多模态医学影像鲁棒配准方法研究
|
摘要
多模态医学影像根据所提供的信息不同可分为两大类：解剖影像和功能影像。解剖影像提供较高分辨率的组织或器官的解剖结构信息，但无法反映其代谢情况；功能影像反映人体组织或器官的功能和代谢信息，但分辨率较低。为了将这些互补信息有机地融合在一起，先决条件就是进行多模态医学影像的配准，配准的精度直接决定着融合的效果。医学影像配准就是寻求一种最优空间变换，使两幅医学影像的对应点在给定的相似性测度下达到空间位置和解剖位置的一致。
在不同模态医学影像成像的过程中，通常将用于成像的放射线、示踪剂和强磁场等对人体有害的影响控制在一定的范围内，加上成像模式本身的一些物理限制，往往导致影像不清晰，并伴有噪声甚至伪影的出现。因此，研究多模态医学影像配准方法对噪声的鲁棒性具有十分重要的理论意义和应用价值。本文取得的主要创新研究成果如下：
(1).针对传统互信息测度的局限性，提出了一种基于主定序和混合熵的多模态医学影像鲁棒配准方法。首先利用主成分分析(PCA)方法定义了医学影像的主定序特征，描述影像邻域像素间的空间信息和微观结构特性；进而结合影像灰度构建了一种基于混合熵的配准测度，有效保证了配准测度函数的光滑性和收敛性。多组多模态医学影像测试结果表明，提出的方法能有效抑制噪声，具有很高的配准精度，鲁棒性强，优于现有的几种方法。
(2).针对非线性高维定序特征，提出了一种基于局部线性嵌入(LLE)和混合熵的多模态医学影像鲁棒配准方法。该方法采用LLE算法对医学影像多方向的定序特征进行降维处理，并通过LLE逆向映射方法重构医学影像的整体定序特征，最后结合影像灰度构成特征空间，基于混合熵的配准测度通过衡量两幅影像对应灰度信息和空间信息的一致性，使配准测度函数更加平滑。实验结果表明，在影像空间分辨率较低和有噪声的情况下，该方法具有精度高、鲁棒性强的特点。
(3).针对医学影像的非刚性配准，提出了一种基于自由变形(FFD)和改进的L-BFGS优化的配准新方法。首先运用仿射变换对待配准影像进行全局粗配准，再对发生局部形变区域采用基于B样条的FFD模型进行非线性空间变换，并将基于LEE和混合熵的配准测度应用于非刚性配准中，在最优配准参数的优化搜索过程中，改进的L-BFGS优化方法采用限制步长和变异操作增强了跳出局部最优解的能力，提高了搜索精度。实验结果表明，该方法在运算速度和配准精度上有较明显的优势，但不适用于噪声情况下影像中存在较大组织形变的配准。
(4).针对配准的物理模型，提出了一种基于局部保留投影(LPP)和粒子群优化(PSO)的医学影像鲁棒配准方法。在医学影像配准过程中，将浮动影像向参考影像配准所产生的一系列空间变换看作视频流中的连续帧，则医学影像配准过程可以看作是一个光滑而连续的视频流，从而配准空间存在于某种低维非线性流形上，但该流形的结构非常复杂，很难与众多形变参数的物理意义对应起来。该方法采用流形学习的LPP算法配合PSO算法进行配准参数的优化搜索，避免了对配准流形直接建模的困难。由于数据降维过程中大量信息被约简，该方法的配准精度要略低于本文之前提出的算法，但其优势在于适用性好，不仅适用于医学影像的刚性、非刚性配准，而且可以推广到其他各种场合的图像配准。
According to the physical principles for imaging, multimodality medical imagesare usually divided into two types: structural and functional images. Structural imagesprovide mainly high-resolution images with geometric and anatomical information.Functional images provide metabolic or neurochemical changes characteristic but withcoarser resolution. In order to fuse complementary characteristics of the underlyinganatomy and tissue microstructure from medical images of different modalities, thegeometric registration is a preliminary and crucial step and has a paramount influenceon the performance of image fusion. Medical image registration is defined as theprocess that determines the best structural and physiological correspondence betweentwo or more medical images.
In multimodality medical imaging, medical images are sometimes blurringbecause the adverse influence of the radioactive ray, tracer and high magnetic field forhuman body must be reduced. Moreover, there are the physical limitations of theimaging process itself, such as noise, limited resolution, insufficient contrast orinhomogeneity. Therefore, robust registration of multimodality medical images is avery challenging problem. The main achievements of this dissertation are as follows:
(1). To improve the robustness and precision of the maximization of mutualinformation (MI) similarity, a principal ordinal feature and hybrid entropy basedregistration method is presented. A principal ordinal feature (OF) is defined and used torepresent the spatial information between the neighboring pixels and the properties ofthe specified micro-structure in medical images. Integrating with pixel intensities, asimilarity measure based on hybrid entropy is defined to register multimodality images.The proposed method is demonstrated using several pairs of multimodality medicalimages and the experimental results show that the noise of images can be effectivelysuppressed and compared with some existing methods, the proposed registrationalgorithm is of higher precision and better robustness.
(2). Due to the nonlinear relationships of high-dimensional OFs in nature, a locallinear embedding (LLE) and hybrid entropy based registration method is proposed. Forhigh dimensional OFs, the LLE algorithm is used to dimensionality reduction and theinverse mapping of LLE is used to fuse complementary information of OFs together.Then a novel similarity measure based on hybrid entropy which integrates intensity with OF is defined to register multimodality images. Through quantitative evaluations,the proposed measure is proven to provide improved robustness with accuracy.
(3). Non-rigid registration of medical images has become a challenging task inmedical image processing and applications. A LLE and improved L-BFGSoptimization based registration method is proposed. A hierarchical transformationmodel of medical images is developed. The global motion is modeled by an affinetransformation while the local motion is described by a free-form deformation (FFD)based on B-splines. Then the proposed LEE and hybrid entropy based similaritymeasure is chosen as the registration function. Finally an improved L-BFGS algorithmis used to search the optimal registration parameters. We evaluate the effectiveness ofthe proposed approach by applying it to the simulated brain image data. Theexperimental results show that the proposed registration algorithm is of higherprecision and faster speed. However, it cannot be applied to image registration withlarge anatomical variation in noisy environment.
(4). Based on a new physical model of image registration, a locality preservingprojection (LPP) and particle swarm optimization (PSO) based registration method isproposed. A large deformation between the reference image and the floating image isdecomposed into a series of small deformations and the result of every deformation istreated as a frame in the registration video. Therefore, the registration process isequivalent to a smooth and continuous video and the registration space is on a certainnonlinear manifold of lower dimensionality. However, the registration manifold isusually too complicated to build the correspondence with numerous deformationparameters. Hence, medical images are projected into manifold space by the LPPalgorithm and the optimal registration parameters are searched by the PSO algorithm.Though the proposed method is not as good in precision as what we expect because ofdimension reduction, it can be widely used to many applications.
在不同模态医学影像成像的过程中，通常将用于成像的放射线、示踪剂和强磁场等对人体有害的影响控制在一定的范围内，加上成像模式本身的一些物理限制，往往导致影像不清晰，并伴有噪声甚至伪影的出现。因此，研究多模态医学影像配准方法对噪声的鲁棒性具有十分重要的理论意义和应用价值。本文取得的主要创新研究成果如下：
(1).针对传统互信息测度的局限性，提出了一种基于主定序和混合熵的多模态医学影像鲁棒配准方法。首先利用主成分分析(PCA)方法定义了医学影像的主定序特征，描述影像邻域像素间的空间信息和微观结构特性；进而结合影像灰度构建了一种基于混合熵的配准测度，有效保证了配准测度函数的光滑性和收敛性。多组多模态医学影像测试结果表明，提出的方法能有效抑制噪声，具有很高的配准精度，鲁棒性强，优于现有的几种方法。
(2).针对非线性高维定序特征，提出了一种基于局部线性嵌入(LLE)和混合熵的多模态医学影像鲁棒配准方法。该方法采用LLE算法对医学影像多方向的定序特征进行降维处理，并通过LLE逆向映射方法重构医学影像的整体定序特征，最后结合影像灰度构成特征空间，基于混合熵的配准测度通过衡量两幅影像对应灰度信息和空间信息的一致性，使配准测度函数更加平滑。实验结果表明，在影像空间分辨率较低和有噪声的情况下，该方法具有精度高、鲁棒性强的特点。
(3).针对医学影像的非刚性配准，提出了一种基于自由变形(FFD)和改进的L-BFGS优化的配准新方法。首先运用仿射变换对待配准影像进行全局粗配准，再对发生局部形变区域采用基于B样条的FFD模型进行非线性空间变换，并将基于LEE和混合熵的配准测度应用于非刚性配准中，在最优配准参数的优化搜索过程中，改进的L-BFGS优化方法采用限制步长和变异操作增强了跳出局部最优解的能力，提高了搜索精度。实验结果表明，该方法在运算速度和配准精度上有较明显的优势，但不适用于噪声情况下影像中存在较大组织形变的配准。
(4).针对配准的物理模型，提出了一种基于局部保留投影(LPP)和粒子群优化(PSO)的医学影像鲁棒配准方法。在医学影像配准过程中，将浮动影像向参考影像配准所产生的一系列空间变换看作视频流中的连续帧，则医学影像配准过程可以看作是一个光滑而连续的视频流，从而配准空间存在于某种低维非线性流形上，但该流形的结构非常复杂，很难与众多形变参数的物理意义对应起来。该方法采用流形学习的LPP算法配合PSO算法进行配准参数的优化搜索，避免了对配准流形直接建模的困难。由于数据降维过程中大量信息被约简，该方法的配准精度要略低于本文之前提出的算法，但其优势在于适用性好，不仅适用于医学影像的刚性、非刚性配准，而且可以推广到其他各种场合的图像配准。
According to the physical principles for imaging, multimodality medical imagesare usually divided into two types: structural and functional images. Structural imagesprovide mainly high-resolution images with geometric and anatomical information.Functional images provide metabolic or neurochemical changes characteristic but withcoarser resolution. In order to fuse complementary characteristics of the underlyinganatomy and tissue microstructure from medical images of different modalities, thegeometric registration is a preliminary and crucial step and has a paramount influenceon the performance of image fusion. Medical image registration is defined as theprocess that determines the best structural and physiological correspondence betweentwo or more medical images.
In multimodality medical imaging, medical images are sometimes blurringbecause the adverse influence of the radioactive ray, tracer and high magnetic field forhuman body must be reduced. Moreover, there are the physical limitations of theimaging process itself, such as noise, limited resolution, insufficient contrast orinhomogeneity. Therefore, robust registration of multimodality medical images is avery challenging problem. The main achievements of this dissertation are as follows:
(1). To improve the robustness and precision of the maximization of mutualinformation (MI) similarity, a principal ordinal feature and hybrid entropy basedregistration method is presented. A principal ordinal feature (OF) is defined and used torepresent the spatial information between the neighboring pixels and the properties ofthe specified micro-structure in medical images. Integrating with pixel intensities, asimilarity measure based on hybrid entropy is defined to register multimodality images.The proposed method is demonstrated using several pairs of multimodality medicalimages and the experimental results show that the noise of images can be effectivelysuppressed and compared with some existing methods, the proposed registrationalgorithm is of higher precision and better robustness.
(2). Due to the nonlinear relationships of high-dimensional OFs in nature, a locallinear embedding (LLE) and hybrid entropy based registration method is proposed. Forhigh dimensional OFs, the LLE algorithm is used to dimensionality reduction and theinverse mapping of LLE is used to fuse complementary information of OFs together.Then a novel similarity measure based on hybrid entropy which integrates intensity with OF is defined to register multimodality images. Through quantitative evaluations,the proposed measure is proven to provide improved robustness with accuracy.
