基于互信息的医学图像配准算法研究
|
摘要
医学图像配准是现代医学图像处理的关键技术,为医生提供了科学的诊断依据。基于互信息的配准方法具有配准精度高、鲁棒性强等优点,近年来已成为医学图像配准领域的研究热点。本文研究了大量基于互信息医学图像配准的算法,所做的主要工作有以下几个方面:
首先,介绍了医学图像配准的研究背景及发展现状,深入研究了基于互信息配准的相关理论知识,分析了算法的原理及配准流程,并对基于互信息的配准方法存在的优缺点及改进方法进行了详细的讨论。
其次,在互信息理论基础上,对图像插值技术进行了研究,针对传统插值方法插值精度低和插值速度慢的缺点,提出了一种新的插值算法,即基于像素点的亮度绝对误差的图像插值算法。
再次,针对基于互信息配准方法存在局部极值、配准时间长等问题,提出利用小波变换中的多分辨率思想,先对待配准图像进行多分辨率分解,在低分辨率下采用FGA优化算法取得配准的初步结果,再在高分辨率下采用Powell优化算法取得精确结果。
最后,采用美国Vanderbilt大学RREP项目组提供的国际通用图像数据,利用Matlab7.0工具对基于互信息的医学图像配准的两种新算法进行单模和多模配准仿真实验,实现了互信息法的图像配准,同时还将配准结果进行比较分析,从而验证了新算法的精确性和鲁棒性。
Medical image registration is the key technology of the modern medicine; it provides the scientific diagnosis for doctors. Registration based on Mutual Information are popular in medical image registration processing fields, which are accepted as the most accurate and robustness. In this paper, a large number of Registration based on Mutual Information algorithms are researched. The main results in this paper are as follows:
Firstly, the background knowledge and current situation were introduced, and the correlative theoretical knowledges Registration based on Mutual Information were deeply researched, and the principle of mutual information and registration processes were introduced, and the strengths and weaknesses of Registration based on Mutual Information algorithms and improving methods were discussed in detail.
Secondly, on the basis of mutual information, image interpolation technology are researched, aim at the traditional interpolation method has low accurate and slow speed, a new interpolation algorithm are proposed, that is, the image interpolation algorithm based on the absolute error of the brightness of pixels, which combines the advantages of nearest interpolation and bicubic interpolation, without prejudice to the case of interpolation accuracy can greatly improve the speed of image interpolation.
Thirdly, to overcome Registration based on Mutual Information algorithms has the shortcoming of the local maxima and the computing expansive, wavelet- based multi-resolution approach was applied in registration. The sub-images which were decomposed by wavelet transformation were registered using FGA, and then the results were applied as the start point for the registration of high-resolution image using Powell's method.
Finally, the single-mode and multimode registration experiments of two algorithms were done under Matlab7.0 environment, in which use the image data which provided by international standard on the United States Vanderbilt University RREP project team, which realized image registration based on mutual information, at the same time, the results of registration are comparative analysis, and the accuracy and robustness of the new algorithm were verified.
首先,介绍了医学图像配准的研究背景及发展现状,深入研究了基于互信息配准的相关理论知识,分析了算法的原理及配准流程,并对基于互信息的配准方法存在的优缺点及改进方法进行了详细的讨论。
其次,在互信息理论基础上,对图像插值技术进行了研究,针对传统插值方法插值精度低和插值速度慢的缺点,提出了一种新的插值算法,即基于像素点的亮度绝对误差的图像插值算法。
再次,针对基于互信息配准方法存在局部极值、配准时间长等问题,提出利用小波变换中的多分辨率思想,先对待配准图像进行多分辨率分解,在低分辨率下采用FGA优化算法取得配准的初步结果,再在高分辨率下采用Powell优化算法取得精确结果。
最后,采用美国Vanderbilt大学RREP项目组提供的国际通用图像数据,利用Matlab7.0工具对基于互信息的医学图像配准的两种新算法进行单模和多模配准仿真实验,实现了互信息法的图像配准,同时还将配准结果进行比较分析,从而验证了新算法的精确性和鲁棒性。
Medical image registration is the key technology of the modern medicine; it provides the scientific diagnosis for doctors. Registration based on Mutual Information are popular in medical image registration processing fields, which are accepted as the most accurate and robustness. In this paper, a large number of Registration based on Mutual Information algorithms are researched. The main results in this paper are as follows:
Firstly, the background knowledge and current situation were introduced, and the correlative theoretical knowledges Registration based on Mutual Information were deeply researched, and the principle of mutual information and registration processes were introduced, and the strengths and weaknesses of Registration based on Mutual Information algorithms and improving methods were discussed in detail.
