基于MDL的统计形状模型的建立及其医学图像分割的研究
|
摘要
随着经济水平的提高,健康已成为现代社会主题之一。医学影像技术使我们可以非侵入地观察人体内部构造和诊断治疗。而医学图像处理和分析作为信息科学技术和医学的交叉学科,将使医学向数字化、智能化、自动化方向迈进。
本文针对椎间盘、椎骨和半月板这三种富于细节变化的核磁共振图像,进行统计形状建模和图像分割处理,具有较强的实用意义。主要工作和创新点如下:
(1)针对统计形状建模中的点对应问题,使用基于最小描述长度的最优化方法加以解决,完成模型的自动建立。并提出使用多尺度弧长参数函数,确保粗尺度上具有最优意义的点对应,同时在精尺度上使用最简单的弧长参数函数来确定特征点,完成对感兴趣目标的快速统计形状建模。为后续图像分割或定量分析打下基础。实验对肌肉骨骼核磁共振成像中椎骨、椎间盘以及半月板等具有临床意义的结构建立了统计形状模型,验证了本文方法与手动取点相比具有客观可重复性且更加简洁,与单一尺度下的最小描述长度方法相比时间效率更高。
(2)主动形状模型是一种行之有效的图像分割方法,在建立主动形状模型中关键的一点是从形状样本集中获得满足点对应关系的轮廓采样点集合。传统的手动标定这些特征点枯燥,耗时,且带有主观性。本文先使用基于最小描述长度优化的方法自动建立统计形状模型,并以得到的点分布模型为基础,快速建立灰度阶外观模型,将之用于相关医学图像的分割,并与手动建模的分割结果相比较,误差相当或有所降低。
Along with the improvement of economics,health is one of the key topics in our modern society.Medical imaging provides a non-intervention overview of inner structures of our bodies and great help in diagnosis and cure.Combining fields like information science and medicine,medical image process and analysis is making another push in the progress of medicine digitally,automatically and intelligently.
In this dissertation,research is done on Statistical Shape Modeling and Segmenting in intervertebral disc, vertebra and meniscus MRI.The main points are as follows:
(1) we describe a minimum description length based optimization method for automatically building statiscal shape models from training set of example boundaries. A multi-scale parameterization on shapes allows the optimization on landmark correspondence in a coarse scale and a most convenient arc parameterization based landmark correspondence in a fine scale. This achieves a fast and accurate SSM building, which is the foundation on following image segmentation and quantitative analysis. In experiments, SSMs are built with vertebral body, intervertebral disc and meniscus shapes extracted from various MRIs respectively. It is testified that the models built with the proposed scheme is not only more repeatable and concise than model based on manually landmarking, but also more temporally efficient than model purely based on optimization.
(2) Active Shape Model (ASM) is an efficient method of image segmenting. One key factor in building models is obtaining correspondent landmarks among the whole shape dataset. Traditional manual landmarking is temporally expensive, subjective,boring and prohibitively extensive in dimension. In this dissertation, a parameterization on shapes allows a Minimum Description Length (MDL) based optimization on landmark correspondence. Base on the point distribution models, we complete gray-level models building, which is the foundation on following image segmentation. The segmentation errors from the proposed method are comparable with or better than those from the manual modeling based segmentation.
