支持向量机算法研究及其在相控HIFU图像系统中的应用
|
摘要
近年来,相控高强度聚焦超声(HIFU——High Intensity Focused Ultrasound)技术已经成为治疗超声和肿瘤热疗的研究热点。相控HIFU技术利用了超声波特有的深穿透能力、强方向性和可聚焦性,通过控制换能器阵元激励信号源的相位,对超声声束施以聚焦,实现超声能量在人体深部组织的高强度汇聚,在短时间内造成病变组织的急性热损伤而不伤及周围的正常组织,因此成为最小损伤治疗肿瘤的一种有效方法。相控HIFU靶点小、强度高,为了避免损伤正常组织和提高治疗效率,必须提供治疗目标的精确位置。由于相控HIFU治疗的非侵入性,位置信息的获取就依赖于其图像引导系统,这是HIFU手术成败的关键。本文针对当前相控HIFU图像引导系统中存在着耗时较长、鲁棒性与精度不高等问题,研究了支持向量机(Support Vector Machines,SVM)算法,并将其应用于该系统中,从而有效地利用已有的先验知识,达到缩短图像引导时间,提高其鲁棒性与精度的目的。
SVM建立在统计学习理论的基础之上,遵循结构风险最小化原则(Structural Risk Minimization , SRM ),而不是传统的经验风险最小化原则( Empirical Risk Minimization,ERM)。由于其完备的理论基础、良好的推广性与解的稀疏性,因此与传统的学习机器相比,SVM可以更为有效地利用先验知识。采用合适的SVM算法,可以实现提高相控HIFU图像系统性能的目的。本文首先对SVM理论基础――统计学习理论作了系统阐述并分析了用于解决模式识别问题与回归估计问题的SVM。在此基础上,重点研究了基于SVM的密度估计问题,提出了一种基于单一核函数的线性SVM密度估计算法以及一种基于多核SVM的密度估计算法,并比较了它们的优缺点。在实际应用中,可以根据需要的不同选择不同的算法形式;不仅用SVM来估计一维密度,而且将其推广到多维密度估计中。
在我们所研究的相控HIFU图像引导系统中,主要包括图像分割与图像配准两部分内容。在术前制定手术治疗计划时,通过分割CT或MRI图像,获取病灶的位置信息,并制定相控HIFU焦点的合理治疗路径。在手术中,通过图像配准技术将手术前的图像与手术中的实时图像融合在一起,从而把手术前的治疗计划,目标轮廓和治疗路径都映射到治疗坐标系中,实现精确治疗。因此,本文分别研究了基于SVM的医学图像分割与配准方法。首先提出了两种基于SVM的图像分割方法。这两种方法都是将先验知识引入水平集分割过程中,从而指导曲线进行演变。一种方法是通过对训练样本的学习,利用SVM密度估计方法建立形状先验模型,将其作为水平集函数更新内容的一部分,添加到高维曲面的演化过程中。其中的物体形状描述方法采用的是水平集函数方法;另一种方法是利用SVM密度估计方法建立水平集函数与图像灰度之间的统计关系,将其作为水平集函数的更新标准,实现高维曲面的演变。这两种方法都被用于MRI、CT以及超声等多种模态下的医学图像序列分割中去,实验结果令人满意。同时,本文也提出了一种基于SVM的多模态医学图像配准方法。以两种模态下已配准好的一对图像为学习样本,利用SVM密度估计方法建立它们的先验联合灰度分布模型,作为配准测度。当待配准的两幅图像达到最佳配准时,它们的联合灰度分布应与该先验模型最相似。因此配准就转变为以该先验模型为目标的一个多参数寻优问题。该配准方法被应用于头部的CT、MRI和PET等多种模态之间的配准,结果表明该方法可以充分利用先验知识,高效、准确地实现配准。
In recent years, phased High Intensity Focused Ultrasound (HIFU) therapy technique has become a new hotspot in the research field of tumor therapy and therapeutic ultrasound. Using the ultrasound peculiar capability of penetration, orientation and focusing, phased HIFU can build high intensity focus in deep tissue and cause acute cell death by focusing ultrasound beams without damaging the close normal tissue. And it has become an efficient method of the minimal-invasive therapy of tumor. To protect normal tissues and increase the treatment efficiency, the accurate location of the tumor target must be provided. It depends on the image guided system of HIFU to acquire the postion information of tumor target because HIFU surgy is non-invasive. It is the key factor of a successful HIFU therapy. In order to solve the problems in the image guided system such as time consuming, low precision and bad robustness, this paper study on support vector machine (SVM) and its application in the image system, and the results are satisfied.
The SVM approach is considered as a good candidate for utilizing the prior knowledge because of its high generalization performance and sparse solution. SVM is a new type of learning machines based on statistical learning theory. It follows the principle of structural risk minimization, not the traditional principle of empirical risk minimization. The HIFU image system can be improved by using SVM correctly. In this paper, an overview on the academic base of SVM-- statistical learning theory is given. SVM’s applications in pattern recognization and regression estimation are introduced. A density estimation method based on linear SVM is given. Furthermore, a method for density estimation is developed based on the Multi-Kernel SVM. We extend these methods into the Multi-dimensional density estimation problem.
In the image guided system of phased HIFU we researched includes two main parts: image segmentation and image registration. In order to make therapy plan before operating, CT or MRI images are segmented. Then the reasonable therapy path of the HIFU focusing beam is built according to the result of segmentation. And image registration is to integrate the pre-operative image with the intra-operative image, to transform the pre-operative coordinates to the operating coordinates, to map the therapy plan including tumor target contour and treatment paths to the operating coordinates. In this background, this paper study on some new medical image segmentation and registration methods based on SVM. For image segmentation, two methods based on SVM for density estimation are presented. All of them improved level set method by incorporating prior knowledge into the curve evolution. One method used SVM to construct a prior model about the image intensity and curvature profile of the structure from training images. When segmenting a novel image being similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. The other method used SVM to construct a prior model of the shape of the desired object from training images. When segmenting a novel image, we improved level set method based on C-V model by incorporating this prior model. At each step of the curve evolution, we estimate the maximum a posteriori (MAP) shape of the object according to prior shape model. And then we evolve the curve towards the MAP estimate. Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images. It shows that the prior knowledge model makes segmentation process more robust and faster. For image registration, a method of computing different modality medical images registration of the same patient is presented. It incorporates prior joint intensity distribution between the two imaging modalities based on registered training images. The prior joint intensity distribution is modeled by support vector machine. Results aligning CT/MR and Pet/MR scans demonstrate that it can attain sub-voxel registration accuracy. Furthermore, it is a fast registration method because support vector machine solution is sparse.