Secondly, on the basis of mutual information, image interpolation technology are researched, aim at the traditional interpolation method has low accurate and slow speed, a new interpolation algorithm are proposed, that is, the image interpolation algorithm based on the absolute error of the brightness of pixels, which combines the advantages of nearest interpolation and bicubic interpolation, without prejudice to the case of interpolation accuracy can greatly improve the speed of image interpolation.
Thirdly, to overcome Registration based on Mutual Information algorithms has the shortcoming of the local maxima and the computing expansive, wavelet- based multi-resolution approach was applied in registration. The sub-images which were decomposed by wavelet transformation were registered using FGA, and then the results were applied as the start point for the registration of high-resolution image using Powell's method.
Finally, the single-mode and multimode registration experiments of two algorithms were done under Matlab7.0 environment, in which use the image data which provided by international standard on the United States Vanderbilt University RREP project team, which realized image registration based on mutual information, at the same time, the results of registration are comparative analysis, and the accuracy and robustness of the new algorithm were verified.
引文
1杨金宝,刘长春,胡顺波.广义信息熵在医学图像配准中的应用,计算机工程与应用, 2008,44(8):34-36
2田捷,包尚联,周明全.医学影响处理与分析.北京:电子工业出版社, 2003:96-111
3傅祖芸.信息论——基础理论与应用.电子工业出版社, 2007:84-99
4 J. B. AntoineMaintz, M. A. Viergever. A Survey of Medical Image Registration. Medical Image Analysis, 1998,2(l):1-6
5 F. Maes, A. Collignon, D. Vandermeulen. Medical Image Registration Using Mutual Information. Processing of the IEEE, 2003,91(10):1699-1722
6 D. Tomǎzevic, B. Likar, F. Pernǔs. Multi-Feature Mutual Information. Medical Imaging: Image Processing, 2004,15(7):143-154
7 F. Maes, A. Cllignon, D. Vandermeulen, et al. Multi-Modality Image Registration by Maximization of Mutual Information. IEEE Trans Med Imaging, 1997:187-198
8 C. Studholme, D. L. G. Hill. An Overlap Invariant Entropy Measure of 3D Medical Images Alignment. Pattern Recognition, 1999:71-86
9 C. Studhohne, D. L. G. Hill, D. J. Hawkes. Incorporating Connected Region Labeling into Automated Image Registration Using Mutual Information. Proc. 2nd IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, 1996,28(16):23-31
10 P. W. Pluim Josien, J. B. Antoine Maintz, M. A. Viergever. Image Registration by Maximization of Combined Mutual Information and Gradient Information. IEEE Transaction on Medical Imaging, 2000,19(8):809-814
11 D. Rueckert, M. J. Clarkson, D. L. G Hill, et al.Non-Rigid Registration Using Higher Order Mutual Information.Proc. SPIE, Medical Imaging:Image Processing, 2000,44(39):438-447.