本文针对椎间盘、椎骨和半月板这三种富于细节变化的核磁共振图像,进行统计形状建模和图像分割处理,具有较强的实用意义。主要工作和创新点如下:
(1)针对统计形状建模中的点对应问题,使用基于最小描述长度的最优化方法加以解决,完成模型的自动建立。并提出使用多尺度弧长参数函数,确保粗尺度上具有最优意义的点对应,同时在精尺度上使用最简单的弧长参数函数来确定特征点,完成对感兴趣目标的快速统计形状建模。为后续图像分割或定量分析打下基础。实验对肌肉骨骼核磁共振成像中椎骨、椎间盘以及半月板等具有临床意义的结构建立了统计形状模型,验证了本文方法与手动取点相比具有客观可重复性且更加简洁,与单一尺度下的最小描述长度方法相比时间效率更高。
(2)主动形状模型是一种行之有效的图像分割方法,在建立主动形状模型中关键的一点是从形状样本集中获得满足点对应关系的轮廓采样点集合。传统的手动标定这些特征点枯燥,耗时,且带有主观性。本文先使用基于最小描述长度优化的方法自动建立统计形状模型,并以得到的点分布模型为基础,快速建立灰度阶外观模型,将之用于相关医学图像的分割,并与手动建模的分割结果相比较,误差相当或有所降低。
Along with the improvement of economics,health is one of the key topics in our modern society.Medical imaging provides a non-intervention overview of inner structures of our bodies and great help in diagnosis and cure.Combining fields like information science and medicine,medical image process and analysis is making another push in the progress of medicine digitally,automatically and intelligently.
In this dissertation,research is done on Statistical Shape Modeling and Segmenting in intervertebral disc, vertebra and meniscus MRI.The main points are as follows:
(1) we describe a minimum description length based optimization method for automatically building statiscal shape models from training set of example boundaries. A multi-scale parameterization on shapes allows the optimization on landmark correspondence in a coarse scale and a most convenient arc parameterization based landmark correspondence in a fine scale. This achieves a fast and accurate SSM building, which is the foundation on following image segmentation and quantitative analysis. In experiments, SSMs are built with vertebral body, intervertebral disc and meniscus shapes extracted from various MRIs respectively. It is testified that the models built with the proposed scheme is not only more repeatable and concise than model based on manually landmarking, but also more temporally efficient than model purely based on optimization.
(2) Active Shape Model (ASM) is an efficient method of image segmenting. One key factor in building models is obtaining correspondent landmarks among the whole shape dataset. Traditional manual landmarking is temporally expensive, subjective,boring and prohibitively extensive in dimension. In this dissertation, a parameterization on shapes allows a Minimum Description Length (MDL) based optimization on landmark correspondence. Base on the point distribution models, we complete gray-level models building, which is the foundation on following image segmentation. The segmentation errors from the proposed method are comparable with or better than those from the manual modeling based segmentation.
引文
[1]包尚联,谢耀钦,周晓东等.基于医学影像计算机辅助诊断的分割方法[J].中国医学物理学杂志,2003,Vol.20,No.2,pp.83-86
[2]田捷,包尚联,周明全.医学影像处理与分析[M].北京:电子工业出版社,2003.
[3]林瑤,田捷.医学图像分割方法综述.模式识别与人工智能,2002,Vol.15,No.2,pp:192-204
[4]简江涛,冯焕清.医学图像分割中的形变模型技术.国际生物医学工程杂志,2007,Vol.30,No.4,pp:222-226
[5]Horace Ho-Shing Ip,Dinggang Shen:An affine-invariant active contour model(AI-snake)for model-based segmentation[J],Image Vision Comput,1998,Vol.16,No.2,pp.135-146
[6]P.Brigger,J.Hoeg,M.Unser,B-Spline Snakes:A Flexible Tool for Parametric Comtour Detection[J],IEEE Transactions on Image Processing,2000,Vol.9,No.9,pp.1484-1496