(3). Non-rigid registration of medical images has become a challenging task inmedical image processing and applications. A LLE and improved L-BFGSoptimization based registration method is proposed. A hierarchical transformationmodel of medical images is developed. The global motion is modeled by an affinetransformation while the local motion is described by a free-form deformation (FFD)based on B-splines. Then the proposed LEE and hybrid entropy based similaritymeasure is chosen as the registration function. Finally an improved L-BFGS algorithmis used to search the optimal registration parameters. We evaluate the effectiveness ofthe proposed approach by applying it to the simulated brain image data. Theexperimental results show that the proposed registration algorithm is of higherprecision and faster speed. However, it cannot be applied to image registration withlarge anatomical variation in noisy environment.
(4). Based on a new physical model of image registration, a locality preservingprojection (LPP) and particle swarm optimization (PSO) based registration method isproposed. A large deformation between the reference image and the floating image isdecomposed into a series of small deformations and the result of every deformation istreated as a frame in the registration video. Therefore, the registration process isequivalent to a smooth and continuous video and the registration space is on a certainnonlinear manifold of lower dimensionality. However, the registration manifold isusually too complicated to build the correspondence with numerous deformationparameters. Hence, medical images are projected into manifold space by the LPPalgorithm and the optimal registration parameters are searched by the PSO algorithm.Though the proposed method is not as good in precision as what we expect because ofdimension reduction, it can be widely used to many applications.
引文
[1].康晓东.现代医学影像技术.天津:天津科学翻泽出版公司.2001.
[2]. Aristeidis S., Christos D., Nikos P. Deformable medical image registration: asurvey. IEEE Trans. on Medical Imaging,2013,32(7):1153-1190.
[3]. Zitova B., Flusser J. Image registration methods: a survey. Image and VisionComputing,2003,21:977-1000.
[4]. Maintz J.B.A., Viergever M.A. A survey of medical image registration. MedicalImage Analysis,1998,2(1):1-37.
[5]. Pluim J.P.W., Maintz J.B.A., Viergever M.A. Mutual-information basedregistration of medical images: a survey. IEEE Trans on Medical Imaging,2003,22(8):986-1004.
[6]. Barillot C., Lemoine D. Data fusion in medical imaging: merging multimodaland multipatient images, identification of structures and3D display aspects.European joumal of radiology,1993,17:22-27.
[7]. Petra A., Elsen V. Medical image matching-a review with classification. IEEETrans on biomedical engineering,1993,16:26-39.
[8]. Michael Fitzpatrick.J. The Retrospective Image Registration Evaluation Project.http://www. insight-journal. org/rire/.
[9]. Roche A., Pennec X., Malandain G., and Ayache N. Rigid registration of3-Dultrasound with MR images: A new approach combining intensity and gradientinformation. IEEE Trans. on Medical Imaging,2001,20(10):1038-1049.
[10]. Wein W., Brunke S., Khamene A., Callstrom M. R., and Navab N. AutomaticCT-ultrasound registration for diagnostic imaging and image-guidedintervention. Medical Image Analysis,2008,12(5):577-585.
[11]. Maintz J. B. A., van den Elsen P. A., and Viergever M. A.3D multimodalitymedical image registration using morphological tools. Image Vis. Comput.,2001,19(1-2):53-62.
[12]. Haber E. and Modersitzki J. Intensity gradient based registration and fusion ofmulti-modal images. Methods Inf. Med.,2007,46(3):292-299.
[13]. Woods, R. P., Mazziotta, J. C., Cherry, S. R. MRI-PET registration withautomated algorithm. Journal of Computer Assisted Tomography.1993,17(4):536-546.
[14]. Hill, D. L. G., Hawkes, D. J., Harrison, N. A., Ruff, C. F. A strategy forautomated multimodality image registration incorporating anatomicalknowledge and image characteristics. Information Processing in MedicalImaging.1993,687:182-196.
[15]. Collignon A., Vandermeulen D., Suetens P., and Marchal G.3-D multimodalitymedical image registration using feature space clustering. In Proc. First Int.Conf. Computer Vistion, Virtual Reality and Robotics in Medicine(CVRMED’95), Lecture Notes in Computer Science, France, Apr.1995,905:195-204.
[16]. Maes F., Collignon A., Vandermeulen D., et a1. Multimodality imageregistration by maximization of mutual information. IEEE Trans. on MedicalImaging,1997,16(2):187-198.
[17]. Collignon A., Maes F., Delaere D., Vandermeulen D., Suetens P., Marchal G.Automated multi-modality image registration based on information theory. InProc.14th Int. Conf. Information Processing in Medical Imaging (IPMI’95),Computational Image and Vision. France,1995,3:263-274.
[18]. Viola P. A., Wells III, W. M. Alignment by maximization of mutual information.International Conference on Computer Vision, IEEE Computer Society Press.1995:16-23.
[19]. Wells III, W. M., Viola P., Atsumi H., Nakajima S., Kikinis R. Multi-modalvolume registration by maximization of mutual information. Medical ImageAnalysis.1996,1:35-51.
[20]. Shannon C. E. A mathematical theory of communication. In Bell SystemTechnical Journal,1948,27:379-423.
[21]. Studholme, C., Hill, D. L. G, Hawkes, D. J. An overlap invariant entropymeasure of3d medical image alignment. Pattern Recognition,1999,32(1):71-86.
[22]. Ronald W. K. So, Tommy W. H. Tang and Albert C. S. Chung. Non-rigid imageregistration of brain magnetic resonance images using graph-cuts. PatternRecognition,2011,44(10-11):2450-2467.
[23]. Gan R., Chung A. C. S., Liao S. Maximum distance-gradient for robust imageregistration. Medical Image Analysis,2008,12:452-468.
[24]. Pluim J. P. W., Maintz J. B. A., and Viergever. M. A. Image registration bymaximization of combined mutual information and gradient information. IEEETrans. on Medical Imaging,2000,19(8):809-814.
[25]. Rueckert D., Clarkson M. J., Hill D. L. G., et al. Non-rigid registration usinghigher-order mutual information. Proceedings of SPIE Medical Imaging2000:Image Processing, San Diego CA,2000:438-447.
[26]. Thevenaz P., Unser M. Optimization of mutual information for multiresolutionimage registration. IEEE Trans on Image Processing,2000,9(12):2083-2099.
[27]. Chen H. M., Varshney P. K. A pyramid approach for multimodality imageregistration based on mutual information. In Proceedings of the ThirdInternational Conference on Information Fusion,2000,1: MOD3/9-MOD3/15.
[28].陈武凡，小波分析及其在医学图像处理中的应用，北京：科学出版社，2002.
[29]. Foroosh H., Zerubia J. B., and Berthod M. Extension of phase correlation tosubpixel registration. IEEE Trans. on Image Processing,2002,11:188-200.
[30]. Reddy B. S. and Chatterji B. N. An FFT-based technique for translation,rotation, and scale-invariant image registration. IEEE Trans. on ImageProcessing,1996,5:1266-1271.
[31]. Modersitzki J. Numerical Methods for Image Registration: Oxford UniversityPress.2004.
[32]. Broit C. Optimal registration of deformed images. Dissertation AbstractsInternational Part B: Science and Engineering [DISS. ABST. INT. PT. B-SCI.&ENG],1982,42(11):1982.
[33]. Bajcsy R., Lieberson R., Reivich M. A Computerized System for the ElasticMatching of Deformed Radiographic Images to Idealized Atlas Images. Journalof Computer Assisted Tomography,1983,7(4):618-625.
[34]. Gee J. C., Haynor D. R., Reivich M., et a1. Finite element approach to warpingof brain images. Medical Imaging,1994:327-337.
[35]. Guyader C. Le and Vese L. A. A combined segmentation and registrationframework with a nonlinear elasticity smoother. Comput. Vis. ImageUnderstand.,2011,115(12):1689-1709.
[36]. Burger M., Modersitzki J., and Ruthotto L. A hyperelastic regularization energyfor image registration. SIAM J. Sci. Comput.,2013,35(1): B132-B148.
[37]. Christensen G E., Johnson H. J. Consistent image registration. IEEE Trans. onMedical Imaging,2001,20(7):568-582.
[38]. Chiang M. C., Leow A. D., Klunder A.D., et a1. Fluid registration of diffusiontensor images using information theory. IEEE Trans. on Medical Imaging,2008,27(4):442-456.
[39]. Christensen G E., Rabbitt R. D., Miller M. I. Deformable templates using largedeformation kinematics. IEEE Trans. on Image Processing,1996,5(10):1435-1447.
[40]. Christensen G. E., Joshi S. C., Miller M. I. Volumetric transformation of brainanatomy. IEEE Trans. on Medical Imaging,1997,16(6):864-877.
[41]. Christensen G. E. Deformable shape models for anatomy. WashingtonUniversity,1994.
[42]. Vercauteren T., Pennec X., Perchant A., and Ayache N. Symmetric log-domaindiffeomorphic registration: A demons-based approach. in Int. Conf. Med. ImageComput. Comput.-Assist. Intervent.,2008:754-761.
[43]. Cahill N. D., Noble J. A., and Hawkes D. J. Demons algorithms for fluid andcurvature registration. in Proc. Int. Symp. Biomed. Imag.,2009:730-733.
[44]. Cahill N. D., Noble J. A., and Hawkes D. J. A Demons algorithm for imageregistration with locally adaptive regularization. in Proc. Int.l Con. Med. ImageComput. Comput.-Assist. Intervent.,2009:574-581.
[45]. Mansi T., Pennec X., Sermesant M., Delingette H., and Ayache N. Ilogdemons:A demons-based registration algorithm for tracking incompressible elasticbiological tissues. Int. J. Comput. Vis.,2011,92(1):92-111.
[46]. Thirion J. P. Image matching as a diffusion process: an analogy with Maxwell’sDemons. Medical Image Analysis,1998,2:243-260.
[47]. Thirion J. P. Non-rigid matching using demons. Image Matching as a DiffusionProcess: An Analogy with Maxwell’s Demons, Medical Image Analysis,1998,2(3):243-260.
[48]. Risser L., Vialard F., Wolz R., Murgasova M., Holm D. D., and Rueckert, D.Simultaneous multi-scale registration using large deformation diffeomorphicmetric mapping. IEEE Trans. on Medical Imaging,2011,30(10):1746-1759.
[49]. Sommer S., Nielsen M., Lauze F., and Pennec X. A multi-scale kernel bundlefor lddmm: Towards sparse deformation description across space and scales. inProc. Int. Conf. Inf. Process. Med. Imag.,2011:624-635.
[50]. Morton K. W., Mayers D. F. Numerical Solution of Partial DifferentialEquations. Cambridge University Press,2006.
[51]. Buhmann M. D. Radial basis functions. Acta Numerica2000,2000,9(0):1-38.
[52]. Powell M. J. D. Radial basis functions for multivariate interpolation: A review.In Conf.1st Algorithms for Approximation (inst Math. Its Appl. Conf. Series).1987:143-167.
[53]. Powell M. J. D. The theory of radial basis function approximation in l990. InAdvances in numerical analysis. V01.2: Wavelets, subdivision algorithms, andradial basis functions, Proc.4th Summer Sch., Lancaster/UK.1990:2.
[54]. Fornefett M., Rohr K., Stiehl H. S. Radial basis functions with compact supportfor elastic registration of medical images. Image and Vision Computing,2001,19(12):87-96.
[55]. Yang X., Xue Z., Liu X., and Xiong D. Topology preservation evaluation ofcompact-support radial basis functions for image registration. Pattern Recognit.Lett.,2011,32(8):1162-1177.
[56]. Rohr K., W rz S. An extension of thin-plate splines for image registration withradial basis functions. in Proc. Int. Symp. Biomed. Imag.,2012:442-445.
[57]. W rz S. and Rohr K. Physics-based elastic registration using non-radial basisfunctions and including landmark localization uncertainties. Comput. Vis.Image Understand.,2008,111(3):263-274.
[58]. Mattes D., Haynor D. R., Vesselle H., et a1. PET-CT image registration in thechest using free-form deformation. IEEE Trans on Medical Imaging.2003,20(1):120-128.
[59]. Kybic J., Unser M. Fast parametric elastic image registration. IEEE Trans onImage Processing,2003,12(11):1427-1442.
[60]. Jiang J., Luk W., and Rueckert D. FPGA-based computation of free-formdeformations. In IEEE International Conference on Field ProgrammableTechnology. IEEE Computer Society Press,2002.