12 B. Torsten, J. P. Thiran. Affine Registration with Feature Space Mutual Information. InProc. Medical Image Computing and Computer-Assisted Intervention (MICCA I'00),Berlin,Germany, 2000:549-556
13 C. E. Shannon. A Mathematical Theory of Communication. The Bell System Technical Journal, 1948,42(27):379-423
14 A. Collignon, F. Maes, D.Delaere, et al. Automated Multi-Modality Image Registration Based on Information Theory. In: BizaisY, Barillot C, Di Paola Reds, Information Processing in Medical Imaging, Dordercht: Kluwer Academic Publishers, 1995:263-274
15 P. Viola, W. M. Wells. Alignment by Maximization of Mutual Information. In:Grimson E, Shafer S, Blake A, Sugihara Keds, International Conference on Computer Vision,1995,Los Alamitos, CA:IEEE Computer Science Press, 1995:16-23
16高智勇,顾滨,林家瑞.基于互信息的医学图像配准实验.生物医学工程学杂志, 2003,20(3):476-478
17张红颖,张加万,孙济洲.基于混合互信息的医学图像配准.计算机应用, 2006,26(10):2351-2353
18翟海亭,吴晓娟,彭彰.一种改进的基于互信息的三维医学图像配准算法.山东大学学报(工学版), 2006,36(4):33-37
19 H. Y. Zhou, T.W. Liu, F.Q. Lin. Towarda efficient registration of Medical images. Computerized Medical Imaging and Graphics. 2007,31(6)374-382
20冯林,管慧娟,滕弘飞.基于互信息的医学图像配准技术研究进展.生物医学工程学杂志, 2005,22(5):1078-1081
21 P. Xu, D. Z. Yao. A Study on Medical Image Registration by Mutual Information with Pyramid Data Structure. Computers in Biology and Medicine, 2007, 37(1):320-327
22 H. X. Luan, F. H. Qi, Z. Xue, et al. Multimodality image registration by maximization of quantitative–qualitative measure of mutual information. Pattern Recognition, 2008,41(1):285-298
23 B. Itova, J. Flusser. Image registration methods a survey. Image Vision Computing 2003;(21)977–1000
24 J. P. W.Pluim, J. B. A. Maintz, M. A. Viergever. Mutual information matching inmultiresolution contexts. Image Vision Computing. 2001,32(19)45–52
25 J. Kybic. High-dimensional mutual information estimation for image registration. In: International conference on image processing. 2004.14(3)1779–1812
26 J. P. W. Pluim, J. B. A. Maintz, M. A. Viergever.Mutual information based registration of medical image: a survery. 2003,22(8):986–1004
27 C. C. Liu, K. Li, Z.G. Liu. Medical image registration by maximization of combined mutual information and edge correlative deviation. Engineering in Medicine and Biology Society. 2005:6379–6382
28 Y. M. Zhu, S. M. Cochoff. Influence of Implementation Parameters on Registration of MR and SPECT Brain Images by Maximization of Mutual Information. J.Nucl. Med, 2002,43(2):160-166
29彭景林,章兢,李树涛.基于改进PV插值和混合优化算法的医学图像配准.电子学报, 2006,34(5):962-965
30 T. Jeffrey. Interpolation Artifacts in Multimodality Image Registration Based on Maximization of Mutual Information. IEEE Transactions on Medical Imaging, 2003,22(7):854-864
31 J. L. Andersson, A. Sundin, S. Valind. A Method for Co-registration of PET and MR Brain Images. Journal of Nuclear Medicine, 1995,36(7):1307-1311
32 G. Borgefors. Hierarchical Chamfer Matching: a Parametric Edge Matching Algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(6):849-853
33吴锋,钱宗才,杭洽时等.基于互信息和模拟退火算法的多模式医学图像配准.第四军医大学学报,2002,23(1):76-78
34冯林,严亮,黄德根等. PSO和Powell混合算法在医学图像配准中的应用研究.北京生物医学工程, 2005,24(11):8-12
35 P. Chalermwat, T. ElGhazawi, J. LeMoigneb, et al. 2-Phase GA Based Image Registration on Parallel Clusters. Future Generation Computer Systems, 2001,17(4):467-471
36 C. Studholme, D. L. Hill, D. J. Hawkes. Automated 3-D Registration of MR and CT Images of the Head. Medical Image Analysis, 1996,(2):163-169
37 Y. Chen, R. R. Brooks. Efficient Global Optimization for Image Registration.IEEE Transaction on Knowledge and Engineering, 2002,(14):79-85
38 J. Cizek, K. Herholz. Fast and Robust Registration of PET and MR Images of Human Brain. Neuro Image, 2004,26(22):434-439
39 J. Orchard. Multimodal image registration using floating regressors in the joint intensity scatter plot. Medical Image Analysis. 2008,12(4)385-396