[7]G.Giraldi,E.Strauss,A.Olibeira,A boundary extraction method based on dual-T-snakes and dynamic programming[A],Proc.CVPR 2000[C],2000,pp.1044-1049
[8]Chen G,Gu L,Qian L,and Xu J,An Improved Level Set for Liver Segmentation and Perfusion Analysis in MRIs[J],IEEE transactions on information technology in biomedicine,2009,Vol.13,No.1,pp.94-103
[9]Yan Nei Law Hwee Kuan Lee,Yip A.M,A Multiresolution Stochastic Level Set Method for Mumford-Shah Image Segmentation[J],IEEE Transactions on Image Processing,2008,Vol.17,No.12,pp,2289-2300
[10]Ben Ayed I.,Mitiche A.,A Region Merging Prior for Variational Level Set Image Segmentation[J],IEEE Transactions on Image Processing,2008,Vol.17,No.12,pp.2301-2311
[11]Folkesson J.,Samset E.,Kwong R.Y.,et al,Unifying statistical classification and geodesic active regions for segmentation of cardiac MRI[J],IEEE Transactions on Information Technology in Biomedicine,2008,Vol.12,No.3,pp.328-334
[12]Lei Ying,Zhi-Pei Liang,David C.Munson,et al.,Unwrapping of MR phase images using a Markov random field model[J].IEEE Transaction on Medical Imaging,2006,Vol.26,No.10,pp.128-136
[13]Mathews Jacob,Xiaoping Zhu,Zhi-Pei Liang,et al.,Improved model-basedmagnetic resonance spectroscopic imaging[J].IEEE Transaction on Medical Imaging,2007,Vol.26,No.10,PP.1305-1318
[14]Sam S. Stong,Justin P. Haldar,Stephanie C. Tsao,Wen-mei W.Hwu,et al.,Accelerating advanced MRI reconstructions on GPUS[A].Proc.Conf.Computing Frontiers 2008[C]:261-272
[15]Steven C.Mitchell,Johan G. Bosch,B P. F. Lelieveldt,et al.3D active appearance models:segmentation of cardiac MR and ultrasound images[J],IEEE Transaction on Medical Imaging,2002,Vol.26,No.10,pp.1167-1179
[16]E. Oost,G.konging,M.Sonka,et al,Automated contour detection in X-ray leftventricular angiograms using multiview active appearance models anddynamic programming[J],IEEE Transaction on Medical Imaging,2006,Vol.25,No.9,pp.1158-1171
[17]J.G.Bosch,S.C.Mitchell,B.P.F.Lelieveldt,et al.,Automatic segmentation of echocardiographic sequences by active appearance motion models[J],IEEE Transaction on Medical Imaging,2002,Vol.21,No.11,pp.1374-1383
[18]Kunio Doi,Computer-aided diagnosis in medical imaging:Historicl review,current status and future potential[J],Computerized Medical Imaging and Graphics,2007,Vol.31,No.4-5,pp.198-211
[19]Shuji Sakai,Hidetake Yabuuchi,Yoshio Matsuo,et al.,Integration of temporal subtraction and nodule detection system for digital chest radiographs into Picture Archiving and Communication System(PACS):Four-year Experience[J].Digital Imaging,2008,Vol.21,No.1,pp.91-98
[20]Timothy F.Cootes,Carole J.Twining,Kolawole O.Babalola,et al.,Diffeomorphic statistical shape models[J].Image Vision Comput,2008,Vol.26,No.3,pp.326-332
[21]David Cristinacce,Timothy F.Cootes:Automatic feature localization with constrained local models[J].Computer Vision and Image Understanding,2007,Vol.41,No.10,pp.3054-3067
[22]Rasmus Larsen,Mikkel B.Stegmann,Sune Darkner,et al.,Texture enhanced appearance models[J].Computer Vision and Image Understanding,2007,Vol.106,No.1,pp.20-30
