基于交叉累计剩余熵的多谱磁共振图像配准

doi:10.11772/j.issn.1001-9081.2015.01.0231

计算机应用 ›› 2015, Vol. 35 ›› Issue (1): 231-234.DOI: 10.11772/j.issn.1001-9081.2015.01.0231

基于交叉累计剩余熵的多谱磁共振图像配准

相艳^1,2, 贺建峰², 易三莉², 刑正伟²

1. 昆明理工大学云南省计算机技术应用重点实验室, 昆明650500;
2. 昆明理工大学信息工程与自动化学院, 昆明650500

收稿日期:2014-08-15 修回日期:2014-09-24 出版日期:2015-01-01 发布日期:2015-01-26
通讯作者: 贺建峰
作者简介:相艳(1979-),女,云南大理人,讲师,硕士,主要研究方向:医学图像分割、图像配准;贺建峰(1965-),男,云南开远人,教授,博士,主要研究方向:医学图像处理、生物信息学;易三莉(1977-),女,湖南岳阳人,讲师,博士,主要研究方向:医学图像增强.
基金资助:
国家自然科学基金资助项目(11265007).

Registration of multispectral magnetic resonance images based on cross cumulative residual entropy

XIANG Yan^1,2, HE Jianfeng², YI Sanli², XING Zhengwei²

1. Key Laboratory of Computer Technologies Application of Yunnan Province, Kunming University of Science and Technology, Kunming Yunnan 650500, China;
2. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China

Received:2014-08-15 Revised:2014-09-24 Online:2015-01-01 Published:2015-01-26

摘要/Abstract

摘要：

针对传统互信息(MI)图像配准容易产生局部极值的问题,提出一种基于交叉累计剩余熵(CCRE)的多谱磁共振图像配准方法.首先,将参考和浮动图像压缩至5位和7位灰度级;然后,采用哈宁窗Sinc插值计算5位灰度图像的CCRE,并用Brent算法搜索CCRE得到预配准的变换参数;最后,从该变换参数出发,采用部分体积(PV)插值计算7位灰度图像的CCRE,用Powell算法进行优化,得到最终的变换参数.实验结果表明,该方法的鲁棒性相比直接采用PV插值的CCRE配准得到提高;配准时间比直接采用哈宁窗Sinc插值的CCRE配准节省了90%左右,且配准精度有所提高.该方法兼顾了鲁棒性、效率和精度,适合用于多谱图像配准.

关键词: 图像配准, 交叉累积剩余熵, 哈宁窗Sinc函数, 部分体积插值, 多谱

Abstract:

To solve the problem that classical Mutual Information (MI) image registration may lead to local extremum, a registration method for multispectral magnetic resonance images based on Cross Cumulative Residual Entropy (CCRE) was proposed. Firstly, the gray level of reference and floating images were compressed into 5 and 7 bits. Then the Hanning windowed Sinc interpolation was used to calculate the CCRE of 5-bit grayscale images, and the Brent algorithm was used to search the CCRE to get the initial transformation parameters of pre-registration. Finally, the Partial Volume (PV) interpolation was adopted to calculate the CCRE of 7-bit grayscale images, and the Powell algorithm was applied to optimize the CCRE to get final parameters from the pre-registration parameters. The experimental results show that the robustness of the proposed method is improved compared with the CCRE registration of PV interpolation, while the registration time is saved about 90% and accuracy is improved compared with the CCRE of Hanning windowed Sinc interpolation. The presented method ensures robustness, efficiency and accuracy, so it is suitable for multi-spectral image registration.

Key words: image registration, Cross Cumulative Residual Entropy (CCRE), Hanning windowed Sinc function, Partial Volume (PV) interpolation, multispectral

中图分类号:

TP391.413

相艳, 贺建峰, 易三莉, 刑正伟. 基于交叉累计剩余熵的多谱磁共振图像配准[J]. 计算机应用, 2015, 35(1): 231-234.

