医学图像增强和配准相似性测度的若干研究

详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文

英文题名：Research on Medical Image Enhancement and Registration Similarity Measures 作者：陈北京 论文级别：硕士 学科专业名称：应用数学 中文关键词：医学图像配准 ; 一阶互信息 ; 二阶互信息 ; 局部极值 ; 多分辨率 英文关键词：medical image registration ; first-order mutual information ; second-order mutual information ; local maxima ; multi-resolution 学位年度：2006 导师：董光昌 学科代码：070104 学位授予单位：浙江大学 论文提交日期：2006-05-01

摘要

医学影像己成为现代医学的一个重要组成部分,而医学图像处理主要是对已获得的图像进行加工、处理,便于临床诊断。本文主要讨论了两类医学图像处理技术:基础的医学图像对比度增强技术和当前研究热点的医学图像配准技术。 基于灰度变换的医学图像对比度增强技术,是一种简单却比较有效的对比度增强法。在对常见的灰度变换概述之后,针对当前一些算法存在的图像对比度增强和边缘细节保持之间的矛盾,我们提出了两种新的MR图像对比度增强算法:基于阈值分割和3次B样条插值的MR增强算法,首先定义了基于对比度和细节的新的质量评价参数,然后利用Otsu阈值算法选取的多个阈值寻求该质量评价参数最佳的三次B样条插值变换,得到理想的增强效果;基于分割和累积指数变换的MR增强算法,先采用多阈值分割将图像分割为不同的区域,然后统计出各区域的灰度均值和方差,并由它们构造出各区域的累积指数非线性变换作用于各区域进行增强。实验表明,这两种算法都能比较好的解决对比度增强和边缘细节保持两方面的冲突,而且速度也不亚于一些传统的算法。 基于灰度的图像配准技术以其较高的精度、不需要预处理而能实现自动配准被广泛采用。而相似性测度是决定配准准确性、鲁棒性和实时性的最主要因素,因此在介绍完配准技术及其涉及的相关技术后,针对一阶互信息的鲁棒性不强的问题进行了相关分析,并介绍了几种互信息的改进测度,其中特别针对二阶互信息进行了重点讨论,分析了灰阶、相关信息和噪声对其影响,得到了二阶互信息的最佳参数取值,然后分析了分辨率对一阶和二阶互信息的影响,改进了二级分辨率策略的配准技术,在分辨率不同的各个级上采用不同的相似性测度。实验表明,相比采用单一测度的算法,多测度结合的算法在配准精度和速度两方面都能得到更为理想的效果。
Medical image has been an important part of modern medical sciences. And, medical image processing focuses on image post-processing in order to improve image quality and facilitate clinical diagnosis. In this thesis, we discuss two classes of technologies on medical image processing, including the basic contrast enhancement technology and registration under intense research.Medical image contrast enhancement based on gray transformation is a simple but effective technology. After the survey of some usual gray transformation, we present two new algorithms for MR, which try to cope with the contradiction between contrast enhancement and edge detail preserving for some traditional algorithms. One is MR image enhancement algorithm based on threshold segmentation and B-Spline interpolation. We first define a new assessment criterion based on luminance contrast and detail, then search the best cubic B-Spline interpolation transformation for ideal enhancement effect by some threhold values chosen by Otsu threshold algorithm. The other is MR image enhancement algorithm based on image segmentation and accumulating index transformation. This method divides the whole image into different regions using multilevel segmentation. For every region, the mean and variance of gray value are calculated to contract the accumulating index transformation for enhancement. Experimental results show that our algorithms can solve the contradition referred above effectively without much speed cost.Voxel intensity based medical image registration has been widely used for its high precision and automatism with no pre-processing. Similarity measure is the most important factor for determining the accuracy, robustness and real-time property of registration. After the description of the registration technology and its related ones, we analyze the robustness of mutual information(MI) and introduce some improved similarity measures of MI. Especially, we discuss the effects of gray level, neighborhood relationship and noise on the second-order information and get its best parameters. Then, after studying the effects of resolution on first-order and second- order information, we improve the multi-resolution registration approach by adopting different similarity measure for different resolution. Experiment results verify that, compared with single measure, multimeasure registration is more perfect not only in precision but also in speed.