SVM建立在统计学习理论的基础之上,遵循结构风险最小化原则(Structural Risk Minimization , SRM ),而不是传统的经验风险最小化原则( Empirical Risk Minimization,ERM)。由于其完备的理论基础、良好的推广性与解的稀疏性,因此与传统的学习机器相比,SVM可以更为有效地利用先验知识。采用合适的SVM算法,可以实现提高相控HIFU图像系统性能的目的。本文首先对SVM理论基础――统计学习理论作了系统阐述并分析了用于解决模式识别问题与回归估计问题的SVM。在此基础上,重点研究了基于SVM的密度估计问题,提出了一种基于单一核函数的线性SVM密度估计算法以及一种基于多核SVM的密度估计算法,并比较了它们的优缺点。在实际应用中,可以根据需要的不同选择不同的算法形式;不仅用SVM来估计一维密度,而且将其推广到多维密度估计中。
在我们所研究的相控HIFU图像引导系统中,主要包括图像分割与图像配准两部分内容。在术前制定手术治疗计划时,通过分割CT或MRI图像,获取病灶的位置信息,并制定相控HIFU焦点的合理治疗路径。在手术中,通过图像配准技术将手术前的图像与手术中的实时图像融合在一起,从而把手术前的治疗计划,目标轮廓和治疗路径都映射到治疗坐标系中,实现精确治疗。因此,本文分别研究了基于SVM的医学图像分割与配准方法。首先提出了两种基于SVM的图像分割方法。这两种方法都是将先验知识引入水平集分割过程中,从而指导曲线进行演变。一种方法是通过对训练样本的学习,利用SVM密度估计方法建立形状先验模型,将其作为水平集函数更新内容的一部分,添加到高维曲面的演化过程中。其中的物体形状描述方法采用的是水平集函数方法;另一种方法是利用SVM密度估计方法建立水平集函数与图像灰度之间的统计关系,将其作为水平集函数的更新标准,实现高维曲面的演变。这两种方法都被用于MRI、CT以及超声等多种模态下的医学图像序列分割中去,实验结果令人满意。同时,本文也提出了一种基于SVM的多模态医学图像配准方法。以两种模态下已配准好的一对图像为学习样本,利用SVM密度估计方法建立它们的先验联合灰度分布模型,作为配准测度。当待配准的两幅图像达到最佳配准时,它们的联合灰度分布应与该先验模型最相似。因此配准就转变为以该先验模型为目标的一个多参数寻优问题。该配准方法被应用于头部的CT、MRI和PET等多种模态之间的配准,结果表明该方法可以充分利用先验知识,高效、准确地实现配准。
In recent years, phased High Intensity Focused Ultrasound (HIFU) therapy technique has become a new hotspot in the research field of tumor therapy and therapeutic ultrasound. Using the ultrasound peculiar capability of penetration, orientation and focusing, phased HIFU can build high intensity focus in deep tissue and cause acute cell death by focusing ultrasound beams without damaging the close normal tissue. And it has become an efficient method of the minimal-invasive therapy of tumor. To protect normal tissues and increase the treatment efficiency, the accurate location of the tumor target must be provided. It depends on the image guided system of HIFU to acquire the postion information of tumor target because HIFU surgy is non-invasive. It is the key factor of a successful HIFU therapy. In order to solve the problems in the image guided system such as time consuming, low precision and bad robustness, this paper study on support vector machine (SVM) and its application in the image system, and the results are satisfied.
The SVM approach is considered as a good candidate for utilizing the prior knowledge because of its high generalization performance and sparse solution. SVM is a new type of learning machines based on statistical learning theory. It follows the principle of structural risk minimization, not the traditional principle of empirical risk minimization. The HIFU image system can be improved by using SVM correctly. In this paper, an overview on the academic base of SVM-- statistical learning theory is given. SVM’s applications in pattern recognization and regression estimation are introduced. A density estimation method based on linear SVM is given. Furthermore, a method for density estimation is developed based on the Multi-Kernel SVM. We extend these methods into the Multi-dimensional density estimation problem.
In the image guided system of phased HIFU we researched includes two main parts: image segmentation and image registration. In order to make therapy plan before operating, CT or MRI images are segmented. Then the reasonable therapy path of the HIFU focusing beam is built according to the result of segmentation. And image registration is to integrate the pre-operative image with the intra-operative image, to transform the pre-operative coordinates to the operating coordinates, to map the therapy plan including tumor target contour and treatment paths to the operating coordinates. In this background, this paper study on some new medical image segmentation and registration methods based on SVM. For image segmentation, two methods based on SVM for density estimation are presented. All of them improved level set method by incorporating prior knowledge into the curve evolution. One method used SVM to construct a prior model about the image intensity and curvature profile of the structure from training images. When segmenting a novel image being similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. The other method used SVM to construct a prior model of the shape of the desired object from training images. When segmenting a novel image, we improved level set method based on C-V model by incorporating this prior model. At each step of the curve evolution, we estimate the maximum a posteriori (MAP) shape of the object according to prior shape model. And then we evolve the curve towards the MAP estimate. Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images. It shows that the prior knowledge model makes segmentation process more robust and faster. For image registration, a method of computing different modality medical images registration of the same patient is presented. It incorporates prior joint intensity distribution between the two imaging modalities based on registered training images. The prior joint intensity distribution is modeled by support vector machine. Results aligning CT/MR and Pet/MR scans demonstrate that it can attain sub-voxel registration accuracy. Furthermore, it is a fast registration method because support vector machine solution is sparse.
引文
[1] Ahmed.M., Yamany.S., Hemayed.E., etc., 3D model building of the jaw impression, In Proc. SPIE, 3023, 87-97.
[2] Alon.N., David.B., Cesa-Bianchi.N., Haussler.D., Scale-sensitive dimensions, uniform convergence, and learn ability, J. ACM, vol. 44, no. 4, pp. 617–631, 1997.
[3] Alex J. S., Bernhard.S. and Klaus-Robert.M., The connection between regularization operators and support vector kernels, Neural Networks, vol. 11, pp. 637–649, 1998.
[4] Bajcsy.R., Kovacic.S., Multiresolution elastic matching, Computer Vision, Graphics and Image Processing, 1989, 46, 1–21.
[5] Balowh, Dooleyl, Wermser. D., Application of principal axes for registration of NMR image sequences [J ] . Pattern Recognition Letters, 2000 ,21(4) :329 - 336.
[6] Balter J , Pelizzari C, Chen G1Correlation of p rojection radio graph s in radiation therapy using open curve segments and points1M ed Phys, 1992, 19: 329～3341
[7] Bankman.I., Hand book of Medical Imaging processing and analysis, San Diego, Academic Press, 2000, 623.
[8] Bartlett.P.L., Long.P., and R. C. Williamson, Fat-shattering and the learn ability of real-valued functions, J. Comput. Syst. Sci., Vol. 52, no. 3, pp. 434–452, 1996.
[9] Bartlett. P. L. and J. Shawe-Taylor, Generalization performance on support vector machines and other pattern classifiers, Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[10] Besl.P., McKay.N., A method for registration of 3-D shapes, IEEE Trans. Pattern Anal, Mach. Intell, 1992, 14, 239–256.
[11] Begelman, G., Pechuk, M., Rivlin, E., Sabo, E., System for computer-aided multiresolution microscopic pathology diagnostics, 2006 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06, 2006, art. no. 1578704, p. 16.
[12] Blumer. A., Ehrenfeucht. A., Haussler. D., and Warmuth.M. K., Learn ability and the Vapnik–Chervonenkis dimension, J. ACM, vol. 36, no. 4, pp. 929–965, 1989.
[13] Boser.B., Guyon. I., and Vapnik. V. N., A training algorithm for optimal margin classifiers, in Proc. 5th Annu. Wkshp. Comput. Learning Theory. Pittsburgh, PA: ACM, 1992, pp. 144–152.
[14] Bro-Nielsen.M., Gramkow.C., Fast fluid registration of medical images, In Proc. 4th International Conference Visualization in Biomedical Computing (VBC’96), 1996, 267–276.
[15] Brunnstrom.K., Stoddart.A., Genetic algorithms for free-form surface matching, In 13th Int. Conference on Pattern Recognition, Vienna, Austria, 1996, 673—689.
[16] Burges. C. J. C., Simplified support vector decision rule, in Proc. 13th Int. Conf. Machine Learning, San Mateo, CA, 1996, pp. 71–77.