[23]Juan R.Cebral,Marcelo Adrián Castro,Sunil Appanaboyina,et al.,Efficient pipeline for image-based patient-specific analysis of cerebral aneurysm hemodynamics:technique and sensitivity[J].IEEE Transaction on Medical Imaging,2005,Vol.24,No.4,PP.457-467
[24]Consrantine Butakoff,Alejandro F.Frangi:A Framework for Weighted Fusion of Multiple Statistical Models of Shape and Appearance[J].IEEE Transaction onPattern Analysis Machine Intelligence,2006,Vol.28,No.11,pp.1847-1857
[25]R.D.Millan,Laura Dempere-Marco,J.M.Pozo,et al.,Morphological Characterization of Intracranial Aneurysms Using 3-D Moment Invariants[J].IEEE Transaction on Medical Imaging,2007,Vol.26,No.9,pp.1270-1282
[26]C.Tobon-Gomez,Constantine Butakoff,S. Aguade,et al.,Automatic Construction of 3D-ASM Intensity Models by Simulating Image Acquisition:Application to Myocardial Gated SPECT Studies[J].IEEE Transaction on Medical Imaging,2008,Vol.27,No.11,pp.1655-1667
[27]Mikkel B.Stegmann,Bjarne K.Ersboll,Rasmus Larsen,FAME-A Flexible Appearance Modelling Environment[J],IEEE Transaction on Medical Imaging,2003,Vol.22,No.10,pp.1319-1331
[28]Joger Hansegard,Stig Urheim,Ketil Lunde,er al.,Constrained Active Appearande Models for Segmentation of Triplane Echocardiograms[J],IEEE Transaction on Medical Imaging,2007,Vol.26,No.10,pp.1391-1401
[29]Tomaz Vrtovec,Franjo Pernus,Bostjan Likar,A Symmetry-Based Method for the Determination of Vertebral Rotation in 3D[A],Proc.MICCA[C],2008:942-950
[30]Tomaz Vrtovec,Bostjan Likar and Franjo Pernus,Quantitative analysis of spinal curvature in 3D:application to CT images of normal spine[J],Physics in Medicine and Biology,2008,Vol.53,No.10,pp.1895-1908
[31]Jie Tian,Jing Bai,Xiu-Ping Yan,Shanglian Bao,Yinghui Li,Wei Liang,and Xin Yang,Multimodality molecular imaging[J],IEEE Engineering in Medicing and Biology Magazine,2008,Vol.27,No.5,pp.48-57
[32]Jie Tian,Jian Xue,Yakang Dai,Jian Chen and Jian Zheng.A Novel Software Platform for Medical Image Processing and Analyzing[J].IEEE Transaction on Information Technology in Biomedicing,2008,Vol.12,No.6,pp.800-812
[33]罗希平,田捷.一种交互式医学图像序列分割方法[J].电子学报,2003,Vol.31,No.1,pp.29-32
[34]薛键,田捷,戴亚康,陈健,海量医学数据处理框架及快速体绘制算法[J].软件学报,2008,Vol.19,No.12,pp.3237-3248
[35]彭文,童若锋,钱归平,董金祥,使用特征点与曲线配准医学图像[J].计算机辅助设计与图形学学报,2006,Vol.18,No.09,pp.1126-1131
[36]秦绪佳,王青,鲍虎军.基于散乱点的增量式曲面逼近[J].计算机辅助设计与图形学学报,2005,Vol.17,No.10,pp.2168-2173
[37]陆剑锋,林海,潘志庚.自适应区域生长算法在医学图像分割中的应用[J].计算机辅助设计与图形学学报,2005,Vol.17,No.10,pp.2168-2173
[38]张绍祥,刘正津,谭立文等.首例中国数字化可视人体完成[J].第三军医大学学报,2002,Vol.24,No.2,pp.1231-1232
[39]钟世镇,李华等,数字化虚拟中国人女性一号(VCH-F1)实验数据集研究报告[J].第一军医大学学报,2003,Vol.23,No.6,pp.193-196
[40]原林,唐雷,黄文华等.虚拟中国人男性一号(VCH-M1)数据集研究[J],第一军医大学学报,2003,Vol.23,No.6,pp.520-523
[41]简江涛,安滨,熊进,刘军伟,冯焕清.中国数字人切片图像的自动配准与分割方法研究[J],中国科学技术大学学报,2007,Vol.37,No.2,pp.195-199
[42]ZHAO ZheEn,Teoh E K.A new scheme for automated 3D PDM construction using deformable models[J]. Image and Vision Computing, 2008, Vol.26,No.2,pp. 275-288.
[43]Lee S J, Sung J W, Kim D J. Tensor-Based AAM with continuous variation estimation, application to variation-robust face recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2009, Vol.31,No.6,pp. 1102-1116.