引文

[1] 章毓晋.图像处理和分析[M].北京:清华大学出版社,1999:72-100. [2] J. Alex Stark. Adaptive image contrast enhancement using generalizations of histogram equalization[J]. IEEE Transactions on Image Processing, 2000, 9(5): 889-896. [3] S.M. Pizer, E. P. Ambum, J. D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. T. H. Romeny, J. B. Zimmerman and K. Zuiderveld. Adaptive histogram equalization and its variation[J]. Computer Vision Graphics and Image Processing (CVGIP), 1987, 39(3): 355-368. [4] 张利平,黄廉卿.基于局部直方图重分布的医学图像增强方法[J].光电子·激光,2004,15(7):877-880. [5] R. Wallis. An approach to the space variant restoration and enhancement of images[C]. In: Proc. of Symposium Current Mathematical Problems in Image Science, Navel Postgraduate School, Monterey, USA, 1976: 329-340. [6] 李宏贵,李兴国,张奇,李国桢,罗正发.非线性滤波器在红外图像增强中的应用[J].数据采集与处理,1999,14(3):302-306. [7] D.C. Chang, W. R. Wu. Image contrast enhancement based on a histogram transformation of local standard deviation[J]. IEEE Transactions on Medical Imaging, 1998,17(4): 518-531. [8] K. R. Bhutanim, A. Battou. An application of fuzzy relation to image enhancement[J]. Pattern Recognition Letters, 1995,16(10): 901-909. [9] Y.S. Choi, R. Krishnapuram. A robust approach to image enhancement based on fuzzy logic[J]. IEEE Transaction on Image Processing, 1997, 6(6): 808-824. [10] H.D. Cheng, Y. H. Chen and Y. Sun.A novel fuzzy entropy approach to image enhancement and thresholding[J]. Signal Processing, 1999, 75(3): 279-301. [11] 张弘,庄天戈.一种用于胸部CT的改进模糊图像增强算法[J].上海交通大学学报,2002,36(7):1026-1028. [12] 董汉丽.基于小波变换的图像增强方法研究[J].郑州纺织工学院学报,1999,10(3):40-43. [13] 吴颖谦,施鹏飞.基于小波变换的低对比度图像增强[J].红外与激光工程,2003,32(1):4-7. [14] J. B. A. Maintz, M. A. Viergever. A survey of medical image registration[J]. Medical Image Analysis, 1998, 2(1): 1-36. [15] J. P. W. Pluim, J. B. A. Maintz, and M. A. Viergever, Mutual-information-based registration of medical Images: A Survey[J]. IEEE Transactions on Medical Imaging, 2003, 22(8): 986-1004. [16] J. V. Hajnal, D. L. G. Hill, and D. J. Hawkes. Medical Image Registration[M]. New York: CRC Press LLC, 2001. [17] M. A. Viergever, Image Guidance of Therapy[J]. IEEE Transactions on Medical Imaging, 1998, 17(5):669-671. [18] T. Peters, B. Davey, P. Munger, et al. Three-Dimensional multimodal image-guidance for Neurosurgery [J]. IEEE Transactions on Medical Imaging, 1996,15(2): 121-128. [19] W. E. L Grimson, G. J. Ettinger, S. J. White, et al. An automatic registration method for frameless stereotaxy, image guided surgery, and enhanced reality visualization[J]. IEEE Transactions on Medical Imaging, 1996, 15(2): 129-140. [20] 吕维雪,段会龙.三维医学图像可视化及其应用[M].杭州:浙江大学出版社,2001. [21] http://www.vuse.vanderbilt.edu/～image/registration/. [22] 罗述谦,周果宏.医学图象处理与分析[M].北京:科学出版社,2003. [23] M. Holden, D. L G. Hill, E. R. E. Eenton, et al. Voxel similarity measures for 3-D serial MR brain image registration[J]. IEEE Transactions on Medical Imaging, 2000,19(2): 94-102. [24] Darko Skerl, Bostjan Likar and Franjo Permus. Evaluation of nine similarity measures used in rigid registration[C]. In: J. Kittler, editors, Proceedings of 17th International Conference on Pattern Recognition (ICPR), Cambridge, UK, 2004:794-797. [25] S. Gao, Y. Xiao and S. H. Hu. A comparison of two similarity measures in intensity-based ultrasound image registration[C]. In: Proceedings of IEEE. International Symposium on Circuits and Systems, 2004(4): 61-64. [26] 李弼程,彭天强,彭波,等.