[17] Buchanan.M., Hynynen.K., Design and experimental evaluation of an intracavitary ultrasound phased array system for hyperthermia, IEEE Transactions on Biomedical Engineering, 1994, 41(12), 1178-1187.
[18] Chan.T., and Vese. L. Active contours without edges. IEEE Trans. Image Processing, 10(2):266–277, February 2001.
[19] Chen, C.-J., Chang, R.-F., Moon, W.K., Chen, D.-R., Wu, H.-K., 2-D ultrasound strain images forbreast cancer diagnosis using nonrigid subregion registration, 2006 Ultrasound in Medicine and Biology, 32 (6), pp. 837-846.
[20] Christensen.G., Rabbitt.R., Miller.M., Deformable templates using large deformation kinematics, IEEE Transactions on Image Processing, 1996, 5(10), 1435–1447.
[21] Chris.J., Diederich, Hynynen.K., Ultrasound technology for hyperthermia, Ultrasound in Med. & Biol., 1999, 25(6), 871-887.
[22] Cortes. C. and Vapnik. V., Support vector networks, Machine Learning, vol. 20, pp. 273–297, 1995.
[23] Cohen. L. D., On active contour models and balloons. ComputerVision, Graphics, and Image Processing, 53(2):211–218, March 1991.
[24] Crum., etc., Non-rigid image registration: theory and practice, Br J Radiol,2004, 77, 140-153.
[25] DaiQiang Peng, Jian Liu, JinWen Tian and Sheng Zheng. Transformation model estimation of image registration via least square support vector machines. Pattern Recognition Letters, Volume 27, Issue 12, September 2006, 1397-1404
[26] Davatzikos.C., Spatial transformation and registration of brain images using elastically deformable models, Computer Vision and Image Understanding, 1997, 66(2),207–222.
[27] Deniz, O., Castrillon, M., Hernandez, M., 2003. Face Recognition using Independent Component Analysis and Support Vector Machines. Pattern Recognition Letters, 24, p.2153-2157.
[28] Desheng Liu, Maggi Kelly and Peng Gong. A spatial–temporal approach to monitoring forest disease spread using multi-temporal high spatial resolution imagery. Remote Sensing of Environment, Volume 101, Issue 2, 30 March 2006, 167-180
[29] Devroye. L., Gyorfi. L., and Lugosi. G., A Probability Theory of Pattern Recognition. New York: Springer-Verlag, 1996.
[30] Ding.L , Goshtasby.A , Satter.M. Volume image registration by template matching [J] . Image and Vision Computing ,2001 ,19(12) :821 - 832.
[31] Douglas.R., Daum, Hynynen.K., Cutting edge acoustics-Noninvasive surgery using ultrasound, IEEE potentials, 1999, 17-20.
[32] Douglas.R., Daum, Nadine.B., etc., In vivo demonstration of noninvasive thermal surgery of the liver and kidney using ultrasonic phased array, Ultrasound in Medicine and Biology, 1999, 25, 1087-1098.
[33] Edwards.P., Hill.D., Little.J., etc., A three-component deformation model for image-guided surgery, Medical Image Analysis, 1998, 2(4), 355-367.
[34] Fan, Y., Rao, H., Giannetta, J., Hurt, H., Wang, J., Davatzikos, C., Shen, D., Diagnosis of brain abnormality using both structural and functional MR images, 2006 Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, art. no. 4030605, pp. 6585-6588.
[35] Fan, Y., Rao, H., Giannetta, J., Hurt, H., Wang, J., Davatzikos, C., Shen, D., Diagnosis of brain abnormality using both structural and functional MR images, 2006 Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, art. no. 4029696, pp. 1044-1047.
[36] Fukunaga, K. and Hayes, R.R. (1989) The Reduced Parzen Classifier, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(4), pp 423-425.
[37] Fu. J.C., Lee. S.K., Wong. S.T.C., J.Y. Yeh, A.H. Wang and H.K. Wu. Image segmentation featureselection and pattern classification for mammographic microcalcifications. Computerized Medical Imaging and Graphics, Volume 29, Issue 6, September 2005, 419-429
[38] Girosi. F., An equivalence between sparse approximation and support vector machines, Neural Comput., vol. 10, no. 6, pp. 1455–1480, 1998.
[39] Girosi. F., Jones. M., and Poggio. T., Regularization theory and neural networks architectures, Neural Comput., vol. 7, no. 2, pp. 219–269, 1995.
[40] Gomes. J., Faugeras. O., Reconciling Distance Functions and Level Sets, J. of Visual Communication and Image Representation 11:209-223, 2000
[41] Hadjiiski, L., Drouillard, D., Chan, H.-P., Sahiner, B., Helvie, M.A., Roubidoux, M., Zhou, C., Characterization of corresponding microcalcification clusters on temporal pairs of mammograms for interval change analysis - Comparison of classifiers, 2006 Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 6144 III, art. no. 61445Q.
[42] Hynynen.K., Review of ultrasound therapy, IEEE Ultrasonics Symposium, 1997,1305-1313.
[43] Josien.P.W., Pluim.J.B. Anitoine Maintz , Max A. Viergever. Interpolation artifacts in mutual information based image registration [J]. Computer Vision and Image Understanding , 2000 ,77 (22) :211 - 232.
[44] Kass. M., Witkin. A. and Terzopoulos. D., Snakes: Active contour models. International Journal of Computer Vision, 1(4):321–331, 1988.
[45] Komunjer.I., Asymmetric Power Distribution: Theory and Applications to Risk Measurement, http://www.hss.caltech.edu/~komunjer/respaper.htm#publ
[46] Lester.H., Arridge.S., A survey of hierarchical non-linear medical image registration, Pattern Recognition, 1999,32(1), 129–149.
[47] Leventon. M., Grimson E., et al. Statistical Shape Influence in Geodesic Active Contours Comp. Vision and Patt. Recon. (CVPR), 2000.
[48] Leventon, M. E., Faugeras, O., Grimson W. E., Wells, W. M., 2000. Level Set Based Segmentation with Intensity and Curvature Priors. Mathematical Methods in Biomedical Image Analysis.
[49] Leventon.M, Eric Grimson. Multi-Modal Volume Registration Using Joint Intensity Distributions, Medical Image Computing and Comp-Assisted Intervention (MICCAI), 1998.
[50] Liu, D., Kelly, M., Gong, P. A spatial-temporal approach to monitoring forest disease spread using multi-temporal high spatial resolution imagery 2006 Remote Sensing of Environment, 101 (2), pp. 167-180.
[51] Mark D. Brentnall, etc. A new high intensity focused ultrasound applicator for surgical application. IEEE Transaction on Ultrasonics and Frequency Control.2001,48(1),53-63.
[52] Martin.R., Vaezy.S., Kaczkowski.P., etc., Hemostasis of Punctured Vessels using Doppler-guided High-intensity Ultrasound, Ultrasound in Med. & Biol., 1999, 25(6), 985–990.
[53] Mumford. D. and Shah. J., Optimal approximation by piecewise smooth functions and associated variational problems. Commun.Pure Appl. Math, 42:577–685, 1989.
[54] Malladi. R., Sethian. J., and Vemuri. B., Shape modelling with front propagation: A level set approach. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17(2):158–174, 1995.
[55] Maintz. J. B. A, Viergever. M.A., A survey of medical image registration, Medical Image Analysis [J], 1998, 2 (1): 1-36.
[56] Maglogiannis, I., Kosmopoulos, D.I., Computational vision systems for the detection ofmalignant melanoma., 2006 Oncology reports., 15 Spec no., pp. 1027-1032.