[61]. Rueckert D., Sonoda L I., Hayes C., Hill D. L. G., Leach M. O., and Hawkes D.J.. Non-rigid registration using free-form deformations: Application to breastMR images. IEEE Trans. on Medical Imaging,1999,18(8):712-721.
[62]. Torsten R, Calvin R M, David A B. Volume-preserving nonrigid registration ofMR breast images using free-form deformation with all incompressibilityconstraint. IEEE Trans. on Medical Imaging,2003,22(6):730-741.
[63]. T.Metz C., Klein S., Schaap M., VanWalsum T., and Niessen W. J. Nonrigidregistration of dynamic medical imaging data using nd+t b-splines and agroupwise optimization approach. Medical Image Analysis,2011,15(2):238-249.
[64]. Shi W., Zhuang X., Pizarro L., Bai W., Wang H., Tung K.-P., Edwards P., andRueckert D. Registration using sparse free-form deformations. in Proc. Int.Conf. Med. Image Comput. Comput.-Assist. Intervent.,2012:659-66.
[65]. Sotiras A. and Paragios N. Discrete symmetric image registration. in Proc. Int.Symp. Biomed. Imag.,2012:342-345.
[66]. Cootes T. F., Twining C. J., Petrovi V. S., Babalola K. O., and Taylor C. J.Computing accurate correspondences across groups of images. IEEE Trans.onPattern Analysis and Machine Intelligence,2010,32(11):1994-2005.
[67]. Buerger C., Schaeffter T., and King A. P. Hierarchical adaptive local affineregistration for fast and robust respiratory motion estimation. Medical ImageAnalysis,2011,15(4):551-564.
[68]. Van den Elsen P. A., Maintz J. B. A., Pol E. J. D., and Viergever M. A.Automatic registration of CT and MR brain images using correlation ofgeometrical features. IEEE Trans. on Medical Imaging,1995,14(2):384-398.
[69]. Verbeeck, R. Rinciples and practive of a workstation for the pre-operativeplanning of stereotactic neurosurgical interventions: from implementation toclinical evalumion. Belgium: Leuven,1996.
[70]. Gildenberg, P. L., Tasker, R. R. Textbook of stereotactic and functionalneurosurgery. New York, NY: McGraw-Hill.1998.
[71]. Simon, D. A., O’Toole, R. V., Blackwell, M., Morgan, F., Digioia, A. M.,Kanade, T. Accuracy validation in image-guided orthopaedic surgery. InMedical Robotics and Computer Assisted Surgery.1995:185-192.
[72]. Ellis, R. E., Toksvig-Larsen, S., Marcacci, M., Caramella, D., Fadda, M. Abiocompatible fiduical marker for evaluating the accuracy of CT imageregistration. Computer Assisted Radiology.1996,1124:693-698.
[73]. Biswal, B. B., Hyde, J. S. Contour-based registration technique to differentitatebetween task-activated and head motion-induced calibration for freehand3Dultrasound. Medical Image Computing and Computer-Assisted Intervention.2000,1935:462-471.
[74]. Declerck,J., Feldmar,J., Goris, M. L., Betting, F. Automatic registration andalignment on a templated of cardiac stress and rest reoriented SPECT images.IEEE Trans. on Medical Imaging.1997,16(6):727-737.
[75]. Maintz J. B. A., van den Elsen P. A., and Viergeveg M. A. Comparison ofedge-based and ridge-based registration of CT and MR brain images. MedicalImage Analysis,1996,1(2):151-161.
[76]. Maintz J. B. A., van den Elsen P. A., and Viergever M. A. Evaluation of ridgeseeking operators for multimodality medical image matching. IEEE Trans. onPattern Analysis and Machine Intelligence,1996,18(4):353-365.
[77]. Grimson, W. E. L., Ettinger, G. J., White, S. J., Lozano-Perez, T., Wells, W. M.,Kikinis, R. An automation registration method for frameless stereotaxy, imageguided surgery, and enhanced reality visualization. IEEE Trans. on MedicalImaging.1996,15(2):129-140.
[78]. Herring, J. L., Dawant, B. M., Maurer, C. R., Muratore, D. M., Galloway, R. L.,Fitzpatrick, J. M. Surfact-based registration of CT images to physical space forimage-guided surgery of the spine: a sensitivity study. IEEE Trans. on MedicalImaging.1998,17(5):743-761.
[79]. Szeliski, R., Lavallee, S. Matching3-D anatomical surfaces with non-rigiddeformations using octree-splines. International Journal of Computer Vision.1996,18(2):171-186.
[80]. Gonzales R. C. and Woods R. E. Digital Image Processing,2nd ed. UpperSaddle Rivef, NJ: Prentice-Hall.2002.
[81]. Bajcsy, R., Kovacic, S. Multiresolution elastic matching. Computer Vision,Graphics and Image Processing.1989,46:1-21.
[82]. Cachier, P. Pennec, X.3D non-rigid registration by gradient descent on aGaussian-windowed similarity measure using convolutions. In MatchematicalMethods in Biomedical Image Analysis, IEEE Computer Society Press, LosAlamitos, CA.2000:182-189.
[83]. Lemieux, L., Wieshmann, U. C., Moran, N. F., Fish, D. R., Shorvon, S. D. Thedetection and significance of subtle change in mixed-signal brain lesions byserial MRI scan matching and spatial normalization. Medical Image analysis.1998,2(3):227-242.
[84]. Gee, J. C., Haynor, D. R., Briquer, L. Le., Bajcsy, R. K. Advances in elasticmatching theory and its implementation. Proceeding of Computer Vision,Virtual Reality and Robotics in Medicine and Medical Robotics andComputer-Assisted Surgery.1997,1205:63-72.
[85]. Ashbumer, J., Friston, K. J. Nonlinear spatial normalization using basisfunctions. Human Brain Mapping.1999,7:254-266.
[86]. Collignon A. Multi-modality medical image registration by maximization ofmutual information. Leuven: Catholic University of Leuven.1998.
[87]. Collignon A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.Automated multi-modality image registration based on information theory.Information Processing in Medical Imaging.1995:263-274.
[88]. Viola P. A., Wells III, W. M. Alignment by maximization of mutual information.International Conference on Computer Vision, IEEE Computer Society Press.1995:16-23.
[89]. Viola P. A. Alignment by maximization of mutual information. Boston:Massachusetts Institute of Technology.1995.
[90]. Wells III, W. M., Viola, P., Kikinis, R. Multi-modal volume registration bymaximization of mutual information. Medical Robotics and Computer AssistedSurgery.1995:55-62.
[91]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Multiresolution voxel similaritymeasures for MR-PET registration. Proceedings of the Intemational Conferenceon Information Processing in Medical Imaging (IPMI).1995,3:287-298.
[92]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Automated3-D registration of MRand CT images of the head. Medical Image Analysis.1996,1(2):163-175.
[93]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Automated three-dimensionalregistration of magnetic resonance and positron emission tomography brainimages by multiresolution optimization of voxel similarity measure. MedicalPhysics.1996,24(1):25-35.
[94]. Wells III, W. M., Viola P., Atsumi H., Nakajima S., Kikinis R. Multi-modalvolume registration by maximization of mutual information. Medical ImageAnalysis.1996,1:35-51.
[95]. Meyer, C. R., Boes, L. J., Kim, B., Bland, P. H., Zasadny,K. R., Kison, P. V,Koral, K., Frey,K. A., Wahl, R. L. Demonstration of accuracy and clinicalversatility of mutual information for automatic multimodality image fusionusing affine and thin-plate spline warped geometric deformations. MedicalImage Analysis.1996,1(3):195-206.
[96]. Glasbey C. A., Mardia K. V. A review of image-warping methods. Journal ofApplied Statistics,1998,25(2):155-171.
[97]. Holden M. A Review of Geometric Transformations for Nonrigid BodyRegistration. IEEE Trans. on Medical Imaging,2008,27(1):111-128.
[98]. Lester H., Arridge S. R. A survey of hierarchical non-linear medical imageregistration. Pattern Recognition,1999,32(1):129-149.
[99]. Fogel D. N., Type R. Image Registration using Multiquadric Functions, theFinite Element Method, Bivariate Mapping Polynomials and Thin Plate Spline.1996, National Center for Geographic Information and Analysis: Santa Barbara,California.
[100]. Christensen G. E. Consistent linear-elastic transformations for image matching.Information Processing in Medical Imaging,1999:224-237.
[101]. Amit Y. A nonlinear variational problem for image matching. SIAM J. Sci.Comput,1994,15(1):207-224.
[102]. Gefen S., Tretiak E., Nissanov J. Elastic3D alignment of rat brain histologicalimages. IEEE Trans. on Medical Imaging,2003,22(11):1480-1489.
[103]. Wu Y. T., Kanade T., Li C. C., et al. Image Registration Using Wavelet-BasedMotion Model. International Joumal of Computer Vision,2000,38(2):129-152.
[104]. Wu Y T., Chen L. F., Lee P. L., et a1. Discrete signal matching usingcoarse-to-fine wavelet basis functions. Pattern Recognition,2003,36(1):171-192.
[105]. Yang J., Wang Y., Tang S., et a1. Multiresolution Elastic Registration of X-RayAngiography Images Using Thin-Plate Spline. IEEE Trans. on Nuclear Science,2007,54(1):152-166.
[106]. Bookstein F. L. Principal warps: thin-plate splines and the decomposition ofdeformations. IEEE Trans. on Pattern Analysis and Machine Intelligence,1989,11(6):567-585.
[107]. Rohr K., Fomefett M., Stiehl H. S. Approximating Thin-Plate Splines for ElasticRegistration: Integration of Landmark Errors and Orientation Attributes.Information Processing in Medical Imaging,1999:252-265.
[108]. Li J., Yang X., and Yu J. Compact support thin plate spline algorithm. J.Electron.(China),2007,24(4):515-522.
[109]. Rohr K. and W rz, S. An extension of thin-plate splines for image registrationwith radial basis functions. in Proc. Int. Symp. Biomed. Imag.,2012:442-445.
[110]. Rabbitt R. D., Weiss J. A., Christensen G. E. and Miller M. I. Mapping ofhyperelastic deformable templates using the finite element method. InProc.SPIE Vis. Geometry,1995:252-265.
[111]. Horn B. K. P., Schunck B. G. Determining Optical Flow. Artificial Intelligence,1981,17(1-3):185-203.
[112]. Barton J. L., Fleet D. J., Beauchemin S. S.. Performance of optical flowtechniques. International Journal of Computer Vision,1994,12(1):43-77.
[113]. Wang H., Dong L., O’Daniel J. Validation of an accelerated demons algorithmfor deformable image registration in radiation therapy. Phys. Med. Biol.,2005,50(12):2887-2905.
[114]. Rogelj P., Kovai S. Symmetric image registration. Medical Image Analysis,2006,10(3):484-493.
[115].林相波,邱天爽,阮素. Demons非刚性配准算法拓扑保持性的研究.自动化学报,2010,36(1):179-183.
[116].许鸿奎,江铭炎,杨明强.基于改进光流场模型的脑部多模医学图像配准.电子学报,2012,40(3):525-529.
[117].朱雪龙.应用信息论基础.北京：清华大学出版社,2000.
[118]. Holden, M., Hill, D. L. G, Jarosz, J. M., Cox, T. C. S., Rohlfing, T., Goodey, J.,Hawkes, D. J. Voxel similarity measures for3-D serial MR brain imageregistration. IEEE Trans. on Medical Imaging.2000,19:94-102.
[119]. Freire, L., Roche, A., Mangin, J. F. What is the best similarity measure formotion correction in fMRI a time series? IEEE Trans. on Medical Imaging.2002,21:470-484.
[120]. Radau, P. E., Slomka, P. J., Julin, P, Svensson, L., Wahlund, L. O. Automatedsegmentation and registration technique for hmpao-spect imaging ofAlzheimer’s patients. Proceedings of SPIE on Medical Imaging: ImageProcessing.2000,3979:372-384.