[44]王绍宇,戚飞虎,夏小玲.基于MDL Shape Model及EFD的行人轮廓2D+time表示[J].中国图象图形学报,2008,Vol.13,No.10,pp.1898-1901
[45]I.T.Jolliffe.Principal Component Analysis[M],Springer-Verlag,New York Berlin Heidelberg Tokio,1986
[46]F.L.Bookstein.Landmark methods for forms without landmarks:localizing group differences in outline shape[J].Medical Image Analysis,1997,Vol.1,No.3,pp.225-244
[47]A.Baumberg,D.Hogg.Learning flexible models from image sequences[A], ECCV1994[C],1994,pp. 299–308
[48]A.Hill,C.Taylor.Automatic landmark generation for point distribution models[A],BMVC1994[C], 1994, pp. 429–438
[49]A.Hill,C.J.Taylor.A framework for automatic landmark identification using a new method of nonrigid correspondence[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,vol. 22,No.3, pp. 241–251
[50]A.Kelemen,G.Szekely,G.Gerig.Elastic model-based segmentation of 3-D neuroradiological data sets[J],IEEE Transaction on Medical Imaging,1999,vol.18,No.10,pp. 828–839
[51]A.C.W.Kotcheff ,C.J.Taylor.Automatic construction of eigenshape models by direct optimization[J] ,Medical Image Analysis, 1998,vol. 2,No.4, pp:303–314
[52]D.Rueckert, F.Frangi,J.A.Schnabel.Automatic construction of 3D statistical defomation models using nonrigid registration[A],MICCAI2001[C],2001,pp. 77–84
[53]Y.Wang,B.S.Peterson,L.H.Staib.Shape-based 3D surface correspondence using geodesics and local geometry[A], CVPR 2000[C],2000, pp. 644–651
[54]Y.Wang,B.S.Peterson,L.H.Staib, Shape-based 3D surface correspondence usinggeodesics and local geometry[A],CVPR 2000[C],2000,vol. 2, pp. 644–651
[55]A.Benayoun,N.Ayache,I.Cohen.Adaptive meshes and non-rigid motion computation[A],ICPR1994[C], 1994, pp. 730–732
[56]C.Kambhamettu,D.B.Goldgof.Point correspondence recovery in non-rigid motion[A],CVPR1992[C], 1992, pp. 222–227
[57]H.D.Tagare.Shape-based non-rigid correspondence with application to heart motion analysis[J],IEEE Transaction on Medical Imaging,1999,vol.18,No.7,pp. 434–349
[58]F.L.Bookstein.Landmarkmethods for formswithout landmarks:Mor-phometrics of group differences in outline shape[J],Medical Image Analysis,1997Vol.1,No.3, pp. 225–243
[59]Davies R H,Twining C J,Cootes T F,Waterton J C,Tylor C J,A Minimum Description Length Approach to Statistical Shape Modeling[J].IEEE Transaction on Medical Imaging, 2002, Vol.21,No.5,pp.525-537.
[60]Thodberg H H.Minimum Description Length Shape and Appearance Models[A],Information Processing in Medical Imaging[C], 2003,PP.51-62.
[61]Andre Souza,Jayaram K.Udupa.Automatic Landmark Slection for Active Shape Models[A],SPIE2005[C],2005,PP.1-7
[62]Sylvia Rueda,Jayaram K.Udupa,Li Bai.Landmark selection for shape model construction via equalization of variance[A], ISBI 2008[C],2008,PP. 1271-1274
[2]田捷,包尚联,周明全.医学影像处理与分析[M].北京:电子工业出版社,2003.
