基于小波变换和混合遗传算法的医学图像配准

梁君婷, 董友, 王明泉, 赵月萍, 冯晓夏

梁君婷, 董友, 王明泉, 赵月萍, 冯晓夏. 基于小波变换和混合遗传算法的医学图像配准[J]. 应用光学, 2010, 31(4): 589-592.
引用本文: 梁君婷, 董友, 王明泉, 赵月萍, 冯晓夏. 基于小波变换和混合遗传算法的医学图像配准[J]. 应用光学, 2010, 31(4): 589-592.
LIANG Jun-ting, DONG You, WANG Ming-quan, ZHAO Yue-ping, FENG Xiao-xia. Medical image registration based on wavelet transformand hybrid genetic algorithm[J]. Journal of Applied Optics, 2010, 31(4): 589-592.
Citation: LIANG Jun-ting, DONG You, WANG Ming-quan, ZHAO Yue-ping, FENG Xiao-xia. Medical image registration based on wavelet transformand hybrid genetic algorithm[J]. Journal of Applied Optics, 2010, 31(4): 589-592.

基于小波变换和混合遗传算法的医学图像配准

详细信息
    通讯作者:

    梁君婷(1984-),女,山西太原人,中北大学信息与通信工程学院硕士研究生,主要从事图像采集与处理方面的研究。

  • 中图分类号: TN911.73;TP391

Medical image registration based on wavelet transformand hybrid genetic algorithm

  • 摘要: 为了解决灰度图像配准中由于目标函数容易陷入局部极值而造成的误匹配问题,使参数随图像的NMI计算和多分辨率级数进行自适应调整,采用基于小波变换多分辨率策略,形成多尺度匹配模型,并将粒子群算法(PSO)作为添加算子,提出了以图像归一化互信息(NMI)作为相似性测度的混合遗传算法,对CT与MRI图像进行了配准。实验结果表明,该方法能够解决遗传算法早熟收敛问题,有效地克服信息函数的局部极值,实现图像的自动配准,具有匹配精确、鲁棒性好及效率高等优点。
    Abstract: To address the disadvantages of image registration, a new method for image registration is proposed,which combines hybrid genetic algorithm with wavelet multi-resolution analysis strategy. In this method, mutual information is used as the similarity measure and a hybrid genetic algorithm is used as the search technique, and the parameters of genetic algorithm are adapted along with the computation of mutual information and the multi-resolution of the images. The experimental results show that this registration method could efficiently restrain the local maxima of mutual information function and the subvoxel accuracy can be achieved, which demonstrates that the algorithm is accurate, robust and efficient for image registration.
  • [1]罗述谦,周果宏. 医学图像处理与分析[M].北京:科学出版社,2003.
    LUO Shu-qian,ZHOU Guo-hong. Processing and analysis of medical image[M]. Beijing:Science Publishing House,2003.
    [2]MAES F,COLLIGNON A,VANDERMEULEN D, et al.Multimodality image registration by maxim-ization of mutual information[J]. IEEE Transactions on Medical Imaging,1997,16(2):187-198.
    [3]STONE H S, MOIGNE J L,MCGUIRE M.The translation sensitivity of Waveletbased registration[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999,21(10):1074-1081.
    [4]杨帆,张汗灵.遗传算法和Powell法结合的多分辨率三维图像配准[J].光电子·激光,2006,17(6):755-758.
    YANG Fan, ZHANG Han-ling.Multiresolution3-D image registration using hybrid genetic algorithm and powells method[J]. Journal of Optoelectronics Laser,2006,17(6):755-758.(in Chinese with an English abstract)
    [5]SHI Y, EBERHART R C.A modified particle swarm optimizer[C].Anchorage:IEEE International Conference on Evolutionary Computation.  Alaska, 1998:69-73.
    [6]JENKINSON M, SMITH S.A global optimization method for robust affine registration of brain images[J]. Medical Image Analysis,2001,5(2):143-156.
计量
  • 文章访问数:  2871
  • HTML全文浏览量:  121
  • PDF下载量:  817
  • 被引次数: 0
出版历程
  • 刊出日期:  2010-07-14

目录

    /

    返回文章
    返回