40 R. Leardi. Genetic algorithm. Comprehensive Chemometrics. 2009:31-653
41 Y. T. Kao, E. Zahara. A hybrid genetic algorithm and partical swarm optimization for multimodal functions. Applied Soft Computing. 2008,8(2):849-857
42 A. Vasan, K. S. Raju. Comparative analysis of Simulated Annealing, Simulated Quenching and Genentic Algorithms for optimal reservoir operation.Applied Soft Computing. 2009,9(1)274-181
43 A. Colorni, M. Dorigo, V. Maniezzo. An Investigation of Some Properties of an Ant Algorithm. Proc. Of the Parallel Problem Solving from Nature Conference (PPSN’92). Brussels, Belgium, Elsevier Publishing, 1992:509-520
44 R. J. Mullen, D. Monekosso, S. Barman, P. Remagnino. A review of ant algorithms.Eaperts Systems with Applications. 2009,36(6):9608-9617
45 J. Kennedy, R. Eberhart. Particle Swarm Optimization. In:Proceedings of IEEE International Conference on Neural Networks,Perth, 1995:942-948
46 R. Eberhart, J. Kennedy. A New Optimizer Using Particle Swarm Theory. In: Proceedings of the 6th International Symposium on Micro Machine and Human Science,Nagoya, 1995:39-43
47 M. Frederik, V. Dirk, S. Paul. Comparative Evaluation of Multi-Resolution Optimization Strategies for Multimodality Image Registration by Maximization of Mutual Information. Medical Image Analysis, 1999(3):373-386
48飞思科技产品研发中心.小波分析理论与MATLAB7实现.电子工业出版社, 2005:61-65
49 G. P. Penney, J. Weese, J. A. Litle, et al. A Comparison of Similarity Measures for Use in 2D-3D Medical Image Registration. IEEE Transactions on Medical Imaging,1998,17(4):586-595
50 X. S. Lu, S. Zhang, H. Su, Y.Z. Chen. Mutual information-based multimodal image registration using a novel joint histogram estimation. Computerized Medical Imageing and Graphics. 2008,32:202-209
51 J. P. W. Pluim, J. B. A. Maintz, M. A. Viergever. F Information measures in medical image registration. IEEE Trans Med Imag, 2004,23(12):1508-1516
52 M. P. Wachowiaka, R. Smolikova, G. D. Tourassib,et al. Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration. SPIE 2003:Medical Imaging, 2003,5032:1090-1100
53 A. Bardera, M. Feixas, Boadal. Normalized similarity measures for medical image registration.SPIE2004: Medical Imaging, 2004,5370:1090-1100
54 S. Arimoto. Information-theoretic consideration on estimation problems. Information and Control, 1971,19:181-190
55李建华,王孙安,杜海峰.一种改进的遗传算法:Family GA.控制与决策. 2009.19(9):999-1004
2田捷,包尚联,周明全.医学影响处理与分析.北京:电子工业出版社, 2003:96-111
3傅祖芸.信息论——基础理论与应用.电子工业出版社, 2007:84-99
4 J. B. AntoineMaintz, M. A. Viergever. A Survey of Medical Image Registration. Medical Image Analysis, 1998,2(l):1-6
5 F. Maes, A. Collignon, D. Vandermeulen. Medical Image Registration Using Mutual Information. Processing of the IEEE, 2003,91(10):1699-1722
6 D. Tomǎzevic, B. Likar, F. Pernǔs. Multi-Feature Mutual Information. Medical Imaging: Image Processing, 2004,15(7):143-154
7 F. Maes, A. Cllignon, D. Vandermeulen, et al. Multi-Modality Image Registration by Maximization of Mutual Information. IEEE Trans Med Imaging, 1997:187-198
8 C. Studholme, D. L. G. Hill. An Overlap Invariant Entropy Measure of 3D Medical Images Alignment. Pattern Recognition, 1999:71-86
9 C. Studhohne, D. L. G. Hill, D. J. Hawkes. Incorporating Connected Region Labeling into Automated Image Registration Using Mutual Information. Proc. 2nd IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, 1996,28(16):23-31
10 P. W. Pluim Josien, J. B. Antoine Maintz, M. A. Viergever. Image Registration by Maximization of Combined Mutual Information and Gradient Information. IEEE Transaction on Medical Imaging, 2000,19(8):809-814
11 D. Rueckert, M. J. Clarkson, D. L. G Hill, et al.Non-Rigid Registration Using Higher Order Mutual Information.Proc. SPIE, Medical Imaging:Image Processing, 2000,44(39):438-447.