XIANG Yan, HE Jianfeng, YI Sanli, XING Zhengwei. Registration of multispectral magnetic resonance images based on cross cumulative residual entropy[J]. Journal of Computer Applications, 2015, 35(1): 231-234.

参考文献

[1] JIA F, LI H. Multi-spectral magnetic resonance image segmentation using random forests [J]. Computer Engineering, 2005, 31(10): 159-161.(贾富仓,李华.基于随机森林的多谱磁共振图像分割[J].计算机工程,2005,31(10):159-161.)
[2] NIE S, NIE B, ZHANG L, et al. Study on segmentation method for multi-spectrum head MRI based on fuzzy K-nearest neighbor rule [J]. Chinese Journal of Biomedical Engineering, 2002, 21(5): 471-476.(聂生东,聂斌,章鲁,等.基于模糊K-近邻规则的多谱磁共振脑图像分割方法的研究[J].中国生物医学工程学报,2002,21(5):471-476.)
[3] HE R, DATTA S, SAJJA B R, et al. Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images [J]. Computerized Medical Imaging and Graphics, 2008, 32(5): 353-366.
[4] GARCÍA-LORENZO D, PRIMA S, ARNOLD D L, et al. Trimmed-likelihood estimation for focal lesions and tissue segmentation in multisequence MRI for multiple sclerosis [J]. IEEE Transactions on Medical Imaging, 2011, 30(8): 1455-1467.
[5] WANG L, SUN F, WANG Y, et al. 3D registration of MR image sequence of human brain based on normalized mutual information [J]. Computer Engineering and Applications, 2011, 47(31): 160-163.(王丽,孙丰荣,王奕琨,等.基于互信息的颅脑MR影像序列的三维配准[J].计算机工程与应用,2011,47(31):160-163.)
[6] XU D, LI S. Research of medical image registration based on mutual information and overcome of local-maxima [J]. Computer Engineering and Applications, 2007, 43(3): 217-219.(徐东,李升辉.互信息医学图像配准研究与局部极值的克服[J].计算机工程与应用,2007,43(3):217-219.)
[7] ZHU S, ZHAO H, LUO B. Application of mutual information based on weighted entropy in medical image registration [J]. Computer Engineering and Applications, 2011, 47(16): 207-210.(朱圣权,赵海峰,罗斌.加权熵互信息在医学图像配准中的应用[J].计算机工程与应用,2011,47(16):207-210.)
[8] WU X, ZHOU J, XIE M. Maximum likelihood estimation image denoising using non-local principle component analysis [J]. Chinese Journal of Biomedical Engineering, 2012, 31(4): 481-486.(吴锡,周激流,谢明元.非局部主成分分析极大似然估计MRI图像Rician噪声去噪[J].中国生物医学工程学报,2012,31(4):481-486.)
[9] WANG F, VEMURI B C. Non-rigid multi-modal image registration using cross-cumulative residual entropy [J]. International Journal of Computer Vision, 2007, 74(2): 201-215.
[10] HASAN M, PICKERING M R, JIA X. Robust automatic registration of multimodal satellite images using CCRE with partial volume interpolation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(10): 4050-4061.
[11] LI C, CHEN Q, QIAN W. Registration algorithm of multispectral images based on cross cumulative residual entropy [J]. Infrared and Laser Engineering, 2013, 42(7): 1866-1870.(李超,陈钱,钱惟贤.基于交叉累计剩余熵的多光谱图像配准方法[J].红外与激光工程,2013,42(7):1866-1870.)
[12] EVANS A C. BrainWeb: simulated MRI volumes for normal brain [EB/OL]. [2014-03-21]. http://brainweb.bic.mni.mcgill.ca/brainweb/selection_normal.html.
[13] RAO M, CHEN Y, VEMURI B C, et al. Cumulative residual entropy, a new measure of information [J]. IEEE Transactions on Information Theory, 2004, 50(6): 1220-1228.
[14] LI X, TAN J. Application of mutual information of regional in head MRI registration [J]. Computer Engineering and Applications, 2009, 45(10): 154-156.(李晓光,谭建豪.邻域互信息在磁共振颅脑图像配准的应用[J].计算机工程与应用,2009,45(10):154-156.)
[15] LU X, ZHANG S, SU H, et al. Mutual information-based multimodal image registration using a novel joint histogram estimation [J]. Computerized Medical Imaging and Graphics, 2008, 32(3): 202-209.
[16] AJA-FERNÁNDEZ S, TRISTÁN-VEGA A. Influence of noise correlation in multiple-coil statistical models with sum of squares reconstruction [J]. Magnetic Resonance in Medicine, 2012, 67(2): 580-585.