[121]. Fei, B., Wheaton, A., Lee, Z., Duerk,J. L., Wilson, D. L. Automatic MR volumeregistration and its evaluation for the pelvis and prostate. Physics in Medicineand Biology.2002,47(5):823-838.
[122]. Slomka, P. J., Mandel, J., Downey, D., Fenster, A. Evaluation of voxel-basedregistration of3-D power Doppler ultrasound and3-D magnetic resonanceangiographic images of carotid arteries. Ultrasound in Medicine and Biology.2001,27(7):945-955.
[123]. Holden, M., Hill, D. L. G, Denton, E. R. E., Jarosz, J. M., Cox,T. C. S., Rohlfing,T., Goodey, J., Hawkes, D. J. Voxel similarity measures for3-D serial MR brainiamge registration. IEEE Trans. on Medical Imaging.2000,19(2):94-102.
[124]. Studholme, C., Cardenas, V, Weiner, M. Multi scale image and multi scaledeformation of brain anatomy for building average brain atlases. Proceedings ofSPIE in Medical Imaging: Image Processing.2001,4322:557-568.
[125]. Studholme, C., Novotny, E, Zubai, I. G., Duncan, J. S. Estimating tissuedeformation between functional images induced by intracranial electrodeimplantation using anatomical MRI. Neurolmage.2001,13(4):561-576.
[126]. Shekhar, K., Zagrodsky, V. Mutual information-based rigid and nonrigidregistration of ultrasound volumes. IEEE Trans. on Medical Imaging.2002,21(1):1660-1668.
[127]. Luan H., Qi F., Xue Z., Chen L., Shen D. Multimodality image registration bymaximization of quantitative-qualitative measure of mutual information. PatternRecognition.2007.
[128]. Luan H., Qi F., Shen D. Multi-model image registration byquantitative-qualitative measure of mutual information (Q-MI). ComputerVision for Biomedical Image applications, ICCV2005workshop, October21,Beijing, China.2005:378-387.
[129]. Krol, Z., Zerfass, P., Rymon-Lipinski, B., Jansen, T., Hauck,W., Zeilhofer,H. F.,Sader, R., Keeve, E. Computer aided osteotomy design for harvestingautologous bone grafts in reconstructive surgery. Proceedings of SPIE, MedicalImaging: Visualization, Image Display, and Image-guided Procedures.2001,4319:244-251.
[130]. Denton, E. R. E., Holden, M., Christ, E., Jarosz, J. M., RussellHones, D.,Goodey, J., Cox, T. C. S., Hill. D. L. G. The identification of cerebral volumechanges in treated growth hormonedeficient adults using serial3D MR imageprocessing. Journal of Computer Assisted Tomography.2000,24(1):139-145.
[131]. Ourselin, S., Roche, A., Prima, S., Ayache, N. Block matching: a generalframework to improve robustness of rigid registration of medical images.Proceedings of Lecture Notes in Computer Science, Medical Image Computingand Computer-Assisted Intervention.2000,1935:557-566.
[132]. Van Laere, K., Koole, M., D’Asseler, Y., Versijpt, J., Audenaert, K., Dumont, E.,Dierckx, R. Automated stereotactic standardization of brain SPECT receptordata using single-photon transmission images. Joumal of Nuclear Medicine.2001,42(2):361-375.
[133]. Jenkinson, M., Smith, S. A global optimization method for robust affineregistration of brain images. Medical Image analysis.2001,5(2):143-156.
[134]. Holden, M. Registration of3D serial MR brain images. London: University ofLondon.2001.
[135]. Horsfield, M. A. Mapping eddy current induced fields for the correction ofdiffusion-weighted echo planar images. Magnetic Resonance Imaging.1999,17(9):1335-1345.
[136]. Otte, M. Elastic registration of fMRI data using Bezier-spline transformations.IEEE Trans. on Medical Imaging.2001,20(3):193-206.
[137]. Hellier, P., Barillot, C. Multimodal non-rigid warping for correction ofdistortions in function MRI. Proceedings of Lecture Notes in Computer Science,Medical Image Computing and Computer-Assisted Intervention.2000,1935:512-520.
[138]. Likar, B., Pernus, F. A Hierarchical approach to elastic registration based onmutual information. Image and Vision Computing.2001,19(12):33-44.
[139]. Maintz, J. B. A., Meijering, E. H. W., Viergever, M. A. General multimodalelastic registration based on mutual information. Proceedings of SPIE, MedicalImaging；Image Processing.1998,3338:144-154.
[140]. Lehman T. M., Gomner C., Spitzer K. Survey: interpolation methods in medicalimage processing. IEEE Trans. on Medical Imaging,1999,18(11):1049-1075.
[141]. Zhu, Y-M., Cochoif, S. M. Influence of implementation parameters onregistration of MR and SPECT brain images by maximization of mutualinformation. Journal of Nuclear Medicine.2002,43(2):160-166.
[142]. Netsch, T., Rosch, R., Weese, J., van Muiswinkel, A., Desmedt, P. Greyvalue-based3-D registration of functional MRI time-series: comparison ofinterplolation order and similarity measure. Proceedings of SPIE, MedicalImaging: Image Processing.2000,3979:1148-l159.
[143]. Pluim J. P. W., Maintz J. B. A., Viergever M. A. Interpolation artifacts in mutualinformation based image registration. Computer Vision and ImageUnderstanding,2000,77(2):211-232.
[144]. Tsao J. Interpolation artifacts in multimodality image registration based onmaximization of mutual information. IEEE Trans. on Medical Imaging,2003,22(7):854-864.
[145]. Studholme C., Hill D. L. G., Hawkes D. J. An ovedap invariant entropy measureof3D medical image alignment. Pattern Recognition,1999,32(1):71-86.
[146]. Maes F., Vandermeulen D., Suetens P. Comparative evaluation ofmultiresolution optimization strategies for multimodality image registration bymaximization of mutual information. Medical Image Analysis,1999,3(4):373-386.
[147]. Chen B. J., Li J. L., Chen G. Study of Medical Image Registration Based onSecond-Order Mutual Information. Proc. of the1st International Conference onBioinformatics and Biomedical Engineering, Wuhan: ICBBE,2007:956-959.
[148]. Pluim J. P. W., Maintz J. B. A., Viergever M. A. F-Information measures inmedical image registration. IEEE Trans. on Medical Imaging,2004,23(12):1508-1516.
[149]. Liao R., Guetter C., Xu C., Sun Y., Khamene A. and Sauer F. Leaning-based2D/3D rigid registration using Jensen-Shannon divergence for image-guidedsurgey. In Proc. International Conference on Medical Image Computing andComputer-Assisted Intervention,2005:255-262.
[150]. He Y., Hamza A. B., and Krim H. A generalized divergence measure for robustimage registration. IEEE Trans. on Signal Process.,2003,51(5):1211-1220.
[151]. Wang S. H., You, H. J. and Fu K. BFSIFT: a novel method to find featurematches for SAR image registration. IEEE Trans.on Geoscience and RemoteSensing Letters,2012,9(4):649-653.
[152]. Hachama M., Desolneux A., Richard, F. J. P. A Bayesian technique for imageclassifying registration. IEEE Trans. on Image Processing,2012,21(9):4080-4091.
[153].李琦，姬红兵，同鸣.一种多模态医学影像鲁棒配准方法.西安电子科技大学学报，2011,38(6):30-36.
[154]. Tan T. N., Sun Z. N. Ordinal Representations for Biometrics Recognition.Proceedings of15th European Signal Processing Conference, Poznan, Poland:EURASIP,2007:35-39.
[155]. Han Y. F., Tan T. N., Sun Z. N., et al. Embedded Palmprint Recognition Systemon Mobile Devices. ICB2007, LNCS4642, Seoul, Korea,2007:1184-1193.
[156]. Sun Z. N., Tan T. N., Wang Y. H., et al. Ordinal Palmprint Representation forPersonal Identification. Proceedings of IEEE Computer Society Conference onComputer Visiton and Pattern Recognition,2005,1:279-284.
[157]. Sun Z. N., Tan T. N., Wang Y. H., et al. Robust Encoding of Local OrdinalMeasures: a General Framework of Iris Recognition. Biometric Authentication,Lecture Notes in Computer Science Volume3087,2004:270-282.
[158]. Gupta R., Mittal A. Illumination and Affine-Invariant Point Matching using anOrdinal Approach. Proceedings of IEEE11th International Conference onComputer Visiton,2007:1-8.
[159]. Theodoridis S.等著，李晶皎等译.模式识别（第二版）.北京:电子工业出版社,2004.
[160].李在铭等编著.数字图像处理、压缩与识别技术.成都：电子科技大学出版社,2000.
[161]. Gholipour A., Kehtarnavaz N., Briggs R., et al. Brain Functional Localization:A Survey of Image Registration Techniques. IEEE Trans. on Medical Imaging,2007,26(4):427-451.
[162]. Loeckx D., Slagmolen P., Maes F., Vandermeulen D., and Suetens P. NonrigidImage Registration Using Conditional Mutual Information. IEEE Trans. onMedical Imaging,2010,29(1):19-29.
[163]. Valle Y. D., Venayagamoorthy G. K., Mohagheghi S., et al. Particle SwarmOptimization: Basic Concepts, Variants and Applications in Power Systems.IEEE Trans. on Evolutionary Computation,2008,12(2):171-195.
[164].冯林,张名举,贺明峰等.用改进的粒子群算法实现多模态刚性医学图像的配准.计算机辅助设计与图形学学报,2004,16(9):1269-1274.
[165]. Van den Bergh F. An Analysis of Particle Swarm Optimizers, PhD thesis.Department of Computer Science, University of Pretoria, South Africa,2002.
[166].胡顺波,刘常春.医学图像配准中的数据抽样方法研究.光电子激光,2008,19(2):237-241.
[167].冯林,严亮,贺明峰等.图像配准中确定性扰动PV插值算法.计算机辅助设计与图像图形学学报,2005,17(5):908-914.
[168].左奇,史忠科.插值方法对互信息局部极值的影响分析.中国图像图形学报,2003,8(3):281-285.
[169]. Keith A. Johnson. The Whole Brain Atlas. http://www.med.harvard. edu/AANLIB/home.html.
[170]. McConnell Brain Imaging Center Montreal Neurological Institute, McGillUniv., Montreal, QC, Canada. BrainWeb. http://mouldy.bic.mni.mcgill. ca/brainweb.
[171]. Xu M., Chen H., and Varshney P. K. Ziv-Zakai Bounds on Image Registration.IEEE Trans. on Signal Processing,2009,57(5).1745–1755.
[172]. Zhang J. P., Li S. Z., Wang J. Intelligent Multimedia Processing with softComputing. Heidelberg: Springer-Verlag,2004.
[173]. Tenenbaum J.B., V N de S., Langford J.C. A global geometric framework fornonlinear dimensionality reduction. Science,2000,290(5500):2319-2323.
[174]. Roweis S.T., Saul L.K. Nonlinear dimensionality reduction by locally linearembedding. Science,2000,290(5500):23-42.
[175]. Li Q., Ji H. B. Multimodality Image Registration Using Local LinearEmbedding and Hybrid Entropy. Neurocomputing.2013,111:34-42.
[176]. Zhan D.C, Zhou Z.H. Neighbor line-based locally linear embedding. In: Proc.of the10th Pacific-Asia Conference on Knowledge Discovery and Data Mining,Singapore:1023-1033.
[177]. Donoho D.L., Grimes C. Hessian eigenmaps: New locally linear embeddingtechniques for high-dimensional data. In: Proc. of the National Academy ofSciences,2003,100(10):5591-5596.
[178]. Ridder D., Kouropteva O., Okun O. Supervised locally linear embedding. In:Proc. Joint International Conference on CANN/ICONIP, Lecture Notes inComputer Science,2003,2714, Springer Verlag, Berlin:333-341.
[179]. Zhang C.S, Wang J., Zhao N.Y, Zhang D. Reconstruction and analysis ofmulti-pose face images based on nonlinear dimensionality reduction. PatternRecognition,2004,37(1):325-336.