[3]林瑤,田捷.医学图像分割方法综述.模式识别与人工智能,2002,Vol.15,No.2,pp:192-204
[4]简江涛,冯焕清.医学图像分割中的形变模型技术.国际生物医学工程杂志,2007,Vol.30,No.4,pp:222-226
[5]Horace Ho-Shing Ip,Dinggang Shen:An affine-invariant active contour model(AI-snake)for model-based segmentation[J],Image Vision Comput,1998,Vol.16,No.2,pp.135-146
[6]P.Brigger,J.Hoeg,M.Unser,B-Spline Snakes:A Flexible Tool for Parametric Comtour Detection[J],IEEE Transactions on Image Processing,2000,Vol.9,No.9,pp.1484-1496
[7]G.Giraldi,E.Strauss,A.Olibeira,A boundary extraction method based on dual-T-snakes and dynamic programming[A],Proc.CVPR 2000[C],2000,pp.1044-1049
[8]Chen G,Gu L,Qian L,and Xu J,An Improved Level Set for Liver Segmentation and Perfusion Analysis in MRIs[J],IEEE transactions on information technology in biomedicine,2009,Vol.13,No.1,pp.94-103
[9]Yan Nei Law Hwee Kuan Lee,Yip A.M,A Multiresolution Stochastic Level Set Method for Mumford-Shah Image Segmentation[J],IEEE Transactions on Image Processing,2008,Vol.17,No.12,pp,2289-2300
[10]Ben Ayed I.,Mitiche A.,A Region Merging Prior for Variational Level Set Image Segmentation[J],IEEE Transactions on Image Processing,2008,Vol.17,No.12,pp.2301-2311
[11]Folkesson J.,Samset E.,Kwong R.Y.,et al,Unifying statistical classification and geodesic active regions for segmentation of cardiac MRI[J],IEEE Transactions on Information Technology in Biomedicine,2008,Vol.12,No.3,pp.328-334
[12]Lei Ying,Zhi-Pei Liang,David C.Munson,et al.,Unwrapping of MR phase images using a Markov random field model[J].IEEE Transaction on Medical Imaging,2006,Vol.26,No.10,pp.128-136
[13]Mathews Jacob,Xiaoping Zhu,Zhi-Pei Liang,et al.,Improved model-basedmagnetic resonance spectroscopic imaging[J].IEEE Transaction on Medical Imaging,2007,Vol.26,No.10,PP.1305-1318
[14]Sam S. Stong,Justin P. Haldar,Stephanie C. Tsao,Wen-mei W.Hwu,et al.,Accelerating advanced MRI reconstructions on GPUS[A].Proc.Conf.Computing Frontiers 2008[C]:261-272
[15]Steven C.Mitchell,Johan G. Bosch,B P. F. Lelieveldt,et al.3D active appearance models:segmentation of cardiac MR and ultrasound images[J],IEEE Transaction on Medical Imaging,2002,Vol.26,No.10,pp.1167-1179
[16]E. Oost,G.konging,M.Sonka,et al,Automated contour detection in X-ray leftventricular angiograms using multiview active appearance models anddynamic programming[J],IEEE Transaction on Medical Imaging,2006,Vol.25,No.9,pp.1158-1171
[17]J.G.Bosch,S.C.Mitchell,B.P.F.Lelieveldt,et al.,Automatic segmentation of echocardiographic sequences by active appearance motion models[J],IEEE Transaction on Medical Imaging,2002,Vol.21,No.11,pp.1374-1383
[18]Kunio Doi,Computer-aided diagnosis in medical imaging:Historicl review,current status and future potential[J],Computerized Medical Imaging and Graphics,2007,Vol.31,No.4-5,pp.198-211
[19]Shuji Sakai,Hidetake Yabuuchi,Yoshio Matsuo,et al.,Integration of temporal subtraction and nodule detection system for digital chest radiographs into Picture Archiving and Communication System(PACS):Four-year Experience[J].Digital Imaging,2008,Vol.21,No.1,pp.91-98
[20]Timothy F.Cootes,Carole J.Twining,Kolawole O.Babalola,et al.,Diffeomorphic statistical shape models[J].Image Vision Comput,2008,Vol.26,No.3,pp.326-332