基于交叉累计剩余熵的多谱磁共振图像配准

Registration of multispectral magnetic resonance images based on cross cumulative residual entropy

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

[1]	孙启昌, 麦永锋, 陈晓军. 基于增强现实的手术导航系统快速标定算法[J]. 计算机应用, 2021, 41(3): 833-838.
[2]	张家岗, 李达平, 杨晓东, 邹茂扬, 吴锡, 胡金蓉. 基于深度卷积特征光流的形变医学图像配准算法[J]. 计算机应用, 2020, 40(6): 1799-1805.
[3]	吴孟桦, 胡晓兵, 李航, 江代渝. 基于图像配准的零件轮廓修正方法[J]. 计算机应用, 2020, 40(4): 1144-1150.
[4]	丁辉, 李丽宏, 原钢. 融合GMS与VCS+GC-RANSAC的图像配准算法[J]. 计算机应用, 2020, 40(4): 1138-1143.
[5]	谢志华, 江鹏, 余新河, 张帅. 基于VGGNet和多谱带循环网络的高光谱人脸识别系统[J]. 计算机应用, 2019, 39(2): 388-391.
[6]	王丽芳, 王雁丽, 蔺素珍, 秦品乐, 高媛. 基于改进的Zernike矩的局部描述符与图割离散优化的非刚性多模态脑部图像配准[J]. 计算机应用, 2019, 39(2): 582-588.
[7]	彭磊, 杨秀云, 张裕飞, 李光耀. 基于全局与局部相似性测度的非刚性点集配准[J]. 计算机应用, 2019, 39(10): 3028-3033.
[8]	梁志刚, 顾军华. 改进头脑风暴优化算法与Powell算法结合的医学图像配准[J]. 计算机应用, 2018, 38(9): 2683-2688.
[9]	叶峰, 洪峥, 赖乙宗, 赵雨亭, 谢先治. 基于匹配质量提纯的改进D-Nets算法[J]. 计算机应用, 2018, 38(4): 1121-1126.
[10]	王丽芳, 成茜, 秦品乐, 高媛. 基于多通道稀疏编码的非刚性多模态医学图像配准[J]. 计算机应用, 2018, 38(4): 1127-1133.
[11]	刘薇, 陈雷霆. 基于自适应切空间的MRI图像配准[J]. 计算机应用, 2017, 37(4): 1193-1197.
[12]	房贻广, 刘武, 高梦珠, 谭守标, 张骥. 基于FREAK描述子的精确图像配准改进算法[J]. 计算机应用, 2016, 36(12): 3402-3405.
[13]	吴伟, 丁香乾, 闫明. 基于异常区域感知的多时相高分辨率遥感图像配准[J]. 计算机应用, 2016, 36(10): 2870-2874.
[14]	查珊珊, 王远军, 聂生东. 基于图形处理器加速的医学图像配准技术进展[J]. 计算机应用, 2015, 35(9): 2486-2491.
[15]	赵伟, 田铮, 杨丽娟, 延伟东, 温金环. 基于典型相关分析方法的尺度不变特征变换误匹配剔除[J]. 计算机应用, 2015, 35(11): 3308-3311.