像配准方法

Non-rigid medical image registration method based on multilayer P-spline and sparse coding

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王丽芳,成茜,秦品乐,高媛
机构 中北大学 大数据学院,太原 030051
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)08-2557-04
DOI 10.3969/j.issn.1001-3695.2018.08.079
摘要 针对传统相似性测度易受灰度偏移场的影响而造成误配,以及单层P样条变换模型中通常无法准确选择初始化网格密度的问题,提出了多层P样条和稀疏编码的非刚性医学图像配准方法。该方法将稀疏编码作为相似性测度,首先把待配准的两幅图像划分图像块,然后使用K-SVD算法训练图像块得到分析字典并寻找稀疏系数,采用多层P样条自由变换模型来模拟非刚性几何形变,结合梯度下降法优化目标函数。实验结果表明,与单层P样条几何变换和sparse-induced、rank-induced相似性测度相比,所提方法能够准确地选择网格密度,并有效克服灰度偏移场对配准的影响,降低了均方根误差,提高了配准的精度和鲁棒性。
关键词 图像配准;稀疏编码;多层P样条;梯度下降法
基金项目 山西省自然科学基金资助项目(2015011045)
本文URL http://www.arocmag.com/article/01-2018-08-079.html
英文标题 Non-rigid medical image registration method based on multilayer P-spline and sparse coding
作者英文名 Wang Lifang, Cheng Xi, Qin Pinle, Gao Yuan
机构英文名 SchoolofDataScience&Technology,NorthUniversityofChina,Taiyuan030051,China
英文摘要 This paper proposed the non-rigid medical image registration method of multilayer P-spline and sparse coding according to two problems, the first one is the mismatch because the traditional similarity measure is easily affected by the gray bias field and the second problem is that single-layer P-spline transformation model is unable to accurately select the initialized grid density.This method regarded sparse coding as the similarity measure, at first, it divided two registered images into image blocks.And then used K-SVD algorithm to train them and thus obtain analysis dictionary.In addition, it found the sparse coefficients and used multilayer P-spline free transform model to simulate the non-rigid geometrical deformation.At last, it combined with the gradient descent method to optimize the objective function.Experimental results show that compared with the single-layer P-spline geometric transformation, sparse-induced and rank-induced similarity measure, the proposed method can accurately select the grid density and effectively overcome the influence of the gray bias field on the registration, reduces the root mean square error and improves the accuracy and robustness of registration.
英文关键词 image registration; sparse coding; multilayer P-spline; gradient descent method
参考文献 查看稿件参考文献
  [1] Francisco P M, Manuel J O, Tavares R S. Medical image registration:a review[J] . Computer Methods in Biomechanics and Biomedical Engineering, 2014, 17(2):73-93.
[2] Bhattacharya M, Das A. Multimodality medical image registration and fusion techniques using mutual information and genetic algorithm-based approaches[J] . Software Tools and Algorithms for Biological Systems, 2011, 696(3):441-449.
[3] 田捷, 代晓倩, 杨飞. 医学成像与医学图像处理教程[M] . 北京:清华大学出版社, 2013:187-189.
[4] Marx B D. Statistical modelling and regression structure:P-spline varying coefficient models for complex data[M] . Berlin:Springer-Verlag, 2010:19-43.
[5] Pradhan S, Patra D. RMI based non-rigid image registration using BF-QPSO optimization and P-spline[J] . International Journal of Electronics and Communications, 2015, 69(3):609-621.
[6] 汪军, 梁凤梅. 基于P样条和局部互信息的非刚性医学图像配准[J] . 计算机应用研究, 2017, 34(8):2538-2541.
[7] Myronenko A, Song Xubo. Intensity-based image registration by minimization of residual complexity[J] . IEEE Trans on Medical Imaging, 2010, 29(11):1882-1891.
[8] 卢振泰, 张娟, 冯前进, 等. 基于局部方差与残差复杂性的医学图像配准[J] . 计算机学报, 2015, 38(12):2400-2411.
[9] Ghaffari A, Fatemizadeh E. Sparse-induced similarity measure:mono-modal image registration via sparse-induced similarity measure[J] . IET Image Processing, 2014, 8(12):728-741.
[10] Ghaffari A, Fatemizadeh E. RISM:single-modal image registration via rank-induced similarity measure[J] . IEEE Trans on Image Processing, 2015, 24(12):5567-5580.
收稿日期 2017/3/14
修回日期 2017/4/27
页码 2557-2560
中图分类号 TP391.41
文献标志码 A