[57] Opper. M., On the annealed VC entropy for margin classifiers: A statistical mechanics study, in B. Sholkopf, C. Burges, and A. Smola, Eds., Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[58] Osuna E ,Freund R ,Girosi F. An improved training algorithm for support vector machines [ A ] . Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing[C] . New York : IEEE Press , 1997. 276 - 285.
[59] Osher. S. and Sethian. J. A., Fronts propagating with curvature dependent speed: Algorithms based on hamilton-jacobi formulation. J. of Computational Physics, 79:12–49, 1988.
[60] O'donnell, T., Funka-Lea, G., Tek, H., Jolly, M.-P., Rasch, M., Setser, R., Comprehensive cardiovascular image analysis using MR and CT at Siemens corporate research, 2006 International Journal of Computer Vision, 70 (2), pp. 165-178.
[61] Peng, D., Liu, J., Tian, J., Zheng, S., Transformation model estimation of image registration via least square support vector machines, 2006 Pattern Recognition Letters, 27 (12), pp. 1397-1404.
[62] Peng, D., Liu, J., Tian, J., Image registration using least square support vector machines, 2006 Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2, art. no. 1713970, pp. 10073-10077.
[63] Platt J C. Fast training of support vector machines using sequential minimal optimization [ A] .Cambridge , MA : MIT Press , 1999. 185 - 208.
[64] Press. W. H., Flannery. B. P., Teukolsky. S. A., and Vetterling. W. T., Numerical recipes in C, 2nd ed. Cambridge, U. K.: Cambridge Univ. Press, 1992, ch. 10, pp. 412-419.
[65] Penney.G., Edwards.P., King.A., etc., A Stochastic Iterative Closest Point Algorithm (stochastICP), In Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention, 2001, 762 – 769.
[66] Penney.G., etc., An Overview of an Ultrasound to CT or MR Registration Algorithm for use in Thermal Ablation of Liver Metastases. In proceedings: Medical Image Understanding and Analysis, 2001, 65-68.
[67] Porter.B.C.,etc. Three dimensional registration and fusion of ultrasound and MRI using major vessels as fiducial markers[J]. IEEE Transactions on Medical Imaging, 2001,20 (4) : 354 - 359.
[68] Pizer. S., Fritsch. D., etc., Segmentation, Registration, and Measurement of Shape Variation via Image Object Shape. IEEE TMI, October 1999
[69] Pelizarri CA , Chen GTY, Spelbring DR, et al. accurate th ree - dimensional regist rat ion of CT, PET, and?o rMR images of the brain.J Comp A ssist Tomogr, 1989; 13 (1) : 20～ 26
[70] Rangarjan, Chui hail, Duncan James. Rigid point feature registration using mutual information J . Medical Image Analysis ,1999 ,3(4) :425 - 440.
[71] Ruey-Feng Chang, Dar-Ren Chen, Woo Kyung Moon and Wei-Ren Lai. 3-D ultrasound strain images for breast cancer diagnosis. International Congress Series, Volume 1281, May 2005, 1069-1074
[72] Sakuma.I., Takai.Y., Kobayashi.E., etc., Navigation of high intensity focused ultrasound applicator with an integrated three-dimensional ultrasound imaging system, MICCAI2002, LNCS 2489, 2002, 133-139.
[73] Sanghvi N. T., Hawes R., Kopecky K., et al, High intensity focused ultrasound for the treatmentof rectal tumors: a feasibility study, 1994 Ultrasonics Symposium, 1895-1898.
[74] Sanghvi.N., Hynynen.K., Lizzi.F., New developments in therapeutic ultrasound, IEEE Engineering in Medicine and Biology, 1996, 15(6), 83-92.
[75] Sholkopf. B., Burges. C., and Smola. A., Eds., Geometry and invariance in kernel-based methods, in Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[76] Sholkopf. B., Smola. A., and Muller. K. R., Nonlinear component analysis as a kernel eigenvalue problem, Neural Comput., vol. 10, pp. 1229–1319, 1998.
[77] Shawe-Taylor. J., Bartlett. P. L., Williamson. R. C., and Anthony. M., Structural risk minimization, IEEE Trans. Inform. Theory, 1998.
[78] Sethian. J. A. and Strain. J. Crystal growth and dendritic solidification. J. of Computational Physics, 98:231–253, 1992.
[79] Staib. L. and Duncan. J.. Boundary finding with parametrically deformable contour models. IEEE Trans. Patt. Analysis and Mach. Intell., 14(11), 1992.
[80] Stewart.C., Tsai.C., Roysam.B., The dual-Bootstrap iterative closest point algorithm with application to retinal image registration, IEEE Transactions of Medical Imaging, 2003, 22(11), 1379-1394.
[81] Shun,Yutaka.S. ,Satoru.G., Using selective correlation coefficient for robust image registration[J] . Pattern Recognition , 2003 , 36(5) : 1 165 - 1 173.
[82] Shuo Li, Thomas Fevens, Adam Krzy?ak and Song Li. Automatic clinical image segmentation using pathological modeling, PCA and SVM. Engineering Applications of Artificial Intelligence, Volume 19, Issue 4, June 2006, 403-410
[83] Talagrand. M., The Glivenko-Cantelli problem, ten years later, J. Theoretical Probability, vol. 9, no. 2, pp. 371–384, 1996.
[84] Tsao.J., Interpolation Artifacts in Multimodality Image Registration Based on Maximization of Mutual Inaformation, IEEE Transactions On Medical Imaging, Vol. 22, No.7, July 2003.
[85] Turk, M.A., Pentland, A.P., 1991. Eigenfaces for recognition. Cognitive Neurosci, 3 (1), 7186.
[86] Thomas M. Lehmann, et al. Survey: Interpolation Methods in Medical Image Processing, IEEE Transactions on Medical Imaging, Vol. 18, No.11, November 1999.
[87] Vaezy.S., Martin.R., Schmiedl.U., etc., Liver hemostasis using high intensity focused ultrasound, Ultrasound Med Biol, 1997, 23(9), 1413–1420.
[88] Vaezy.S., Martin.R, Yaziju.H., etc., Hemostasis of punctured blood vessels using high intensity focused ultrasound, Ultrasound Med Biol, 1998, 24(6), 903–910.
[89] Vaezy S,Shi X,Martin RW ,et a1.Real-time visualization of high intensity focused ultrasound treatment using ultrasound imaging.Ultrasound MedBiol,2001,27:33—42.
[90] Vapnik V N. 张学工译. 统计学习理论的本质[M] . 北京:清华大学出版社,2000.
[91] Vapnik, V. and Mukherjee, S. (2000) Support Vector Method for Multivariate Density Estimation,, Advances in Neural Information Processing Systems, pp 659 -665, MIT Press.
[92] Vidyasagar, A Theory of Learning and Generalization. New York: Springer, 1997.
[93] Wang.H., Qian.J., Ultrasound dynamically focussed phased array for local hyperthermia in cancer therapy, Acoustics letters, 10(1), 1986, 5-10.
[94] Wang.Z, Wu.F., Wang.Z., etc., Targeted damage effects of high intensity focused ultrasound on liver tissues of Guizhou Province miniswine, Ultrason Sonochem, 1997, 4(2), 181-182.
[95] Warfield. S., Dengler. J., Zaers. J., Guttmann. C., Gil. W., J. Ettinger, J. Hiller, and R. Kikinis. Automatic identification of grey matter structures from mri to improve the segmentation of white matter lesions. J. of Image Guided Surgery, 1(6):326–338, 1995.
[96] Wang. Y. and Staib. L. Boundary finding with correspondence using statistical shape models. In Proc. IEEE Conf. Comp. Vision and Patt. Recog., pages 338–345, 1998.
