血管造影图像统计分割研究
|
摘要
心脑血管疾病目前已成为对人类威胁最大的三大类疾病之首,血管造影图像是当前诊断、治疗和深入了解该类疾病的主要手段。磁共振血管造影技术(Magnetic Resonance Angiography,MRA)由于不需注入造影剂,无任何创伤,三维信息的获取容易实现,目前已在医院广泛使用。目前适用于脑血管的MR血管成像技术只有时间飞越法(Time of Flight ,TOF)血管成像技术和相位对比(Phase Contrast ,PC)血管成像技术。鉴于TOF法成像速度快,可用于观察血管与周围结构的关系,是目前医院使用最广的成像方法,因此,在本论文中所有试验都是以针对TOF MRA为主。
磁共振血管造影图像的特点和血管结构的复杂性都对现有的图像处理技术提出了挑战。本论文以实现基于病人个体的血管三维分割重建这一应用为背景,主要针对基于统计分类的血管造影图像分割进行了深入的研究,主要开展了如下的工作:
1.深入分析了当前主流血管造影图像分割技术,重点对基于统计模型的分割方法进行了研究。主要包括:有限混合模型聚类算法的原理、面临的问题以及解决对策,常用参数估计算法的选择。给出了常用马尔科夫随机场模型的能量函数和局部概率函数,对常用能量最小化优化算法的进行了对比分析研究。
2.在充分考虑图像的高阶多尺度特征地基础上,提出了一种新颖的脑血管图像分割方法。首先,通过K最近邻法将高阶多尺度特征映射到一概率图像。随后,将灰度特征和概率信息同时并入贝叶斯分割框架。与仅依靠灰度特征的分割方法相比,新方法能够很好地克服飞跃法磁共振血管成像区域灰度变化大所带来的分割困难。实验结果也表明新方法可以获得更为准确的分割结果且不需要对分割结果进行后处理。
3.提出了一种改进的自适应血管分割方法,首先,为了获得更为准确的分割方法,我们利用一个局部观测模型来取代全局观测模型;其次,对于二值分割这个特定应用,为了加快分割过程,在充分利用血管组织仅占颅腔5%这一先验知识的基础上,对迭代条件模式算法(Iterated Conditional Modes,ICM)进行了改进,改进后的算法极大的减少了分割过程的处理时间。为了验证所提算法的准确性和快速性,我们分别采用人工合成模型和实际临床数据对算法性能进行了验证。
Vascular diseases are the top of the major sources of deaths in the world. Angiographic imaging is commonly used world-wide for the diagnosis of cardiovascular, cerebrovascular, and peripheral vascular disease.
Magnetic resonance angiography (MRA) is a noninvasive MRI-based flow imaging technique. Its ability to provide detailed images of blood vessels enabled its use in the diagnosis and surgical planning of the blood vessels diseases. It is widely used clinically.
There are two techniques commonly used in performing MRA: time-of-flight (TOF) angiography, phase contrast angiography (PCA).Because of its fast and high contrast, TOF is widely used clinically and is the main motivation behind our work. However, it is the big challenge for the nowdays image processing technique as the limitation of MRA imaging and the complex vasculature structure.
To implement the magnetic resonance angiography image-based patient-specific three dimension reconstruction, this dissertation focuses on the research of statistical model based blood vessels extraction.The major works are as follows:
1. A deep research on statistical models based segmentation method was focused, after making a comprehensive research on major blood vessel segmentation techniques proposed in the up-to-date literature. The main research content includes: Bayes segmentation framework, the selection of finite mixture model and parameters estimation techniques; the difference between different Markov random field models and energy minimization algorithms.
2. In TOF MRA, intensity values are often not sufficiently high in the low flow regions where the vascular signal approximates that of the background. A drawback of this kind of methods is with poor capability in capturing distal blood vessels, while in some applications this finer detail may be required.A multi-feature incorporated bayes segmentation framework was proposed. Different from most of the existing methods, we have paid same attention to the shape feature of blood vessels and intensity feature. Both high order multiscale feature and intensity feature are incorporated into a Bayesian segmentation framework. Maximum a posterior (MAP) method is further used to estimate the posterior probabilities of vessel and background for classification. The results present clearly that the segmentation algorithm does capture many of the distal arteries.