[21]David Cristinacce,Timothy F.Cootes:Automatic feature localization with constrained local models[J].Computer Vision and Image Understanding,2007,Vol.41,No.10,pp.3054-3067
[22]Rasmus Larsen,Mikkel B.Stegmann,Sune Darkner,et al.,Texture enhanced appearance models[J].Computer Vision and Image Understanding,2007,Vol.106,No.1,pp.20-30
[23]Juan R.Cebral,Marcelo Adrián Castro,Sunil Appanaboyina,et al.,Efficient pipeline for image-based patient-specific analysis of cerebral aneurysm hemodynamics:technique and sensitivity[J].IEEE Transaction on Medical Imaging,2005,Vol.24,No.4,PP.457-467
[24]Consrantine Butakoff,Alejandro F.Frangi:A Framework for Weighted Fusion of Multiple Statistical Models of Shape and Appearance[J].IEEE Transaction onPattern Analysis Machine Intelligence,2006,Vol.28,No.11,pp.1847-1857
[25]R.D.Millan,Laura Dempere-Marco,J.M.Pozo,et al.,Morphological Characterization of Intracranial Aneurysms Using 3-D Moment Invariants[J].IEEE Transaction on Medical Imaging,2007,Vol.26,No.9,pp.1270-1282
[26]C.Tobon-Gomez,Constantine Butakoff,S. Aguade,et al.,Automatic Construction of 3D-ASM Intensity Models by Simulating Image Acquisition:Application to Myocardial Gated SPECT Studies[J].IEEE Transaction on Medical Imaging,2008,Vol.27,No.11,pp.1655-1667
[27]Mikkel B.Stegmann,Bjarne K.Ersboll,Rasmus Larsen,FAME-A Flexible Appearance Modelling Environment[J],IEEE Transaction on Medical Imaging,2003,Vol.22,No.10,pp.1319-1331
[28]Joger Hansegard,Stig Urheim,Ketil Lunde,er al.,Constrained Active Appearande Models for Segmentation of Triplane Echocardiograms[J],IEEE Transaction on Medical Imaging,2007,Vol.26,No.10,pp.1391-1401
[29]Tomaz Vrtovec,Franjo Pernus,Bostjan Likar,A Symmetry-Based Method for the Determination of Vertebral Rotation in 3D[A],Proc.MICCA[C],2008:942-950
[30]Tomaz Vrtovec,Bostjan Likar and Franjo Pernus,Quantitative analysis of spinal curvature in 3D:application to CT images of normal spine[J],Physics in Medicine and Biology,2008,Vol.53,No.10,pp.1895-1908
[31]Jie Tian,Jing Bai,Xiu-Ping Yan,Shanglian Bao,Yinghui Li,Wei Liang,and Xin Yang,Multimodality molecular imaging[J],IEEE Engineering in Medicing and Biology Magazine,2008,Vol.27,No.5,pp.48-57
[32]Jie Tian,Jian Xue,Yakang Dai,Jian Chen and Jian Zheng.A Novel Software Platform for Medical Image Processing and Analyzing[J].IEEE Transaction on Information Technology in Biomedicing,2008,Vol.12,No.6,pp.800-812
[33]罗希平,田捷.一种交互式医学图像序列分割方法[J].电子学报,2003,Vol.31,No.1,pp.29-32
[34]薛键,田捷,戴亚康,陈健,海量医学数据处理框架及快速体绘制算法[J].软件学报,2008,Vol.19,No.12,pp.3237-3248
[35]彭文,童若锋,钱归平,董金祥,使用特征点与曲线配准医学图像[J].计算机辅助设计与图形学学报,2006,Vol.18,No.09,pp.1126-1131
[36]秦绪佳,王青,鲍虎军.基于散乱点的增量式曲面逼近[J].计算机辅助设计与图形学学报,2005,Vol.17,No.10,pp.2168-2173
[37]陆剑锋,林海,潘志庚.自适应区域生长算法在医学图像分割中的应用[J].计算机辅助设计与图形学学报,2005,Vol.17,No.10,pp.2168-2173
[38]张绍祥,刘正津,谭立文等.首例中国数字化可视人体完成[J].第三军医大学学报,2002,Vol.24,No.2,pp.1231-1232
[39]钟世镇,李华等,数字化虚拟中国人女性一号(VCH-F1)实验数据集研究报告[J].第一军医大学学报,2003,Vol.23,No.6,pp.193-196
[40]原林,唐雷,黄文华等.虚拟中国人男性一号(VCH-M1)数据集研究[J],第一军医大学学报,2003,Vol.23,No.6,pp.520-523
[41]简江涛,安滨,熊进,刘军伟,冯焕清.中国数字人切片图像的自动配准与分割方法研究[J],中国科学技术大学学报,2007,Vol.37,No.2,pp.195-199
[42]ZHAO ZheEn,Teoh E K.A new scheme for automated 3D PDM construction using deformable models[J]. Image and Vision Computing, 2008, Vol.26,No.2,pp. 275-288.