[97] Wachowiak. M. P., Smol. I. R., Tourassi.G. D.,et al. Generalized mutual information similarity metrics for multimodal biomedical image registration[A] . Houston , Texas ,USA : The Institute of Electrical and Electronics Engineers , Inc. ,2002 ,2 : 1 005 - 1006.
[98] Wahba, Spline Models for Observational Data, vol. 59. Philadelphia, PA: SIAM, 1990.
[99] Wu, J.-Z., Xie, J.-Y., Adaptive watermarking scheme utilizing support vector machine for synchronization, 2006 Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 40 (3), pp. 480-484+489.
[100] Wiley, Statistical Learning Theory. New York: 1998, p. 736.
[101] Williamson. R. C., Smola. A., Entropy number, operators, and support vector kernels, Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[102] Weston, J. Gammerman, A. Stitson, M.O. Vapnick, V. Vovk, V. and Watkins, C. (1999) Support Vector Density Estimation, Advances in Kernel Methods, MIT Press.
[103] Weisstein.E.C., Jacobi method. Technical report.
[104] Yamany.S., Farag.A., Free-form surface registration using surface signatures, In International Conference on Computer Vision, 1998, 809-813.
[105] Zaitsev.A., Sanghvi.N., Ikenberry.S., etc., High intensity focused ultrasound (HIFU) Treatment of human pancreatic cancer, 1996 IEEE Ultrasonics Symposium, 1295-1298.
[106] Zeng. X., Staib. L.H., Schultz. R.T. and J.S.Duncan, Volumetric Layer Segmentation Using Coupled Surfaces Propagation, Comp. Vision and Patt. Recon. (CVPR) 1998
[107] 鲍苏苏, 王鸿樟. 高强度相控聚焦超声肿瘤热疗仪研究和实现, 声学技术, 1996, 15(1), 39-39.
[108] 程树群, 王鸿樟, 高功率聚焦超声破坏肝细胞的机理研究, 中国超声医学杂志, 1996, 12(3),1-4.
[109] 葛云,舒华忠,罗立民. 基于Legendre 正交矩的配准方法及其在二值图像配准中的应用[J] . 电子学报,2001 ,29(1) :54 - 57.
[110] 何申戌,熊六林,王国民等,高强度聚焦超声治疗869例腹腔盆腔实性癌瘤和组织增生症临床初步报告,中国超声医学杂志,2002,18(3), 180-183.
[111] 何申戌 , 熊六林,姚松森等, 高能聚焦超声热疗临床前实验研究 , 北京医科大学学报,1999,31(6), 573-576.
[112] 侯珍秀 , 赵永平, 陈新亮等, HIFU设备中肿瘤定位及其轮廓提取和记录,哈尔滨工业大学学报,2005, 37(2).
[113] 敬宗玉, 邹建中, MRI在HIFU治疗肿瘤中的应用, 临床超声医学杂志, 2005, 7(2).
[114] 刘丽萍, 肖子文, 肖雁冰等, 超声对高强度聚焦超声治疗的实时监控研究, 中华超声影像学杂志, 2005, 14(3).
[115] 李小平,谢敬华,李培根,五坐标高强度聚焦超声刀的研制,医疗卫生装备,2002, 4, 22-24.
[116] 罗述谦, 周果宏, 医学图象处理与分析, 北京,科学出版社, 2003, 140.
[117] 罗述谦. 医学图像配准技术[J ] . 国外医学生物医学工程分册,1999 ,22 (1) :1 - 7.
[118] 罗纲,罗斌. 图象特征点集配准的加权相关迭代算法[J] . 中国图象图形学报,2000 ,2 (9) :755 - 758.
[119] 石珍龙, 耿晓鸣, HIFU工程技术问题初探, 中国医疗器械信息, 2002,6.
[120] 吴锋,钱宗才,杭洽时等. 基于轮廓的力矩主轴法在医 学图像配准中的应用[J ] . 第四军医大学学报,2001 ,22 (6) :567 - 569.
[121] 于晋生,朱厚卿,兰江等,高强度体外聚焦热疗仪的特性与致热效果,中国超声医学杂志,1998, 14(4), 26.
[122] 杨新,李俊,杜啸晓. 图像偏微分方程的原理与应用. 上海交通大学出版社,2003.
[123] 杨虎,马斌荣等 基于最大互信息的人脑MR-PET图像配准方法. 北京生物医学工程 2001, 20(4): 246-251
[124] 邹建中,伍烽,李佩希等,超声监控超声聚焦刀治疗肝癌及疗效评价研究,中国超声医学杂志, 2000, 16(10), 766-768.
[125] 邹建中,HIFU 高强度聚焦超声治疗肿瘤的超声定位实时监控及疗效评价,临床超声医学杂志, 2001, 3(11) , 23-29.
[126] 邹建中, HIFU高强度聚焦超声治疗肿瘤的超声定位实时监控及疗效评价, 临床超声医学杂志, 2001, 3(11).
[127] 张淑英, 高强度聚焦超声(HIFU)治疗肿瘤的影像学观察及疗效评价, 国外医学临床放射学分册, 2005, 28(5).
[128] 张洪峰,钱晓平,孙福成等,HIFU肿瘤热疗机的计算机辅助治疗系统,中国医疗器械杂志,2002, 26(2), 96-99.
[129] 翟亮, 孙福成, 蒋继伟等, 超声热疗技术的发展与应用, 中国医疗器械杂志, 2002, 26(4).
[130] 翟亮,孙福成,蒋继伟等,超声热疗技术的发展与应用,中国医疗器械杂志,2002, 26(4), 281-284.
[131] 赵富强,于红玉,马斌荣,等. 基于图像特征的 CT - MR 图像配准[J ]. 北京生物医学工程,2000 ,19(4) :206 - 211.
[132] http://www.cancersnet.com/news/2001/03/0319/0319006.htm.
[133] http://www.cssc.net.cn/news-c3.php?id=101.
[134] www.varian.com/orad/prd151_a.html.
[135] www.elekta.com/healthcareus.nsf.
[136] www.varian.com/orad/prd187.html.
[2] Alon.N., David.B., Cesa-Bianchi.N., Haussler.D., Scale-sensitive dimensions, uniform convergence, and learn ability, J. ACM, vol. 44, no. 4, pp. 617–631, 1997.
[3] Alex J. S., Bernhard.S. and Klaus-Robert.M., The connection between regularization operators and support vector kernels, Neural Networks, vol. 11, pp. 637–649, 1998.
[4] Bajcsy.R., Kovacic.S., Multiresolution elastic matching, Computer Vision, Graphics and Image Processing, 1989, 46, 1–21.
[5] Balowh, Dooleyl, Wermser. D., Application of principal axes for registration of NMR image sequences [J ] . Pattern Recognition Letters, 2000 ,21(4) :329 - 336.
[6] Balter J , Pelizzari C, Chen G1Correlation of p rojection radio graph s in radiation therapy using open curve segments and points1M ed Phys, 1992, 19: 329～3341
[7] Bankman.I., Hand book of Medical Imaging processing and analysis, San Diego, Academic Press, 2000, 623.
[8] Bartlett.P.L., Long.P., and R. C. Williamson, Fat-shattering and the learn ability of real-valued functions, J. Comput. Syst. Sci., Vol. 52, no. 3, pp. 434–452, 1996.
[9] Bartlett. P. L. and J. Shawe-Taylor, Generalization performance on support vector machines and other pattern classifiers, Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[10] Besl.P., McKay.N., A method for registration of 3-D shapes, IEEE Trans. Pattern Anal, Mach. Intell, 1992, 14, 239–256.