12 B. Torsten, J. P. Thiran. Affine Registration with Feature Space Mutual Information. InProc. Medical Image Computing and Computer-Assisted Intervention (MICCA I'00),Berlin,Germany, 2000:549-556
13 C. E. Shannon. A Mathematical Theory of Communication. The Bell System Technical Journal, 1948,42(27):379-423
14 A. Collignon, F. Maes, D.Delaere, et al. Automated Multi-Modality Image Registration Based on Information Theory. In: BizaisY, Barillot C, Di Paola Reds, Information Processing in Medical Imaging, Dordercht: Kluwer Academic Publishers, 1995:263-274
15 P. Viola, W. M. Wells. Alignment by Maximization of Mutual Information. In:Grimson E, Shafer S, Blake A, Sugihara Keds, International Conference on Computer Vision,1995,Los Alamitos, CA:IEEE Computer Science Press, 1995:16-23
16高智勇,顾滨,林家瑞.基于互信息的医学图像配准实验.生物医学工程学杂志, 2003,20(3):476-478
17张红颖,张加万,孙济洲.基于混合互信息的医学图像配准.计算机应用, 2006,26(10):2351-2353
18翟海亭,吴晓娟,彭彰.一种改进的基于互信息的三维医学图像配准算法.山东大学学报(工学版), 2006,36(4):33-37
19 H. Y. Zhou, T.W. Liu, F.Q. Lin. Towarda efficient registration of Medical images. Computerized Medical Imaging and Graphics. 2007,31(6)374-382
20冯林,管慧娟,滕弘飞.基于互信息的医学图像配准技术研究进展.生物医学工程学杂志, 2005,22(5):1078-1081
21 P. Xu, D. Z. Yao. A Study on Medical Image Registration by Mutual Information with Pyramid Data Structure. Computers in Biology and Medicine, 2007, 37(1):320-327
22 H. X. Luan, F. H. Qi, Z. Xue, et al. Multimodality image registration by maximization of quantitative–qualitative measure of mutual information. Pattern Recognition, 2008,41(1):285-298
23 B. Itova, J. Flusser. Image registration methods a survey. Image Vision Computing 2003;(21)977–1000
24 J. P. W.Pluim, J. B. A. Maintz, M. A. Viergever. Mutual information matching inmultiresolution contexts. Image Vision Computing. 2001,32(19)45–52
25 J. Kybic. High-dimensional mutual information estimation for image registration. In: International conference on image processing. 2004.14(3)1779–1812
26 J. P. W. Pluim, J. B. A. Maintz, M. A. Viergever.Mutual information based registration of medical image: a survery. 2003,22(8):986–1004
27 C. C. Liu, K. Li, Z.G. Liu. Medical image registration by maximization of combined mutual information and edge correlative deviation. Engineering in Medicine and Biology Society. 2005:6379–6382
28 Y. M. Zhu, S. M. Cochoff. Influence of Implementation Parameters on Registration of MR and SPECT Brain Images by Maximization of Mutual Information. J.Nucl. Med, 2002,43(2):160-166
29彭景林,章兢,李树涛.基于改进PV插值和混合优化算法的医学图像配准.电子学报, 2006,34(5):962-965
30 T. Jeffrey. Interpolation Artifacts in Multimodality Image Registration Based on Maximization of Mutual Information. IEEE Transactions on Medical Imaging, 2003,22(7):854-864
31 J. L. Andersson, A. Sundin, S. Valind. A Method for Co-registration of PET and MR Brain Images. Journal of Nuclear Medicine, 1995,36(7):1307-1311
32 G. Borgefors. Hierarchical Chamfer Matching: a Parametric Edge Matching Algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(6):849-853
33吴锋,钱宗才,杭洽时等.基于互信息和模拟退火算法的多模式医学图像配准.第四军医大学学报,2002,23(1):76-78
34冯林,严亮,黄德根等. PSO和Powell混合算法在医学图像配准中的应用研究.北京生物医学工程, 2005,24(11):8-12