3. An adaptive statistical approach to extracting whole cerebrovascular tree in time-of-flight magnetic resonance angiography (TOF-MRA) is proposed. Firstly, in order to get a more accurate segmentation result, a localized observation model is proposed instead of defining the observation model over the entire dataset. Secondly, for the binary segmentation, an improved Iterative Conditional Model (ICM) algorithm is presented to accelerate the segmentation process. The experimental results showed that the proposed algorithm can obtain more satisfactory segmentation results and save more processing time than conventional approaches, simultaneously.
磁共振血管造影图像的特点和血管结构的复杂性都对现有的图像处理技术提出了挑战。本论文以实现基于病人个体的血管三维分割重建这一应用为背景,主要针对基于统计分类的血管造影图像分割进行了深入的研究,主要开展了如下的工作:
1.深入分析了当前主流血管造影图像分割技术,重点对基于统计模型的分割方法进行了研究。主要包括:有限混合模型聚类算法的原理、面临的问题以及解决对策,常用参数估计算法的选择。给出了常用马尔科夫随机场模型的能量函数和局部概率函数,对常用能量最小化优化算法的进行了对比分析研究。
2.在充分考虑图像的高阶多尺度特征地基础上,提出了一种新颖的脑血管图像分割方法。首先,通过K最近邻法将高阶多尺度特征映射到一概率图像。随后,将灰度特征和概率信息同时并入贝叶斯分割框架。与仅依靠灰度特征的分割方法相比,新方法能够很好地克服飞跃法磁共振血管成像区域灰度变化大所带来的分割困难。实验结果也表明新方法可以获得更为准确的分割结果且不需要对分割结果进行后处理。
3.提出了一种改进的自适应血管分割方法,首先,为了获得更为准确的分割方法,我们利用一个局部观测模型来取代全局观测模型;其次,对于二值分割这个特定应用,为了加快分割过程,在充分利用血管组织仅占颅腔5%这一先验知识的基础上,对迭代条件模式算法(Iterated Conditional Modes,ICM)进行了改进,改进后的算法极大的减少了分割过程的处理时间。为了验证所提算法的准确性和快速性,我们分别采用人工合成模型和实际临床数据对算法性能进行了验证。
Vascular diseases are the top of the major sources of deaths in the world. Angiographic imaging is commonly used world-wide for the diagnosis of cardiovascular, cerebrovascular, and peripheral vascular disease.
Magnetic resonance angiography (MRA) is a noninvasive MRI-based flow imaging technique. Its ability to provide detailed images of blood vessels enabled its use in the diagnosis and surgical planning of the blood vessels diseases. It is widely used clinically.
There are two techniques commonly used in performing MRA: time-of-flight (TOF) angiography, phase contrast angiography (PCA).Because of its fast and high contrast, TOF is widely used clinically and is the main motivation behind our work. However, it is the big challenge for the nowdays image processing technique as the limitation of MRA imaging and the complex vasculature structure.
To implement the magnetic resonance angiography image-based patient-specific three dimension reconstruction, this dissertation focuses on the research of statistical model based blood vessels extraction.The major works are as follows:
1. A deep research on statistical models based segmentation method was focused, after making a comprehensive research on major blood vessel segmentation techniques proposed in the up-to-date literature. The main research content includes: Bayes segmentation framework, the selection of finite mixture model and parameters estimation techniques; the difference between different Markov random field models and energy minimization algorithms.
2. In TOF MRA, intensity values are often not sufficiently high in the low flow regions where the vascular signal approximates that of the background. A drawback of this kind of methods is with poor capability in capturing distal blood vessels, while in some applications this finer detail may be required.A multi-feature incorporated bayes segmentation framework was proposed. Different from most of the existing methods, we have paid same attention to the shape feature of blood vessels and intensity feature. Both high order multiscale feature and intensity feature are incorporated into a Bayesian segmentation framework. Maximum a posterior (MAP) method is further used to estimate the posterior probabilities of vessel and background for classification. The results present clearly that the segmentation algorithm does capture many of the distal arteries.
3. An adaptive statistical approach to extracting whole cerebrovascular tree in time-of-flight magnetic resonance angiography (TOF-MRA) is proposed. Firstly, in order to get a more accurate segmentation result, a localized observation model is proposed instead of defining the observation model over the entire dataset. Secondly, for the binary segmentation, an improved Iterative Conditional Model (ICM) algorithm is presented to accelerate the segmentation process. The experimental results showed that the proposed algorithm can obtain more satisfactory segmentation results and save more processing time than conventional approaches, simultaneously.
引文
[1] http://www.med.jhu.du/vascsurg/AAAA1A1.html-Anchor-11 481/.