[11] Begelman, G., Pechuk, M., Rivlin, E., Sabo, E., System for computer-aided multiresolution microscopic pathology diagnostics, 2006 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems, ICVS'06, 2006, art. no. 1578704, p. 16.
[12] Blumer. A., Ehrenfeucht. A., Haussler. D., and Warmuth.M. K., Learn ability and the Vapnik–Chervonenkis dimension, J. ACM, vol. 36, no. 4, pp. 929–965, 1989.
[13] Boser.B., Guyon. I., and Vapnik. V. N., A training algorithm for optimal margin classifiers, in Proc. 5th Annu. Wkshp. Comput. Learning Theory. Pittsburgh, PA: ACM, 1992, pp. 144–152.
[14] Bro-Nielsen.M., Gramkow.C., Fast fluid registration of medical images, In Proc. 4th International Conference Visualization in Biomedical Computing (VBC’96), 1996, 267–276.
[15] Brunnstrom.K., Stoddart.A., Genetic algorithms for free-form surface matching, In 13th Int. Conference on Pattern Recognition, Vienna, Austria, 1996, 673—689.
[16] Burges. C. J. C., Simplified support vector decision rule, in Proc. 13th Int. Conf. Machine Learning, San Mateo, CA, 1996, pp. 71–77.
[17] Buchanan.M., Hynynen.K., Design and experimental evaluation of an intracavitary ultrasound phased array system for hyperthermia, IEEE Transactions on Biomedical Engineering, 1994, 41(12), 1178-1187.
[18] Chan.T., and Vese. L. Active contours without edges. IEEE Trans. Image Processing, 10(2):266–277, February 2001.
[19] Chen, C.-J., Chang, R.-F., Moon, W.K., Chen, D.-R., Wu, H.-K., 2-D ultrasound strain images forbreast cancer diagnosis using nonrigid subregion registration, 2006 Ultrasound in Medicine and Biology, 32 (6), pp. 837-846.
[20] Christensen.G., Rabbitt.R., Miller.M., Deformable templates using large deformation kinematics, IEEE Transactions on Image Processing, 1996, 5(10), 1435–1447.
[21] Chris.J., Diederich, Hynynen.K., Ultrasound technology for hyperthermia, Ultrasound in Med. & Biol., 1999, 25(6), 871-887.
[22] Cortes. C. and Vapnik. V., Support vector networks, Machine Learning, vol. 20, pp. 273–297, 1995.
[23] Cohen. L. D., On active contour models and balloons. ComputerVision, Graphics, and Image Processing, 53(2):211–218, March 1991.
[24] Crum., etc., Non-rigid image registration: theory and practice, Br J Radiol,2004, 77, 140-153.
[25] DaiQiang Peng, Jian Liu, JinWen Tian and Sheng Zheng. Transformation model estimation of image registration via least square support vector machines. Pattern Recognition Letters, Volume 27, Issue 12, September 2006, 1397-1404
[26] Davatzikos.C., Spatial transformation and registration of brain images using elastically deformable models, Computer Vision and Image Understanding, 1997, 66(2),207–222.
[27] Deniz, O., Castrillon, M., Hernandez, M., 2003. Face Recognition using Independent Component Analysis and Support Vector Machines. Pattern Recognition Letters, 24, p.2153-2157.
[28] Desheng Liu, Maggi Kelly and Peng Gong. A spatial–temporal approach to monitoring forest disease spread using multi-temporal high spatial resolution imagery. Remote Sensing of Environment, Volume 101, Issue 2, 30 March 2006, 167-180
[29] Devroye. L., Gyorfi. L., and Lugosi. G., A Probability Theory of Pattern Recognition. New York: Springer-Verlag, 1996.
[30] Ding.L , Goshtasby.A , Satter.M. Volume image registration by template matching [J] . Image and Vision Computing ,2001 ,19(12) :821 - 832.
[31] Douglas.R., Daum, Hynynen.K., Cutting edge acoustics-Noninvasive surgery using ultrasound, IEEE potentials, 1999, 17-20.
[32] Douglas.R., Daum, Nadine.B., etc., In vivo demonstration of noninvasive thermal surgery of the liver and kidney using ultrasonic phased array, Ultrasound in Medicine and Biology, 1999, 25, 1087-1098.
[33] Edwards.P., Hill.D., Little.J., etc., A three-component deformation model for image-guided surgery, Medical Image Analysis, 1998, 2(4), 355-367.
[34] Fan, Y., Rao, H., Giannetta, J., Hurt, H., Wang, J., Davatzikos, C., Shen, D., Diagnosis of brain abnormality using both structural and functional MR images, 2006 Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, art. no. 4030605, pp. 6585-6588.
[35] Fan, Y., Rao, H., Giannetta, J., Hurt, H., Wang, J., Davatzikos, C., Shen, D., Diagnosis of brain abnormality using both structural and functional MR images, 2006 Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, art. no. 4029696, pp. 1044-1047.
[36] Fukunaga, K. and Hayes, R.R. (1989) The Reduced Parzen Classifier, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(4), pp 423-425.
[37] Fu. J.C., Lee. S.K., Wong. S.T.C., J.Y. Yeh, A.H. Wang and H.K. Wu. Image segmentation featureselection and pattern classification for mammographic microcalcifications. Computerized Medical Imaging and Graphics, Volume 29, Issue 6, September 2005, 419-429
[38] Girosi. F., An equivalence between sparse approximation and support vector machines, Neural Comput., vol. 10, no. 6, pp. 1455–1480, 1998.
[39] Girosi. F., Jones. M., and Poggio. T., Regularization theory and neural networks architectures, Neural Comput., vol. 7, no. 2, pp. 219–269, 1995.
[40] Gomes. J., Faugeras. O., Reconciling Distance Functions and Level Sets, J. of Visual Communication and Image Representation 11:209-223, 2000
[41] Hadjiiski, L., Drouillard, D., Chan, H.-P., Sahiner, B., Helvie, M.A., Roubidoux, M., Zhou, C., Characterization of corresponding microcalcification clusters on temporal pairs of mammograms for interval change analysis - Comparison of classifiers, 2006 Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 6144 III, art. no. 61445Q.
[42] Hynynen.K., Review of ultrasound therapy, IEEE Ultrasonics Symposium, 1997,1305-1313.
[43] Josien.P.W., Pluim.J.B. Anitoine Maintz , Max A. Viergever. Interpolation artifacts in mutual information based image registration [J]. Computer Vision and Image Understanding , 2000 ,77 (22) :211 - 232.
[44] Kass. M., Witkin. A. and Terzopoulos. D., Snakes: Active contour models. International Journal of Computer Vision, 1(4):321–331, 1988.
[45] Komunjer.I., Asymmetric Power Distribution: Theory and Applications to Risk Measurement, http://www.hss.caltech.edu/~komunjer/respaper.htm#publ
[46] Lester.H., Arridge.S., A survey of hierarchical non-linear medical image registration, Pattern Recognition, 1999,32(1), 129–149.
[47] Leventon. M., Grimson E., et al. Statistical Shape Influence in Geodesic Active Contours Comp. Vision and Patt. Recon. (CVPR), 2000.
[48] Leventon, M. E., Faugeras, O., Grimson W. E., Wells, W. M., 2000. Level Set Based Segmentation with Intensity and Curvature Priors. Mathematical Methods in Biomedical Image Analysis.
[49] Leventon.M, Eric Grimson. Multi-Modal Volume Registration Using Joint Intensity Distributions, Medical Image Computing and Comp-Assisted Intervention (MICCAI), 1998.