智能图像处理技术[M].北京:电子工业出版社,2004. [27] A. Roche, G. Malandain, N. Ayache, et al. The correlation ratio as a new similarity Measure for multi-modal image registration[C]. In: MICCAI98, MIT, USA, Springer Verlag Press, 1998, 1496:1125-1124. [28] R. P. Woods, J. C. Mazziotta and S. R. Cherry. MRI-PET registration with automated algorithm[J]. Journal of Computer Assisted Tomography, 1993,17(4): 536-546. [29] P. A. Van den Elsen, J. B. A. Maintz, E. J. D. Pol and M. A. Viergever. Automatic registration of CT and MR brain images using correlation of geometrical features[J]. IEEE Transactions on Medical Imaging, 1995, 14(2): 384-396. [30] 沈晋慧.遗传算法在医学图像配准技术中的应用[J].首都医科大学学报,2003,24(1):30-32. [31] 付宇光,唐焕文,计明军,钟明军,唐一源.模拟退火算法在图像配准中的应用[J].中国生物医学工程学报.2004,23(5):405-409. [32] 江军,於文雪,舒华忠.鲍威尔和模拟退火优化算法结合的多分辨率三维图像配准[J].2004,3:176-178. [33] M. Breeuwer, J. P. Wadley, H. L. T. de Bliek, J. Buurman, P. A. C. Desmedt, P. Gieles, F. A. Gerritsen, N. L. Dorward, N. D. Kitche, B. Velani, D. G. T. Thomas, C. R. Jr Maurer, et al. Progress in the European Applications in Surgical Interventions (EASI) Project[J]. Computer Assisted Radiology and Surgery (CARS), 1998: 627-634. [34] A. Collignon, F. Maes, D. Delaere, et al. Automated multi-modality image registration based on information theory[C]. In: Y. Bizais, editor, Proceedings of the Information Processing in Medical Imaging Conference. Dordrecht: Kluwer Academic Publishers, 1995: 263-274. [35] P. Viola. Alignment by maximization of mutual information[D]. Massachusetts: Massachusetts Institute of Technology (MIT), 1995. [36] C. Studholme, D. L. G. Hill, and D. J. Hawkes. An overlap invariant entropy measure of 3D medical image[J]. Pattern Recognition, 1999, 32:71-86. [37] C. Studholme. Measures of 3D medical image alignment[D]. London: University of London, 1997. [38] A. Ben Hamza, Yun He and Hamid Krim. An information divergence measure for ISAR image registration[C]. In: Proc. of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing, 2001: 130-133. [39] Yun He, A. Ben Hamza, and Hamid Krim. A generalized divergence measure for robust image registration[J]. IEEE Transactions on Signal Processing, 2003, 51(5): 1211-1220. [40] J. West, J. M. Fitzpatrick, M. Y. Wang, et al. Comparison and evaluation of retrospective intermodality brain image registration techniques[J]. Journal of Computer Assisted Tomography, 1997, 21(4): 554-566. [41] R. Marti, R. Zwiggelaar, C. Rubin. A novel similarity to evaluate image correspondence[C]. In: Proc. of 15th International Conference on Pattern Recognition, 2000:167-170. [42] 陈明,陈武凡,冯前进,杨丰.基于互信息量和模糊梯度相似性的医学图像配准[J].电子学报, 2003, 31(12): 1835-1838. [43] J. Pluim, J. Maintz, and M. Viergever. Image registration by maximization of combined mutual information and gradient information[J]. IEEE Transactions on Medical Imaging, 2003,19(8): 809-814. [44] D. Rueckert, M. J. Clarkson, D. Hill and D. Hawkes. Non-rigid registration using higher-order mutual information[A]. In: Proc. of SPIE, 2000, 3979: 438-447. [45] Z. Gao, Y. Qian, J. Lin. Medical image registration by maximization of relative mutual information[C]. In: Proc. of 2001 Annual National Conference on Biomedical information & Control, Wuhan, China, 2001: 328-329.