[180].吴晓荣,何明一,张易凡.基于多小波分解的多光谱图像矢量融合.电子与信息学报,2007,29(4):789-794.
[181].胡良梅,高隽,何柯峰.图像融合质量评价方法的研究.电子学报,2004,32(12A):218-221
[182].焦李成,侯彪,王爽等.图像多尺度几何分析理论与应用--后小波分析理论与应用.西安：西安电子科技大学出版社,2008.
[183]. Ali F. E., El-Dokany I. M., Saad A. Fusion of MR and CT Images Using theCurvelet Transform.25th National Radio Science Conference Faculty ofEngineering, Tanta Univ., Egypt,2008,3:1-8.
[184]. Fluck O., Vetter C., Wein W., et al. A survey of medical image registration ongraphics hardware. Computer Methods and Programs in Biomedicine,2011,104(3): e45-e57.
[185]. piclin., Bo tjan L., Pernu F. Groupwise registration of multimodal imagesby an efficient joint entropy minimization scheme. IEEE Trans. on ImageProcessing,2012,21(5):2546-2558.
[186]. Liao S. and Chung Albert. C. S. Nonrigid brain MR image registration usinguniform spherical region descriptor. IEEE Trans. on Image Processing,2012,21(1):157-169.
[187]. Benoit M Dawant. Non-rigid registration of medical images: purpose andmethods, a short survey. IEEE, International Symposium on BiomedicalImaging,2002:465-468.
[188]. Kyriacou S. K., Davatzikos C. Nonlinear elastic registration of brainimageswith tumor pathology using a biomechanical model [MRI]. IEEE Trans. onMedical Imaging,1999,18:580-592.
[189]. Ashburner J., Friston K. J. Nonlinear functions spatial normalization using basis,Human Brain Mapping,1999,7:254-266.
[190]. Xie Z., Farin G. E. Image registration using hierarchical B-splines. IEEE, Trans.on Visualization and Computer Graphics,2004,10(1):85-94.
[191]. D′ez Y., Oliver A., Llad′o X., et al. Revisiting intensity-based imageregistration applied to mammography. IEEE Trans. on Information Technologyin Biomedicine,2011,15(5):716-725.
[192]. Liu D. C., Nocedal J.. On the limited memory BFGS method for large scaleoptimization. Mathematical Programming,1989,45:503-528.
[193]. Morales J. L. A mumerical study of limited memory BFGS methods. AppliedMathematics Letters,2002,15(4):481-487.
[194]. Zhou C. Y., Byrd R. H., Lu P. H., et al. Algorithm778: L-BFGS-B: Fortransubroutines for large-scale bound constrained optimization. ACM Transactionson Mathematical Software (TOMS),1997,23(4):550-560.
[195]. Morales J. L., Nocedal J.. Remark on “algorithm778: L-BFGS-B: Fortransubroutines for large-scale bound constrained optimization”. ACM Transactionson Mathematical Software (TOMS),2011,38(1):1-4.
[196]. Hellier P, Barillot Ch. Cooperation between local and global approaches toregister brain images. Int Conf on Information Processing in Medical Imaging,IPM01. Insana M F, Leahy R M, eds. Davis, California. Lecture Notes inComputer Science2082,2001.
[197]. Diplomarbeit. Physics-based nonrigid registration for medical image analysis.Master Thesis. Aus dem Institut fur Medizinische Informatik der MedizinischenUniversitat zu L ubeck,2001.
[198]. Bro-Nielsen M, Gramkow C. Fast fluid registration of medical images.Visualization in Biomedical Computing, Hamburg, Lecture Notes in ComputerScience,1996,1131:265-276.
[199]. Wollny G, Kruggel F. Computional cost of nonrigid registration algorithmsbased on fluid dynamics. IEEE Trans. on Medical Imaging,2002,21(8):946-953.
[200]. Belkin M., Niyogi P. Laplacian Eigenmaps and spectral techniques forembedding and clustering. Advances in Neural Information Processing Systems,2002,14:585-591.
[201]. Belkin M., Niyogi P. Laplacian Eigenmaps for dimensionality reduction anddata representation. Neural Computation,2003,5(6):1373-1396.
[202]. Zhang Z., Zha H. Principal manifolds and nonlinear dimensionality reductionvia tangent space alignment. SIAM J. Scientific Computing,2004,26(1):313-338.
[203]. Yang J., Li F. X., Wang J. A better scaled local tangent space alignmentalgorithm. Journal of Software,2005,16(9):1584-1590.
[204]. Zhang P., Qiao H., Zhang B. An improved local tangent space alignmentmethod for manifold learning. Pattern Recognition Letters,2011,32:181-189.
[205]. He X. F., Niyogi P. Locality preserving projections. Advances in NeuralInformation Processing Systems,2003,16:153-160.
[206]. He X. F., Yan S. C., Hu Y. X., et a1. Learning locality preserving subspace forvisual recognition. Proc. Ninth IEEE Int. Conf. Computer Vision,2003:385-392.
[207]. He X. F., Yah S. C., Hu Y. X., et a1. Face recognition using Laplacianfaces.IEEE Trans. on Pattern Analysis and Machine Intelligence,2005,27(3):328-340.
[208]. He X. F., Cai D., Yan S. C., et a1. Neighborhood preserving embedding. Proe.10th IEEE Int. Conf. Computer Vision,2005:1208-1213.
[209]. Wang Y., Wu Y. Complete neighborhood preserving embedding for facerecognition. Pattern Recognition,2010,43(3):1008-1015.
[210]. Zhang D. M., Liu H. Y., Li L., Luo B. Image recognition with extension ofneighborhood preserving embedding on matrices. Journal of information&computational science,2012,9(6):1511-1520.
[211]. Pang Y. W., Zheng L., Liu Z. K., et a1. Neighborhood preserving projections(NPP): a novel linear dimension reduction method. Proc. ICIC,2005:117-125.
[212]. Pang Y. W., Yu N. H., Li H. Q., et a1. Face recognition using neighborhoodpreserving projections. Proc. PCM,2005:854-864.
[213]. Kokiopoulou E., Saad, Y. Orthogonal neighborhood preserving projections: aprojection-based dimensionality reduction technique. IEEE Trans. on patternanalysis and machine intelligence,2007,29(12):2143-2156.
[214]. Zhang T. H., Huang K. Q., Li X. L., Yang J. and Tao D. C. Discriminativeorthogonal neighborhood-preserving projections for classification. IEEE Trans.on systems, man and cybernetics-part B: cybernetics,2010,40(1):253-263.
[215]. Hamm J., Ye D. H., Verma R., et al. GRAM: A frame work for geodesicregistration on anatomical manifolds. Medical Image Analysis,2010,14:633-642.
[2]. Aristeidis S., Christos D., Nikos P. Deformable medical image registration: asurvey. IEEE Trans. on Medical Imaging,2013,32(7):1153-1190.
[3]. Zitova B., Flusser J. Image registration methods: a survey. Image and VisionComputing,2003,21:977-1000.
[4]. Maintz J.B.A., Viergever M.A. A survey of medical image registration. MedicalImage Analysis,1998,2(1):1-37.
[5]. Pluim J.P.W., Maintz J.B.A., Viergever M.A. Mutual-information basedregistration of medical images: a survey. IEEE Trans on Medical Imaging,2003,22(8):986-1004.
[6]. Barillot C., Lemoine D. Data fusion in medical imaging: merging multimodaland multipatient images, identification of structures and3D display aspects.European joumal of radiology,1993,17:22-27.
[7]. Petra A., Elsen V. Medical image matching-a review with classification. IEEETrans on biomedical engineering,1993,16:26-39.
[8]. Michael Fitzpatrick.J. The Retrospective Image Registration Evaluation Project.http://www. insight-journal. org/rire/.
[9]. Roche A., Pennec X., Malandain G., and Ayache N. Rigid registration of3-Dultrasound with MR images: A new approach combining intensity and gradientinformation. IEEE Trans. on Medical Imaging,2001,20(10):1038-1049.
[10]. Wein W., Brunke S., Khamene A., Callstrom M. R., and Navab N. AutomaticCT-ultrasound registration for diagnostic imaging and image-guidedintervention. Medical Image Analysis,2008,12(5):577-585.
[11]. Maintz J. B. A., van den Elsen P. A., and Viergever M. A.3D multimodalitymedical image registration using morphological tools. Image Vis. Comput.,2001,19(1-2):53-62.
[12]. Haber E. and Modersitzki J. Intensity gradient based registration and fusion ofmulti-modal images. Methods Inf. Med.,2007,46(3):292-299.
[13]. Woods, R. P., Mazziotta, J. C., Cherry, S. R. MRI-PET registration withautomated algorithm. Journal of Computer Assisted Tomography.1993,17(4):536-546.
[14]. Hill, D. L. G., Hawkes, D. J., Harrison, N. A., Ruff, C. F. A strategy forautomated multimodality image registration incorporating anatomicalknowledge and image characteristics. Information Processing in MedicalImaging.1993,687:182-196.
[15]. Collignon A., Vandermeulen D., Suetens P., and Marchal G.3-D multimodalitymedical image registration using feature space clustering. In Proc. First Int.Conf. Computer Vistion, Virtual Reality and Robotics in Medicine(CVRMED’95), Lecture Notes in Computer Science, France, Apr.1995,905:195-204.
[16]. Maes F., Collignon A., Vandermeulen D., et a1. Multimodality imageregistration by maximization of mutual information. IEEE Trans. on MedicalImaging,1997,16(2):187-198.
[17]. Collignon A., Maes F., Delaere D., Vandermeulen D., Suetens P., Marchal G.Automated multi-modality image registration based on information theory. InProc.14th Int. Conf. Information Processing in Medical Imaging (IPMI’95),Computational Image and Vision. France,1995,3:263-274.
[18]. Viola P. A., Wells III, W. M. Alignment by maximization of mutual information.International Conference on Computer Vision, IEEE Computer Society Press.1995:16-23.
[19]. Wells III, W. M., Viola P., Atsumi H., Nakajima S., Kikinis R. Multi-modalvolume registration by maximization of mutual information. Medical ImageAnalysis.1996,1:35-51.
[20]. Shannon C. E. A mathematical theory of communication. In Bell SystemTechnical Journal,1948,27:379-423.
[21]. Studholme, C., Hill, D. L. G, Hawkes, D. J. An overlap invariant entropymeasure of3d medical image alignment. Pattern Recognition,1999,32(1):71-86.
[22]. Ronald W. K. So, Tommy W. H. Tang and Albert C. S. Chung. Non-rigid imageregistration of brain magnetic resonance images using graph-cuts. PatternRecognition,2011,44(10-11):2450-2467.
[23]. Gan R., Chung A. C. S., Liao S. Maximum distance-gradient for robust imageregistration. Medical Image Analysis,2008,12:452-468.
[24]. Pluim J. P. W., Maintz J. B. A., and Viergever. M. A. Image registration bymaximization of combined mutual information and gradient information. IEEETrans. on Medical Imaging,2000,19(8):809-814.
[25]. Rueckert D., Clarkson M. J., Hill D. L. G., et al. Non-rigid registration usinghigher-order mutual information. Proceedings of SPIE Medical Imaging2000:Image Processing, San Diego CA,2000:438-447.
[26]. Thevenaz P., Unser M. Optimization of mutual information for multiresolutionimage registration. IEEE Trans on Image Processing,2000,9(12):2083-2099.
[27]. Chen H. M., Varshney P. K. A pyramid approach for multimodality imageregistration based on mutual information. In Proceedings of the ThirdInternational Conference on Information Fusion,2000,1: MOD3/9-MOD3/15.
[28].陈武凡，小波分析及其在医学图像处理中的应用，北京：科学出版社，2002.
[29]. Foroosh H., Zerubia J. B., and Berthod M. Extension of phase correlation tosubpixel registration. IEEE Trans. on Image Processing,2002,11:188-200.
[30]. Reddy B. S. and Chatterji B. N. An FFT-based technique for translation,rotation, and scale-invariant image registration. IEEE Trans. on ImageProcessing,1996,5:1266-1271.