35 P. Chalermwat, T. ElGhazawi, J. LeMoigneb, et al. 2-Phase GA Based Image Registration on Parallel Clusters. Future Generation Computer Systems, 2001,17(4):467-471
36 C. Studholme, D. L. Hill, D. J. Hawkes. Automated 3-D Registration of MR and CT Images of the Head. Medical Image Analysis, 1996,(2):163-169
37 Y. Chen, R. R. Brooks. Efficient Global Optimization for Image Registration.IEEE Transaction on Knowledge and Engineering, 2002,(14):79-85
38 J. Cizek, K. Herholz. Fast and Robust Registration of PET and MR Images of Human Brain. Neuro Image, 2004,26(22):434-439
39 J. Orchard. Multimodal image registration using floating regressors in the joint intensity scatter plot. Medical Image Analysis. 2008,12(4)385-396
40 R. Leardi. Genetic algorithm. Comprehensive Chemometrics. 2009:31-653
41 Y. T. Kao, E. Zahara. A hybrid genetic algorithm and partical swarm optimization for multimodal functions. Applied Soft Computing. 2008,8(2):849-857
42 A. Vasan, K. S. Raju. Comparative analysis of Simulated Annealing, Simulated Quenching and Genentic Algorithms for optimal reservoir operation.Applied Soft Computing. 2009,9(1)274-181
43 A. Colorni, M. Dorigo, V. Maniezzo. An Investigation of Some Properties of an Ant Algorithm. Proc. Of the Parallel Problem Solving from Nature Conference (PPSN’92). Brussels, Belgium, Elsevier Publishing, 1992:509-520
44 R. J. Mullen, D. Monekosso, S. Barman, P. Remagnino. A review of ant algorithms.Eaperts Systems with Applications. 2009,36(6):9608-9617
45 J. Kennedy, R. Eberhart. Particle Swarm Optimization. In:Proceedings of IEEE International Conference on Neural Networks,Perth, 1995:942-948
46 R. Eberhart, J. Kennedy. A New Optimizer Using Particle Swarm Theory. In: Proceedings of the 6th International Symposium on Micro Machine and Human Science,Nagoya, 1995:39-43
47 M. Frederik, V. Dirk, S. Paul. Comparative Evaluation of Multi-Resolution Optimization Strategies for Multimodality Image Registration by Maximization of Mutual Information. Medical Image Analysis, 1999(3):373-386
48飞思科技产品研发中心.小波分析理论与MATLAB7实现.电子工业出版社, 2005:61-65
49 G. P. Penney, J. Weese, J. A. Litle, et al. A Comparison of Similarity Measures for Use in 2D-3D Medical Image Registration. IEEE Transactions on Medical Imaging,1998,17(4):586-595
50 X. S. Lu, S. Zhang, H. Su, Y.Z. Chen. Mutual information-based multimodal image registration using a novel joint histogram estimation. Computerized Medical Imageing and Graphics. 2008,32:202-209
51 J. P. W. Pluim, J. B. A. Maintz, M. A. Viergever. F Information measures in medical image registration. IEEE Trans Med Imag, 2004,23(12):1508-1516
52 M. P. Wachowiaka, R. Smolikova, G. D. Tourassib,et al. Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration. SPIE 2003:Medical Imaging, 2003,5032:1090-1100
53 A. Bardera, M. Feixas, Boadal. Normalized similarity measures for medical image registration.SPIE2004: Medical Imaging, 2004,5370:1090-1100
54 S. Arimoto. Information-theoretic consideration on estimation problems. Information and Control, 1971,19:181-190
55李建华,王孙安,杜海峰.一种改进的遗传算法:Family GA.控制与决策. 2009.19(9):999-1004