[50] Liu, D., Kelly, M., Gong, P. A spatial-temporal approach to monitoring forest disease spread using multi-temporal high spatial resolution imagery 2006 Remote Sensing of Environment, 101 (2), pp. 167-180.
[51] Mark D. Brentnall, etc. A new high intensity focused ultrasound applicator for surgical application. IEEE Transaction on Ultrasonics and Frequency Control.2001,48(1),53-63.
[52] Martin.R., Vaezy.S., Kaczkowski.P., etc., Hemostasis of Punctured Vessels using Doppler-guided High-intensity Ultrasound, Ultrasound in Med. & Biol., 1999, 25(6), 985–990.
[53] Mumford. D. and Shah. J., Optimal approximation by piecewise smooth functions and associated variational problems. Commun.Pure Appl. Math, 42:577–685, 1989.
[54] Malladi. R., Sethian. J., and Vemuri. B., Shape modelling with front propagation: A level set approach. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17(2):158–174, 1995.
[55] Maintz. J. B. A, Viergever. M.A., A survey of medical image registration, Medical Image Analysis [J], 1998, 2 (1): 1-36.
[56] Maglogiannis, I., Kosmopoulos, D.I., Computational vision systems for the detection ofmalignant melanoma., 2006 Oncology reports., 15 Spec no., pp. 1027-1032.
[57] Opper. M., On the annealed VC entropy for margin classifiers: A statistical mechanics study, in B. Sholkopf, C. Burges, and A. Smola, Eds., Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[58] Osuna E ,Freund R ,Girosi F. An improved training algorithm for support vector machines [ A ] . Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing[C] . New York : IEEE Press , 1997. 276 - 285.
[59] Osher. S. and Sethian. J. A., Fronts propagating with curvature dependent speed: Algorithms based on hamilton-jacobi formulation. J. of Computational Physics, 79:12–49, 1988.
[60] O'donnell, T., Funka-Lea, G., Tek, H., Jolly, M.-P., Rasch, M., Setser, R., Comprehensive cardiovascular image analysis using MR and CT at Siemens corporate research, 2006 International Journal of Computer Vision, 70 (2), pp. 165-178.
[61] Peng, D., Liu, J., Tian, J., Zheng, S., Transformation model estimation of image registration via least square support vector machines, 2006 Pattern Recognition Letters, 27 (12), pp. 1397-1404.
[62] Peng, D., Liu, J., Tian, J., Image registration using least square support vector machines, 2006 Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2, art. no. 1713970, pp. 10073-10077.
[63] Platt J C. Fast training of support vector machines using sequential minimal optimization [ A] .Cambridge , MA : MIT Press , 1999. 185 - 208.
[64] Press. W. H., Flannery. B. P., Teukolsky. S. A., and Vetterling. W. T., Numerical recipes in C, 2nd ed. Cambridge, U. K.: Cambridge Univ. Press, 1992, ch. 10, pp. 412-419.
[65] Penney.G., Edwards.P., King.A., etc., A Stochastic Iterative Closest Point Algorithm (stochastICP), In Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention, 2001, 762 – 769.
[66] Penney.G., etc., An Overview of an Ultrasound to CT or MR Registration Algorithm for use in Thermal Ablation of Liver Metastases. In proceedings: Medical Image Understanding and Analysis, 2001, 65-68.
[67] Porter.B.C.,etc. Three dimensional registration and fusion of ultrasound and MRI using major vessels as fiducial markers[J]. IEEE Transactions on Medical Imaging, 2001,20 (4) : 354 - 359.
[68] Pizer. S., Fritsch. D., etc., Segmentation, Registration, and Measurement of Shape Variation via Image Object Shape. IEEE TMI, October 1999
[69] Pelizarri CA , Chen GTY, Spelbring DR, et al. accurate th ree - dimensional regist rat ion of CT, PET, and?o rMR images of the brain.J Comp A ssist Tomogr, 1989; 13 (1) : 20～ 26
[70] Rangarjan, Chui hail, Duncan James. Rigid point feature registration using mutual information J . Medical Image Analysis ,1999 ,3(4) :425 - 440.
[71] Ruey-Feng Chang, Dar-Ren Chen, Woo Kyung Moon and Wei-Ren Lai. 3-D ultrasound strain images for breast cancer diagnosis. International Congress Series, Volume 1281, May 2005, 1069-1074
[72] Sakuma.I., Takai.Y., Kobayashi.E., etc., Navigation of high intensity focused ultrasound applicator with an integrated three-dimensional ultrasound imaging system, MICCAI2002, LNCS 2489, 2002, 133-139.
[73] Sanghvi N. T., Hawes R., Kopecky K., et al, High intensity focused ultrasound for the treatmentof rectal tumors: a feasibility study, 1994 Ultrasonics Symposium, 1895-1898.
[74] Sanghvi.N., Hynynen.K., Lizzi.F., New developments in therapeutic ultrasound, IEEE Engineering in Medicine and Biology, 1996, 15(6), 83-92.
[75] Sholkopf. B., Burges. C., and Smola. A., Eds., Geometry and invariance in kernel-based methods, in Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[76] Sholkopf. B., Smola. A., and Muller. K. R., Nonlinear component analysis as a kernel eigenvalue problem, Neural Comput., vol. 10, pp. 1229–1319, 1998.
[77] Shawe-Taylor. J., Bartlett. P. L., Williamson. R. C., and Anthony. M., Structural risk minimization, IEEE Trans. Inform. Theory, 1998.
[78] Sethian. J. A. and Strain. J. Crystal growth and dendritic solidification. J. of Computational Physics, 98:231–253, 1992.
[79] Staib. L. and Duncan. J.. Boundary finding with parametrically deformable contour models. IEEE Trans. Patt. Analysis and Mach. Intell., 14(11), 1992.
[80] Stewart.C., Tsai.C., Roysam.B., The dual-Bootstrap iterative closest point algorithm with application to retinal image registration, IEEE Transactions of Medical Imaging, 2003, 22(11), 1379-1394.
[81] Shun,Yutaka.S. ,Satoru.G., Using selective correlation coefficient for robust image registration[J] . Pattern Recognition , 2003 , 36(5) : 1 165 - 1 173.
[82] Shuo Li, Thomas Fevens, Adam Krzy?ak and Song Li. Automatic clinical image segmentation using pathological modeling, PCA and SVM. Engineering Applications of Artificial Intelligence, Volume 19, Issue 4, June 2006, 403-410
[83] Talagrand. M., The Glivenko-Cantelli problem, ten years later, J. Theoretical Probability, vol. 9, no. 2, pp. 371–384, 1996.
[84] Tsao.J., Interpolation Artifacts in Multimodality Image Registration Based on Maximization of Mutual Inaformation, IEEE Transactions On Medical Imaging, Vol. 22, No.7, July 2003.
[85] Turk, M.A., Pentland, A.P., 1991. Eigenfaces for recognition. Cognitive Neurosci, 3 (1), 7186.
[86] Thomas M. Lehmann, et al. Survey: Interpolation Methods in Medical Image Processing, IEEE Transactions on Medical Imaging, Vol. 18, No.11, November 1999.
[87] Vaezy.S., Martin.R., Schmiedl.U., etc., Liver hemostasis using high intensity focused ultrasound, Ultrasound Med Biol, 1997, 23(9), 1413–1420.
[88] Vaezy.S., Martin.R, Yaziju.H., etc., Hemostasis of punctured blood vessels using high intensity focused ultrasound, Ultrasound Med Biol, 1998, 24(6), 903–910.