[43]Lee S J, Sung J W, Kim D J. Tensor-Based AAM with continuous variation estimation, application to variation-robust face recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2009, Vol.31,No.6,pp. 1102-1116.
[44]王绍宇,戚飞虎,夏小玲.基于MDL Shape Model及EFD的行人轮廓2D+time表示[J].中国图象图形学报,2008,Vol.13,No.10,pp.1898-1901
[45]I.T.Jolliffe.Principal Component Analysis[M],Springer-Verlag,New York Berlin Heidelberg Tokio,1986
[46]F.L.Bookstein.Landmark methods for forms without landmarks:localizing group differences in outline shape[J].Medical Image Analysis,1997,Vol.1,No.3,pp.225-244
[47]A.Baumberg,D.Hogg.Learning flexible models from image sequences[A], ECCV1994[C],1994,pp. 299–308
[48]A.Hill,C.Taylor.Automatic landmark generation for point distribution models[A],BMVC1994[C], 1994, pp. 429–438
[49]A.Hill,C.J.Taylor.A framework for automatic landmark identification using a new method of nonrigid correspondence[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,vol. 22,No.3, pp. 241–251
[50]A.Kelemen,G.Szekely,G.Gerig.Elastic model-based segmentation of 3-D neuroradiological data sets[J],IEEE Transaction on Medical Imaging,1999,vol.18,No.10,pp. 828–839
[51]A.C.W.Kotcheff ,C.J.Taylor.Automatic construction of eigenshape models by direct optimization[J] ,Medical Image Analysis, 1998,vol. 2,No.4, pp:303–314
[52]D.Rueckert, F.Frangi,J.A.Schnabel.Automatic construction of 3D statistical defomation models using nonrigid registration[A],MICCAI2001[C],2001,pp. 77–84
[53]Y.Wang,B.S.Peterson,L.H.Staib.Shape-based 3D surface correspondence using geodesics and local geometry[A], CVPR 2000[C],2000, pp. 644–651
[54]Y.Wang,B.S.Peterson,L.H.Staib, Shape-based 3D surface correspondence usinggeodesics and local geometry[A],CVPR 2000[C],2000,vol. 2, pp. 644–651
[55]A.Benayoun,N.Ayache,I.Cohen.Adaptive meshes and non-rigid motion computation[A],ICPR1994[C], 1994, pp. 730–732
[56]C.Kambhamettu,D.B.Goldgof.Point correspondence recovery in non-rigid motion[A],CVPR1992[C], 1992, pp. 222–227
[57]H.D.Tagare.Shape-based non-rigid correspondence with application to heart motion analysis[J],IEEE Transaction on Medical Imaging,1999,vol.18,No.7,pp. 434–349
[58]F.L.Bookstein.Landmarkmethods for formswithout landmarks:Mor-phometrics of group differences in outline shape[J],Medical Image Analysis,1997Vol.1,No.3, pp. 225–243
[59]Davies R H,Twining C J,Cootes T F,Waterton J C,Tylor C J,A Minimum Description Length Approach to Statistical Shape Modeling[J].IEEE Transaction on Medical Imaging, 2002, Vol.21,No.5,pp.525-537.
[60]Thodberg H H.Minimum Description Length Shape and Appearance Models[A],Information Processing in Medical Imaging[C], 2003,PP.51-62.
[61]Andre Souza,Jayaram K.Udupa.Automatic Landmark Slection for Active Shape Models[A],SPIE2005[C],2005,PP.1-7
[62]Sylvia Rueda,Jayaram K.Udupa,Li Bai.Landmark selection for shape model construction via equalization of variance[A], ISBI 2008[C],2008,PP. 1271-1274