[31]. Modersitzki J. Numerical Methods for Image Registration: Oxford UniversityPress.2004.
[32]. Broit C. Optimal registration of deformed images. Dissertation AbstractsInternational Part B: Science and Engineering [DISS. ABST. INT. PT. B-SCI.&ENG],1982,42(11):1982.
[33]. Bajcsy R., Lieberson R., Reivich M. A Computerized System for the ElasticMatching of Deformed Radiographic Images to Idealized Atlas Images. Journalof Computer Assisted Tomography,1983,7(4):618-625.
[34]. Gee J. C., Haynor D. R., Reivich M., et a1. Finite element approach to warpingof brain images. Medical Imaging,1994:327-337.
[35]. Guyader C. Le and Vese L. A. A combined segmentation and registrationframework with a nonlinear elasticity smoother. Comput. Vis. ImageUnderstand.,2011,115(12):1689-1709.
[36]. Burger M., Modersitzki J., and Ruthotto L. A hyperelastic regularization energyfor image registration. SIAM J. Sci. Comput.,2013,35(1): B132-B148.
[37]. Christensen G E., Johnson H. J. Consistent image registration. IEEE Trans. onMedical Imaging,2001,20(7):568-582.
[38]. Chiang M. C., Leow A. D., Klunder A.D., et a1. Fluid registration of diffusiontensor images using information theory. IEEE Trans. on Medical Imaging,2008,27(4):442-456.
[39]. Christensen G E., Rabbitt R. D., Miller M. I. Deformable templates using largedeformation kinematics. IEEE Trans. on Image Processing,1996,5(10):1435-1447.
[40]. Christensen G. E., Joshi S. C., Miller M. I. Volumetric transformation of brainanatomy. IEEE Trans. on Medical Imaging,1997,16(6):864-877.
[41]. Christensen G. E. Deformable shape models for anatomy. WashingtonUniversity,1994.
[42]. Vercauteren T., Pennec X., Perchant A., and Ayache N. Symmetric log-domaindiffeomorphic registration: A demons-based approach. in Int. Conf. Med. ImageComput. Comput.-Assist. Intervent.,2008:754-761.
[43]. Cahill N. D., Noble J. A., and Hawkes D. J. Demons algorithms for fluid andcurvature registration. in Proc. Int. Symp. Biomed. Imag.,2009:730-733.
[44]. Cahill N. D., Noble J. A., and Hawkes D. J. A Demons algorithm for imageregistration with locally adaptive regularization. in Proc. Int.l Con. Med. ImageComput. Comput.-Assist. Intervent.,2009:574-581.
[45]. Mansi T., Pennec X., Sermesant M., Delingette H., and Ayache N. Ilogdemons:A demons-based registration algorithm for tracking incompressible elasticbiological tissues. Int. J. Comput. Vis.,2011,92(1):92-111.
[46]. Thirion J. P. Image matching as a diffusion process: an analogy with Maxwell’sDemons. Medical Image Analysis,1998,2:243-260.
[47]. Thirion J. P. Non-rigid matching using demons. Image Matching as a DiffusionProcess: An Analogy with Maxwell’s Demons, Medical Image Analysis,1998,2(3):243-260.
[48]. Risser L., Vialard F., Wolz R., Murgasova M., Holm D. D., and Rueckert, D.Simultaneous multi-scale registration using large deformation diffeomorphicmetric mapping. IEEE Trans. on Medical Imaging,2011,30(10):1746-1759.
[49]. Sommer S., Nielsen M., Lauze F., and Pennec X. A multi-scale kernel bundlefor lddmm: Towards sparse deformation description across space and scales. inProc. Int. Conf. Inf. Process. Med. Imag.,2011:624-635.
[50]. Morton K. W., Mayers D. F. Numerical Solution of Partial DifferentialEquations. Cambridge University Press,2006.
[51]. Buhmann M. D. Radial basis functions. Acta Numerica2000,2000,9(0):1-38.
[52]. Powell M. J. D. Radial basis functions for multivariate interpolation: A review.In Conf.1st Algorithms for Approximation (inst Math. Its Appl. Conf. Series).1987:143-167.
[53]. Powell M. J. D. The theory of radial basis function approximation in l990. InAdvances in numerical analysis. V01.2: Wavelets, subdivision algorithms, andradial basis functions, Proc.4th Summer Sch., Lancaster/UK.1990:2.
[54]. Fornefett M., Rohr K., Stiehl H. S. Radial basis functions with compact supportfor elastic registration of medical images. Image and Vision Computing,2001,19(12):87-96.
[55]. Yang X., Xue Z., Liu X., and Xiong D. Topology preservation evaluation ofcompact-support radial basis functions for image registration. Pattern Recognit.Lett.,2011,32(8):1162-1177.
[56]. Rohr K., W rz S. An extension of thin-plate splines for image registration withradial basis functions. in Proc. Int. Symp. Biomed. Imag.,2012:442-445.
[57]. W rz S. and Rohr K. Physics-based elastic registration using non-radial basisfunctions and including landmark localization uncertainties. Comput. Vis.Image Understand.,2008,111(3):263-274.
[58]. Mattes D., Haynor D. R., Vesselle H., et a1. PET-CT image registration in thechest using free-form deformation. IEEE Trans on Medical Imaging.2003,20(1):120-128.
[59]. Kybic J., Unser M. Fast parametric elastic image registration. IEEE Trans onImage Processing,2003,12(11):1427-1442.
[60]. Jiang J., Luk W., and Rueckert D. FPGA-based computation of free-formdeformations. In IEEE International Conference on Field ProgrammableTechnology. IEEE Computer Society Press,2002.
[61]. Rueckert D., Sonoda L I., Hayes C., Hill D. L. G., Leach M. O., and Hawkes D.J.. Non-rigid registration using free-form deformations: Application to breastMR images. IEEE Trans. on Medical Imaging,1999,18(8):712-721.
[62]. Torsten R, Calvin R M, David A B. Volume-preserving nonrigid registration ofMR breast images using free-form deformation with all incompressibilityconstraint. IEEE Trans. on Medical Imaging,2003,22(6):730-741.
[63]. T.Metz C., Klein S., Schaap M., VanWalsum T., and Niessen W. J. Nonrigidregistration of dynamic medical imaging data using nd+t b-splines and agroupwise optimization approach. Medical Image Analysis,2011,15(2):238-249.
[64]. Shi W., Zhuang X., Pizarro L., Bai W., Wang H., Tung K.-P., Edwards P., andRueckert D. Registration using sparse free-form deformations. in Proc. Int.Conf. Med. Image Comput. Comput.-Assist. Intervent.,2012:659-66.
[65]. Sotiras A. and Paragios N. Discrete symmetric image registration. in Proc. Int.Symp. Biomed. Imag.,2012:342-345.
[66]. Cootes T. F., Twining C. J., Petrovi V. S., Babalola K. O., and Taylor C. J.Computing accurate correspondences across groups of images. IEEE Trans.onPattern Analysis and Machine Intelligence,2010,32(11):1994-2005.
[67]. Buerger C., Schaeffter T., and King A. P. Hierarchical adaptive local affineregistration for fast and robust respiratory motion estimation. Medical ImageAnalysis,2011,15(4):551-564.
[68]. Van den Elsen P. A., Maintz J. B. A., Pol E. J. D., and Viergever M. A.Automatic registration of CT and MR brain images using correlation ofgeometrical features. IEEE Trans. on Medical Imaging,1995,14(2):384-398.
[69]. Verbeeck, R. Rinciples and practive of a workstation for the pre-operativeplanning of stereotactic neurosurgical interventions: from implementation toclinical evalumion. Belgium: Leuven,1996.
[70]. Gildenberg, P. L., Tasker, R. R. Textbook of stereotactic and functionalneurosurgery. New York, NY: McGraw-Hill.1998.
[71]. Simon, D. A., O’Toole, R. V., Blackwell, M., Morgan, F., Digioia, A. M.,Kanade, T. Accuracy validation in image-guided orthopaedic surgery. InMedical Robotics and Computer Assisted Surgery.1995:185-192.
[72]. Ellis, R. E., Toksvig-Larsen, S., Marcacci, M., Caramella, D., Fadda, M. Abiocompatible fiduical marker for evaluating the accuracy of CT imageregistration. Computer Assisted Radiology.1996,1124:693-698.
[73]. Biswal, B. B., Hyde, J. S. Contour-based registration technique to differentitatebetween task-activated and head motion-induced calibration for freehand3Dultrasound. Medical Image Computing and Computer-Assisted Intervention.2000,1935:462-471.
[74]. Declerck,J., Feldmar,J., Goris, M. L., Betting, F. Automatic registration andalignment on a templated of cardiac stress and rest reoriented SPECT images.IEEE Trans. on Medical Imaging.1997,16(6):727-737.
[75]. Maintz J. B. A., van den Elsen P. A., and Viergeveg M. A. Comparison ofedge-based and ridge-based registration of CT and MR brain images. MedicalImage Analysis,1996,1(2):151-161.
[76]. Maintz J. B. A., van den Elsen P. A., and Viergever M. A. Evaluation of ridgeseeking operators for multimodality medical image matching. IEEE Trans. onPattern Analysis and Machine Intelligence,1996,18(4):353-365.
[77]. Grimson, W. E. L., Ettinger, G. J., White, S. J., Lozano-Perez, T., Wells, W. M.,Kikinis, R. An automation registration method for frameless stereotaxy, imageguided surgery, and enhanced reality visualization. IEEE Trans. on MedicalImaging.1996,15(2):129-140.
[78]. Herring, J. L., Dawant, B. M., Maurer, C. R., Muratore, D. M., Galloway, R. L.,Fitzpatrick, J. M. Surfact-based registration of CT images to physical space forimage-guided surgery of the spine: a sensitivity study. IEEE Trans. on MedicalImaging.1998,17(5):743-761.
[79]. Szeliski, R., Lavallee, S. Matching3-D anatomical surfaces with non-rigiddeformations using octree-splines. International Journal of Computer Vision.1996,18(2):171-186.
[80]. Gonzales R. C. and Woods R. E. Digital Image Processing,2nd ed. UpperSaddle Rivef, NJ: Prentice-Hall.2002.
[81]. Bajcsy, R., Kovacic, S. Multiresolution elastic matching. Computer Vision,Graphics and Image Processing.1989,46:1-21.
[82]. Cachier, P. Pennec, X.3D non-rigid registration by gradient descent on aGaussian-windowed similarity measure using convolutions. In MatchematicalMethods in Biomedical Image Analysis, IEEE Computer Society Press, LosAlamitos, CA.2000:182-189.
[83]. Lemieux, L., Wieshmann, U. C., Moran, N. F., Fish, D. R., Shorvon, S. D. Thedetection and significance of subtle change in mixed-signal brain lesions byserial MRI scan matching and spatial normalization. Medical Image analysis.1998,2(3):227-242.
[84]. Gee, J. C., Haynor, D. R., Briquer, L. Le., Bajcsy, R. K. Advances in elasticmatching theory and its implementation. Proceeding of Computer Vision,Virtual Reality and Robotics in Medicine and Medical Robotics andComputer-Assisted Surgery.1997,1205:63-72.
[85]. Ashbumer, J., Friston, K. J. Nonlinear spatial normalization using basisfunctions. Human Brain Mapping.1999,7:254-266.
[86]. Collignon A. Multi-modality medical image registration by maximization ofmutual information. Leuven: Catholic University of Leuven.1998.
[87]. Collignon A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P., Marchal, G.Automated multi-modality image registration based on information theory.Information Processing in Medical Imaging.1995:263-274.
[88]. Viola P. A., Wells III, W. M. Alignment by maximization of mutual information.International Conference on Computer Vision, IEEE Computer Society Press.1995:16-23.
[89]. Viola P. A. Alignment by maximization of mutual information. Boston:Massachusetts Institute of Technology.1995.
[90]. Wells III, W. M., Viola, P., Kikinis, R. Multi-modal volume registration bymaximization of mutual information. Medical Robotics and Computer AssistedSurgery.1995:55-62.