[89] Vaezy S,Shi X,Martin RW ,et a1.Real-time visualization of high intensity focused ultrasound treatment using ultrasound imaging.Ultrasound MedBiol,2001,27:33—42.
[90] Vapnik V N. 张学工译. 统计学习理论的本质[M] . 北京:清华大学出版社,2000.
[91] Vapnik, V. and Mukherjee, S. (2000) Support Vector Method for Multivariate Density Estimation,, Advances in Neural Information Processing Systems, pp 659 -665, MIT Press.
[92] Vidyasagar, A Theory of Learning and Generalization. New York: Springer, 1997.
[93] Wang.H., Qian.J., Ultrasound dynamically focussed phased array for local hyperthermia in cancer therapy, Acoustics letters, 10(1), 1986, 5-10.
[94] Wang.Z, Wu.F., Wang.Z., etc., Targeted damage effects of high intensity focused ultrasound on liver tissues of Guizhou Province miniswine, Ultrason Sonochem, 1997, 4(2), 181-182.
[95] Warfield. S., Dengler. J., Zaers. J., Guttmann. C., Gil. W., J. Ettinger, J. Hiller, and R. Kikinis. Automatic identification of grey matter structures from mri to improve the segmentation of white matter lesions. J. of Image Guided Surgery, 1(6):326–338, 1995.
[96] Wang. Y. and Staib. L. Boundary finding with correspondence using statistical shape models. In Proc. IEEE Conf. Comp. Vision and Patt. Recog., pages 338–345, 1998.
[97] Wachowiak. M. P., Smol. I. R., Tourassi.G. D.,et al. Generalized mutual information similarity metrics for multimodal biomedical image registration[A] . Houston , Texas ,USA : The Institute of Electrical and Electronics Engineers , Inc. ,2002 ,2 : 1 005 - 1006.
[98] Wahba, Spline Models for Observational Data, vol. 59. Philadelphia, PA: SIAM, 1990.
[99] Wu, J.-Z., Xie, J.-Y., Adaptive watermarking scheme utilizing support vector machine for synchronization, 2006 Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 40 (3), pp. 480-484+489.
[100] Wiley, Statistical Learning Theory. New York: 1998, p. 736.
[101] Williamson. R. C., Smola. A., Entropy number, operators, and support vector kernels, Advances in Kernel Methods—Support Vector Learning. Cambridge, MA: MIT Press, 1999.
[102] Weston, J. Gammerman, A. Stitson, M.O. Vapnick, V. Vovk, V. and Watkins, C. (1999) Support Vector Density Estimation, Advances in Kernel Methods, MIT Press.
[103] Weisstein.E.C., Jacobi method. Technical report.
[104] Yamany.S., Farag.A., Free-form surface registration using surface signatures, In International Conference on Computer Vision, 1998, 809-813.
[105] Zaitsev.A., Sanghvi.N., Ikenberry.S., etc., High intensity focused ultrasound (HIFU) Treatment of human pancreatic cancer, 1996 IEEE Ultrasonics Symposium, 1295-1298.
[106] Zeng. X., Staib. L.H., Schultz. R.T. and J.S.Duncan, Volumetric Layer Segmentation Using Coupled Surfaces Propagation, Comp. Vision and Patt. Recon. (CVPR) 1998
[107] 鲍苏苏, 王鸿樟. 高强度相控聚焦超声肿瘤热疗仪研究和实现, 声学技术, 1996, 15(1), 39-39.
[108] 程树群, 王鸿樟, 高功率聚焦超声破坏肝细胞的机理研究, 中国超声医学杂志, 1996, 12(3),1-4.
[109] 葛云,舒华忠,罗立民. 基于Legendre 正交矩的配准方法及其在二值图像配准中的应用[J] . 电子学报,2001 ,29(1) :54 - 57.
[110] 何申戌,熊六林,王国民等,高强度聚焦超声治疗869例腹腔盆腔实性癌瘤和组织增生症临床初步报告,中国超声医学杂志,2002,18(3), 180-183.
[111] 何申戌 , 熊六林,姚松森等, 高能聚焦超声热疗临床前实验研究 , 北京医科大学学报,1999,31(6), 573-576.
[112] 侯珍秀 , 赵永平, 陈新亮等, HIFU设备中肿瘤定位及其轮廓提取和记录,哈尔滨工业大学学报,2005, 37(2).
[113] 敬宗玉, 邹建中, MRI在HIFU治疗肿瘤中的应用, 临床超声医学杂志, 2005, 7(2).
[114] 刘丽萍, 肖子文, 肖雁冰等, 超声对高强度聚焦超声治疗的实时监控研究, 中华超声影像学杂志, 2005, 14(3).
[115] 李小平,谢敬华,李培根,五坐标高强度聚焦超声刀的研制,医疗卫生装备,2002, 4, 22-24.
[116] 罗述谦, 周果宏, 医学图象处理与分析, 北京,科学出版社, 2003, 140.
[117] 罗述谦. 医学图像配准技术[J ] . 国外医学生物医学工程分册,1999 ,22 (1) :1 - 7.
[118] 罗纲,罗斌. 图象特征点集配准的加权相关迭代算法[J] . 中国图象图形学报,2000 ,2 (9) :755 - 758.
[119] 石珍龙, 耿晓鸣, HIFU工程技术问题初探, 中国医疗器械信息, 2002,6.
[120] 吴锋,钱宗才,杭洽时等. 基于轮廓的力矩主轴法在医 学图像配准中的应用[J ] . 第四军医大学学报,2001 ,22 (6) :567 - 569.
[121] 于晋生,朱厚卿,兰江等,高强度体外聚焦热疗仪的特性与致热效果,中国超声医学杂志,1998, 14(4), 26.
[122] 杨新,李俊,杜啸晓. 图像偏微分方程的原理与应用. 上海交通大学出版社,2003.
[123] 杨虎,马斌荣等 基于最大互信息的人脑MR-PET图像配准方法. 北京生物医学工程 2001, 20(4): 246-251
[124] 邹建中,伍烽,李佩希等,超声监控超声聚焦刀治疗肝癌及疗效评价研究,中国超声医学杂志, 2000, 16(10), 766-768.
[125] 邹建中,HIFU 高强度聚焦超声治疗肿瘤的超声定位实时监控及疗效评价,临床超声医学杂志, 2001, 3(11) , 23-29.
[126] 邹建中, HIFU高强度聚焦超声治疗肿瘤的超声定位实时监控及疗效评价, 临床超声医学杂志, 2001, 3(11).
[127] 张淑英, 高强度聚焦超声(HIFU)治疗肿瘤的影像学观察及疗效评价, 国外医学临床放射学分册, 2005, 28(5).
[128] 张洪峰,钱晓平,孙福成等,HIFU肿瘤热疗机的计算机辅助治疗系统,中国医疗器械杂志,2002, 26(2), 96-99.
[129] 翟亮, 孙福成, 蒋继伟等, 超声热疗技术的发展与应用, 中国医疗器械杂志, 2002, 26(4).
[130] 翟亮,孙福成,蒋继伟等,超声热疗技术的发展与应用,中国医疗器械杂志,2002, 26(4), 281-284.
[131] 赵富强,于红玉,马斌荣,等. 基于图像特征的 CT - MR 图像配准[J ]. 北京生物医学工程,2000 ,19(4) :206 - 211.
[132] http://www.cancersnet.com/news/2001/03/0319/0319006.htm.
[133] http://www.cssc.net.cn/news-c3.php?id=101.
[134] www.varian.com/orad/prd151_a.html.
[135] www.elekta.com/healthcareus.nsf.
[136] www.varian.com/orad/prd187.html.