[91]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Multiresolution voxel similaritymeasures for MR-PET registration. Proceedings of the Intemational Conferenceon Information Processing in Medical Imaging (IPMI).1995,3:287-298.
[92]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Automated3-D registration of MRand CT images of the head. Medical Image Analysis.1996,1(2):163-175.
[93]. Studholme, C., Hill, D. L. G, Hawkes, D. J. Automated three-dimensionalregistration of magnetic resonance and positron emission tomography brainimages by multiresolution optimization of voxel similarity measure. MedicalPhysics.1996,24(1):25-35.
[94]. Wells III, W. M., Viola P., Atsumi H., Nakajima S., Kikinis R. Multi-modalvolume registration by maximization of mutual information. Medical ImageAnalysis.1996,1:35-51.
[95]. Meyer, C. R., Boes, L. J., Kim, B., Bland, P. H., Zasadny,K. R., Kison, P. V,Koral, K., Frey,K. A., Wahl, R. L. Demonstration of accuracy and clinicalversatility of mutual information for automatic multimodality image fusionusing affine and thin-plate spline warped geometric deformations. MedicalImage Analysis.1996,1(3):195-206.
[96]. Glasbey C. A., Mardia K. V. A review of image-warping methods. Journal ofApplied Statistics,1998,25(2):155-171.
[97]. Holden M. A Review of Geometric Transformations for Nonrigid BodyRegistration. IEEE Trans. on Medical Imaging,2008,27(1):111-128.
[98]. Lester H., Arridge S. R. A survey of hierarchical non-linear medical imageregistration. Pattern Recognition,1999,32(1):129-149.
[99]. Fogel D. N., Type R. Image Registration using Multiquadric Functions, theFinite Element Method, Bivariate Mapping Polynomials and Thin Plate Spline.1996, National Center for Geographic Information and Analysis: Santa Barbara,California.
[100]. Christensen G. E. Consistent linear-elastic transformations for image matching.Information Processing in Medical Imaging,1999:224-237.
[101]. Amit Y. A nonlinear variational problem for image matching. SIAM J. Sci.Comput,1994,15(1):207-224.
[102]. Gefen S., Tretiak E., Nissanov J. Elastic3D alignment of rat brain histologicalimages. IEEE Trans. on Medical Imaging,2003,22(11):1480-1489.
[103]. Wu Y. T., Kanade T., Li C. C., et al. Image Registration Using Wavelet-BasedMotion Model. International Joumal of Computer Vision,2000,38(2):129-152.
[104]. Wu Y T., Chen L. F., Lee P. L., et a1. Discrete signal matching usingcoarse-to-fine wavelet basis functions. Pattern Recognition,2003,36(1):171-192.
[105]. Yang J., Wang Y., Tang S., et a1. Multiresolution Elastic Registration of X-RayAngiography Images Using Thin-Plate Spline. IEEE Trans. on Nuclear Science,2007,54(1):152-166.
[106]. Bookstein F. L. Principal warps: thin-plate splines and the decomposition ofdeformations. IEEE Trans. on Pattern Analysis and Machine Intelligence,1989,11(6):567-585.
[107]. Rohr K., Fomefett M., Stiehl H. S. Approximating Thin-Plate Splines for ElasticRegistration: Integration of Landmark Errors and Orientation Attributes.Information Processing in Medical Imaging,1999:252-265.
[108]. Li J., Yang X., and Yu J. Compact support thin plate spline algorithm. J.Electron.(China),2007,24(4):515-522.
[109]. Rohr K. and W rz, S. An extension of thin-plate splines for image registrationwith radial basis functions. in Proc. Int. Symp. Biomed. Imag.,2012:442-445.
[110]. Rabbitt R. D., Weiss J. A., Christensen G. E. and Miller M. I. Mapping ofhyperelastic deformable templates using the finite element method. InProc.SPIE Vis. Geometry,1995:252-265.
[111]. Horn B. K. P., Schunck B. G. Determining Optical Flow. Artificial Intelligence,1981,17(1-3):185-203.
[112]. Barton J. L., Fleet D. J., Beauchemin S. S.. Performance of optical flowtechniques. International Journal of Computer Vision,1994,12(1):43-77.
[113]. Wang H., Dong L., O’Daniel J. Validation of an accelerated demons algorithmfor deformable image registration in radiation therapy. Phys. Med. Biol.,2005,50(12):2887-2905.
[114]. Rogelj P., Kovai S. Symmetric image registration. Medical Image Analysis,2006,10(3):484-493.
[115].林相波,邱天爽,阮素. Demons非刚性配准算法拓扑保持性的研究.自动化学报,2010,36(1):179-183.
[116].许鸿奎,江铭炎,杨明强.基于改进光流场模型的脑部多模医学图像配准.电子学报,2012,40(3):525-529.
[117].朱雪龙.应用信息论基础.北京：清华大学出版社,2000.
[118]. Holden, M., Hill, D. L. G, Jarosz, J. M., Cox, T. C. S., Rohlfing, T., Goodey, J.,Hawkes, D. J. Voxel similarity measures for3-D serial MR brain imageregistration. IEEE Trans. on Medical Imaging.2000,19:94-102.
[119]. Freire, L., Roche, A., Mangin, J. F. What is the best similarity measure formotion correction in fMRI a time series? IEEE Trans. on Medical Imaging.2002,21:470-484.
[120]. Radau, P. E., Slomka, P. J., Julin, P, Svensson, L., Wahlund, L. O. Automatedsegmentation and registration technique for hmpao-spect imaging ofAlzheimer’s patients. Proceedings of SPIE on Medical Imaging: ImageProcessing.2000,3979:372-384.
[121]. Fei, B., Wheaton, A., Lee, Z., Duerk,J. L., Wilson, D. L. Automatic MR volumeregistration and its evaluation for the pelvis and prostate. Physics in Medicineand Biology.2002,47(5):823-838.
[122]. Slomka, P. J., Mandel, J., Downey, D., Fenster, A. Evaluation of voxel-basedregistration of3-D power Doppler ultrasound and3-D magnetic resonanceangiographic images of carotid arteries. Ultrasound in Medicine and Biology.2001,27(7):945-955.
[123]. Holden, M., Hill, D. L. G, Denton, E. R. E., Jarosz, J. M., Cox,T. C. S., Rohlfing,T., Goodey, J., Hawkes, D. J. Voxel similarity measures for3-D serial MR brainiamge registration. IEEE Trans. on Medical Imaging.2000,19(2):94-102.
[124]. Studholme, C., Cardenas, V, Weiner, M. Multi scale image and multi scaledeformation of brain anatomy for building average brain atlases. Proceedings ofSPIE in Medical Imaging: Image Processing.2001,4322:557-568.
[125]. Studholme, C., Novotny, E, Zubai, I. G., Duncan, J. S. Estimating tissuedeformation between functional images induced by intracranial electrodeimplantation using anatomical MRI. Neurolmage.2001,13(4):561-576.
[126]. Shekhar, K., Zagrodsky, V. Mutual information-based rigid and nonrigidregistration of ultrasound volumes. IEEE Trans. on Medical Imaging.2002,21(1):1660-1668.
[127]. Luan H., Qi F., Xue Z., Chen L., Shen D. Multimodality image registration bymaximization of quantitative-qualitative measure of mutual information. PatternRecognition.2007.
[128]. Luan H., Qi F., Shen D. Multi-model image registration byquantitative-qualitative measure of mutual information (Q-MI). ComputerVision for Biomedical Image applications, ICCV2005workshop, October21,Beijing, China.2005:378-387.
[129]. Krol, Z., Zerfass, P., Rymon-Lipinski, B., Jansen, T., Hauck,W., Zeilhofer,H. F.,Sader, R., Keeve, E. Computer aided osteotomy design for harvestingautologous bone grafts in reconstructive surgery. Proceedings of SPIE, MedicalImaging: Visualization, Image Display, and Image-guided Procedures.2001,4319:244-251.
[130]. Denton, E. R. E., Holden, M., Christ, E., Jarosz, J. M., RussellHones, D.,Goodey, J., Cox, T. C. S., Hill. D. L. G. The identification of cerebral volumechanges in treated growth hormonedeficient adults using serial3D MR imageprocessing. Journal of Computer Assisted Tomography.2000,24(1):139-145.
[131]. Ourselin, S., Roche, A., Prima, S., Ayache, N. Block matching: a generalframework to improve robustness of rigid registration of medical images.Proceedings of Lecture Notes in Computer Science, Medical Image Computingand Computer-Assisted Intervention.2000,1935:557-566.
[132]. Van Laere, K., Koole, M., D’Asseler, Y., Versijpt, J., Audenaert, K., Dumont, E.,Dierckx, R. Automated stereotactic standardization of brain SPECT receptordata using single-photon transmission images. Joumal of Nuclear Medicine.2001,42(2):361-375.
[133]. Jenkinson, M., Smith, S. A global optimization method for robust affineregistration of brain images. Medical Image analysis.2001,5(2):143-156.
[134]. Holden, M. Registration of3D serial MR brain images. London: University ofLondon.2001.
[135]. Horsfield, M. A. Mapping eddy current induced fields for the correction ofdiffusion-weighted echo planar images. Magnetic Resonance Imaging.1999,17(9):1335-1345.
[136]. Otte, M. Elastic registration of fMRI data using Bezier-spline transformations.IEEE Trans. on Medical Imaging.2001,20(3):193-206.
[137]. Hellier, P., Barillot, C. Multimodal non-rigid warping for correction ofdistortions in function MRI. Proceedings of Lecture Notes in Computer Science,Medical Image Computing and Computer-Assisted Intervention.2000,1935:512-520.
[138]. Likar, B., Pernus, F. A Hierarchical approach to elastic registration based onmutual information. Image and Vision Computing.2001,19(12):33-44.
[139]. Maintz, J. B. A., Meijering, E. H. W., Viergever, M. A. General multimodalelastic registration based on mutual information. Proceedings of SPIE, MedicalImaging；Image Processing.1998,3338:144-154.
[140]. Lehman T. M., Gomner C., Spitzer K. Survey: interpolation methods in medicalimage processing. IEEE Trans. on Medical Imaging,1999,18(11):1049-1075.
[141]. Zhu, Y-M., Cochoif, S. M. Influence of implementation parameters onregistration of MR and SPECT brain images by maximization of mutualinformation. Journal of Nuclear Medicine.2002,43(2):160-166.
[142]. Netsch, T., Rosch, R., Weese, J., van Muiswinkel, A., Desmedt, P. Greyvalue-based3-D registration of functional MRI time-series: comparison ofinterplolation order and similarity measure. Proceedings of SPIE, MedicalImaging: Image Processing.2000,3979:1148-l159.
[143]. Pluim J. P. W., Maintz J. B. A., Viergever M. A. Interpolation artifacts in mutualinformation based image registration. Computer Vision and ImageUnderstanding,2000,77(2):211-232.
[144]. Tsao J. Interpolation artifacts in multimodality image registration based onmaximization of mutual information. IEEE Trans. on Medical Imaging,2003,22(7):854-864.
[145]. Studholme C., Hill D. L. G., Hawkes D. J. An ovedap invariant entropy measureof3D medical image alignment. Pattern Recognition,1999,32(1):71-86.
[146]. Maes F., Vandermeulen D., Suetens P. Comparative evaluation ofmultiresolution optimization strategies for multimodality image registration bymaximization of mutual information. Medical Image Analysis,1999,3(4):373-386.
[147]. Chen B. J., Li J. L., Chen G. Study of Medical Image Registration Based onSecond-Order Mutual Information. Proc. of the1st International Conference onBioinformatics and Biomedical Engineering, Wuhan: ICBBE,2007:956-959.
[148]. Pluim J. P. W., Maintz J. B. A., Viergever M. A. F-Information measures inmedical image registration. IEEE Trans. on Medical Imaging,2004,23(12):1508-1516.
[149]. Liao R., Guetter C., Xu C., Sun Y., Khamene A. and Sauer F. Leaning-based2D/3D rigid registration using Jensen-Shannon divergence for image-guidedsurgey. In Proc. International Conference on Medical Image Computing andComputer-Assisted Intervention,2005:255-262.
[150]. He Y., Hamza A. B., and Krim H. A generalized divergence measure for robustimage registration. IEEE Trans. on Signal Process.,2003,51(5):1211-1220.
[151]. Wang S. H., You, H. J. and Fu K. BFSIFT: a novel method to find featurematches for SAR image registration. IEEE Trans.on Geoscience and RemoteSensing Letters,2012,9(4):649-653.
[152]. Hachama M., Desolneux A., Richard, F. J. P. A Bayesian technique for imageclassifying registration. IEEE Trans. on Image Processing,2012,21(9):4080-4091.
[153].李琦，姬红兵，同鸣.一种多模态医学影像鲁棒配准方法.西安电子科技大学学报，2011,38(6):30-36.
[154]. Tan T. N., Sun Z. N. Ordinal Representations for Biometrics Recognition.Proceedings of15th European Signal Processing Conference, Poznan, Poland:EURASIP,2007:35-39.
[155]. Han Y. F., Tan T. N., Sun Z. N., et al. Embedded Palmprint Recognition Systemon Mobile Devices. ICB2007, LNCS4642, Seoul, Korea,2007:1184-1193.
[156]. Sun Z. N., Tan T. N., Wang Y. H., et al. Ordinal Palmprint Representation forPersonal Identification. Proceedings of IEEE Computer Society Conference onComputer Visiton and Pattern Recognition,2005,1:279-284.
[157]. Sun Z. N., Tan T. N., Wang Y. H., et al. Robust Encoding of Local OrdinalMeasures: a General Framework of Iris Recognition. Biometric Authentication,Lecture Notes in Computer Science Volume3087,2004:270-282.
[158]. Gupta R., Mittal A. Illumination and Affine-Invariant Point Matching using anOrdinal Approach. Proceedings of IEEE11th International Conference onComputer Visiton,2007:1-8.
[159]. Theodoridis S.等著，李晶皎等译.模式识别（第二版）.北京:电子工业出版社,2004.
[160].李在铭等编著.数字图像处理、压缩与识别技术.成都：电子科技大学出版社,2000.
[161]. Gholipour A., Kehtarnavaz N., Briggs R., et al. Brain Functional Localization:A Survey of Image Registration Techniques. IEEE Trans. on Medical Imaging,2007,26(4):427-451.
[162]. Loeckx D., Slagmolen P., Maes F., Vandermeulen D., and Suetens P. NonrigidImage Registration Using Conditional Mutual Information. IEEE Trans. onMedical Imaging,2010,29(1):19-29.
[163]. Valle Y. D., Venayagamoorthy G. K., Mohagheghi S., et al. Particle SwarmOptimization: Basic Concepts, Variants and Applications in Power Systems.IEEE Trans. on Evolutionary Computation,2008,12(2):171-195.
[164].冯林,张名举,贺明峰等.用改进的粒子群算法实现多模态刚性医学图像的配准.计算机辅助设计与图形学学报,2004,16(9):1269-1274.
[165]. Van den Bergh F. An Analysis of Particle Swarm Optimizers, PhD thesis.Department of Computer Science, University of Pretoria, South Africa,2002.
[166].胡顺波,刘常春.医学图像配准中的数据抽样方法研究.光电子激光,2008,19(2):237-241.
[167].冯林,严亮,贺明峰等.图像配准中确定性扰动PV插值算法.计算机辅助设计与图像图形学学报,2005,17(5):908-914.
[168].左奇,史忠科.插值方法对互信息局部极值的影响分析.中国图像图形学报,2003,8(3):281-285.
[169]. Keith A. Johnson. The Whole Brain Atlas. http://www.med.harvard. edu/AANLIB/home.html.
[170]. McConnell Brain Imaging Center Montreal Neurological Institute, McGillUniv., Montreal, QC, Canada. BrainWeb. http://mouldy.bic.mni.mcgill. ca/brainweb.
[171]. Xu M., Chen H., and Varshney P. K. Ziv-Zakai Bounds on Image Registration.IEEE Trans. on Signal Processing,2009,57(5).1745–1755.
[172]. Zhang J. P., Li S. Z., Wang J. Intelligent Multimedia Processing with softComputing. Heidelberg: Springer-Verlag,2004.
[173]. Tenenbaum J.B., V N de S., Langford J.C. A global geometric framework fornonlinear dimensionality reduction. Science,2000,290(5500):2319-2323.
[174]. Roweis S.T., Saul L.K. Nonlinear dimensionality reduction by locally linearembedding. Science,2000,290(5500):23-42.
[175]. Li Q., Ji H. B. Multimodality Image Registration Using Local LinearEmbedding and Hybrid Entropy. Neurocomputing.2013,111:34-42.
[176]. Zhan D.C, Zhou Z.H. Neighbor line-based locally linear embedding. In: Proc.of the10th Pacific-Asia Conference on Knowledge Discovery and Data Mining,Singapore:1023-1033.
[177]. Donoho D.L., Grimes C. Hessian eigenmaps: New locally linear embeddingtechniques for high-dimensional data. In: Proc. of the National Academy ofSciences,2003,100(10):5591-5596.
[178]. Ridder D., Kouropteva O., Okun O. Supervised locally linear embedding. In:Proc. Joint International Conference on CANN/ICONIP, Lecture Notes inComputer Science,2003,2714, Springer Verlag, Berlin:333-341.
[179]. Zhang C.S, Wang J., Zhao N.Y, Zhang D. Reconstruction and analysis ofmulti-pose face images based on nonlinear dimensionality reduction. PatternRecognition,2004,37(1):325-336.
[180].吴晓荣,何明一,张易凡.基于多小波分解的多光谱图像矢量融合.电子与信息学报,2007,29(4):789-794.
[181].胡良梅,高隽,何柯峰.图像融合质量评价方法的研究.电子学报,2004,32(12A):218-221
[182].焦李成,侯彪,王爽等.图像多尺度几何分析理论与应用--后小波分析理论与应用.西安：西安电子科技大学出版社,2008.
[183]. Ali F. E., El-Dokany I. M., Saad A. Fusion of MR and CT Images Using theCurvelet Transform.25th National Radio Science Conference Faculty ofEngineering, Tanta Univ., Egypt,2008,3:1-8.
[184]. Fluck O., Vetter C., Wein W., et al. A survey of medical image registration ongraphics hardware. Computer Methods and Programs in Biomedicine,2011,104(3): e45-e57.
[185]. piclin., Bo tjan L., Pernu F. Groupwise registration of multimodal imagesby an efficient joint entropy minimization scheme. IEEE Trans. on ImageProcessing,2012,21(5):2546-2558.
[186]. Liao S. and Chung Albert. C. S. Nonrigid brain MR image registration usinguniform spherical region descriptor. IEEE Trans. on Image Processing,2012,21(1):157-169.
[187]. Benoit M Dawant. Non-rigid registration of medical images: purpose andmethods, a short survey. IEEE, International Symposium on BiomedicalImaging,2002:465-468.
[188]. Kyriacou S. K., Davatzikos C. Nonlinear elastic registration of brainimageswith tumor pathology using a biomechanical model [MRI]. IEEE Trans. onMedical Imaging,1999,18:580-592.
[189]. Ashburner J., Friston K. J. Nonlinear functions spatial normalization using basis,Human Brain Mapping,1999,7:254-266.
[190]. Xie Z., Farin G. E. Image registration using hierarchical B-splines. IEEE, Trans.on Visualization and Computer Graphics,2004,10(1):85-94.
[191]. D′ez Y., Oliver A., Llad′o X., et al. Revisiting intensity-based imageregistration applied to mammography. IEEE Trans. on Information Technologyin Biomedicine,2011,15(5):716-725.
[192]. Liu D. C., Nocedal J.. On the limited memory BFGS method for large scaleoptimization. Mathematical Programming,1989,45:503-528.
[193]. Morales J. L. A mumerical study of limited memory BFGS methods. AppliedMathematics Letters,2002,15(4):481-487.
[194]. Zhou C. Y., Byrd R. H., Lu P. H., et al. Algorithm778: L-BFGS-B: Fortransubroutines for large-scale bound constrained optimization. ACM Transactionson Mathematical Software (TOMS),1997,23(4):550-560.
[195]. Morales J. L., Nocedal J.. Remark on “algorithm778: L-BFGS-B: Fortransubroutines for large-scale bound constrained optimization”. ACM Transactionson Mathematical Software (TOMS),2011,38(1):1-4.
[196]. Hellier P, Barillot Ch. Cooperation between local and global approaches toregister brain images. Int Conf on Information Processing in Medical Imaging,IPM01. Insana M F, Leahy R M, eds. Davis, California. Lecture Notes inComputer Science2082,2001.
[197]. Diplomarbeit. Physics-based nonrigid registration for medical image analysis.Master Thesis. Aus dem Institut fur Medizinische Informatik der MedizinischenUniversitat zu L ubeck,2001.
[198]. Bro-Nielsen M, Gramkow C. Fast fluid registration of medical images.Visualization in Biomedical Computing, Hamburg, Lecture Notes in ComputerScience,1996,1131:265-276.
[199]. Wollny G, Kruggel F. Computional cost of nonrigid registration algorithmsbased on fluid dynamics. IEEE Trans. on Medical Imaging,2002,21(8):946-953.
[200]. Belkin M., Niyogi P. Laplacian Eigenmaps and spectral techniques forembedding and clustering. Advances in Neural Information Processing Systems,2002,14:585-591.
[201]. Belkin M., Niyogi P. Laplacian Eigenmaps for dimensionality reduction anddata representation. Neural Computation,2003,5(6):1373-1396.
[202]. Zhang Z., Zha H. Principal manifolds and nonlinear dimensionality reductionvia tangent space alignment. SIAM J. Scientific Computing,2004,26(1):313-338.
[203]. Yang J., Li F. X., Wang J. A better scaled local tangent space alignmentalgorithm. Journal of Software,2005,16(9):1584-1590.
[204]. Zhang P., Qiao H., Zhang B. An improved local tangent space alignmentmethod for manifold learning. Pattern Recognition Letters,2011,32:181-189.
[205]. He X. F., Niyogi P. Locality preserving projections. Advances in NeuralInformation Processing Systems,2003,16:153-160.
[206]. He X. F., Yan S. C., Hu Y. X., et a1. Learning locality preserving subspace forvisual recognition. Proc. Ninth IEEE Int. Conf. Computer Vision,2003:385-392.
[207]. He X. F., Yah S. C., Hu Y. X., et a1. Face recognition using Laplacianfaces.IEEE Trans. on Pattern Analysis and Machine Intelligence,2005,27(3):328-340.
[208]. He X. F., Cai D., Yan S. C., et a1. Neighborhood preserving embedding. Proe.10th IEEE Int. Conf. Computer Vision,2005:1208-1213.
[209]. Wang Y., Wu Y. Complete neighborhood preserving embedding for facerecognition. Pattern Recognition,2010,43(3):1008-1015.
[210]. Zhang D. M., Liu H. Y., Li L., Luo B. Image recognition with extension ofneighborhood preserving embedding on matrices. Journal of information&computational science,2012,9(6):1511-1520.
[211]. Pang Y. W., Zheng L., Liu Z. K., et a1. Neighborhood preserving projections(NPP): a novel linear dimension reduction method. Proc. ICIC,2005:117-125.
[212]. Pang Y. W., Yu N. H., Li H. Q., et a1. Face recognition using neighborhoodpreserving projections. Proc. PCM,2005:854-864.
[213]. Kokiopoulou E., Saad, Y. Orthogonal neighborhood preserving projections: aprojection-based dimensionality reduction technique. IEEE Trans. on patternanalysis and machine intelligence,2007,29(12):2143-2156.
[214]. Zhang T. H., Huang K. Q., Li X. L., Yang J. and Tao D. C. Discriminativeorthogonal neighborhood-preserving projections for classification. IEEE Trans.on systems, man and cybernetics-part B: cybernetics,2010,40(1):253-263.
[215]. Hamm J., Ye D. H., Verma R., et al. GRAM: A frame work for geodesicregistration on anatomical manifolds. Medical Image Analysis,2010,14:633-642.