[2]Group E.C.S.T.C., Randomised trial of endarterectony for recently carotid stenosis: Final results of MRC European Carotid Surgery(ECST). Lancet, 1998. 351(9113): 1379-1387.
[3]Coatrieux J. L., Collorec M.G., R., Roux C., Computer vision approaches for the three dimensional reconstruction of coronary arteries: Review and prospects. Critical Rev. Biomed. Eng.,1994. 22(1): 1-38.
[4]Higgins W.E., Spyra W.J.T., Karwoski R.A., Ritman E.L., System for analyzing high-resolution three dimensional coronary angiograms. IEEE Trans. Med. Imag., 1996. 15: 377-385.
[5]Stafford Johnson D.B.,Prince M.R.,Chenevert T.L.,Magnetic resonance angiography: a review[J].Acad Radiol,1998,5(4):289-305.
[6] Nishimura D.G., et al., Magnetic resonance angiography. IEEE Trans. Med. Imag, 1986. 5: 140-151.
[7] Kawata Y., Niki N., and Kumazaki, T., Computer-assisted analysis and 3D visualization of blood vessels based on cone-beam CT images. Image Analysis Applications and Computer Graphics. Berlin, Germany: Springer-Verlag,1995.
[8] Marks M.P., Napel S., Jordan J.E., et al., Diagnosis of carotid artery disease: Preliminary experience with MIP spiral CT angiography. Amer. J. Radiol., 1993. 160(6): 1267-1271.
[9]Rosenfield J.K.,Pieczek A.M., Human coronary and peripheral arteries: On-line three-dimensional reconstruction from 2-D intravascular US scans: Work in progress. Radiology, 1992, 184(3): 823-832.
[10] Shekhar R., Cothren R.M., Vince D.G.et al., Three dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images. Computerized Medical Imaging and Graphics, 1999. 23(6): 299-309.
[11]Cothren R.M., Shekhar R., Tuzcu E.M., et al., Three dimensional reconstruction of the coronary artery wall by image fusion of intravascular ultrasound and bi-plane angiography,Int. J. Card. Imaging, 2000. 16(2): 69-85.
[12]罗述谦,周果宏. 医学图象处理与分析[M].北京:科学出版社,2003.
[13] Pal N.R.,Pals K., A Review on image segmentation techniques. Pattern Recognition. 1999 ,(24):131-137 .
[14]Pham D. L., Xu C., Prince J.L., Current Methods in Medical Image Segmentation [J]. Annual Review of Biomedical Engineering, 2000,2:315-338
[15]Kapur T., Model-based three-dimensional medical image segmentation, Ph.D. thesis, Artif. Intell. Lab., Massachusetts Inst. Technol., Cambridge, 1999.
[16]Nakajima S, Atsumi H, Kikinis R, et al.,Use of cortical surface vessel registration for image-guided neurosurgery. Neurosurgery, 1997. 6(40): 1201-1210.
[17]Kikinis R.,Gleason L.,Moriarty T.M.,et al., Computer-assisted interactive three dimensionalplanning for neurosurgical procedures. Neurosurgery, 1996. 38(4): 640-651.
[18] Broeders I.A., Blankensteijn J.D., Olree M., et al. Preoperative sizing of grafts for transfemoral endovascular aneurysm management: A prospective comparative study of spiral CT angiography, arteriography and conventional CT imaging. J. Endovascular Surgery,, 1997. 4(3): 252-261.
[19] Lanzino G.,Kaptain G.,Kallems D.F., et al. Intracranial dissecting aneurysm causing subarachnoid hemorrhage: The role of computerized tomographic angiography and magnetic resonance angiography. Surg. Neurol., 1997. 48(5): 477-481.
[20] Guglielmi G., Vinuela F., Sepetka I., et al. Electrothrombosis of saccular aneurysms via endovascular approach. Part 1: Electrochemical basis, technique, and experimental results. J Neurosurg 1991,75:1-7.
[21]Masutani Y., Kurihara T., Suzuki M., Dohi T., Quantitative vascular shape analysis for 3-D MR-angiography using mathematical morphology in Computer Vision, Virtual Reality, and Robotics in Medicine,. 1995: 449-454.
[22] Anderson C.M., Lee R.E., Levin D.L., et al., Measurement of internal carotid artery stenosis from source MR angiograms. Radiology 1994, 193:219-226.
[23] Yim P.J., Mullick R., Summers R.M.,et al., Measurement of stenosis from magnetic resonance angiography using vessel skeletons. Proceedings of SPIE,2000 ,3978, 245.
[24]Patel M.R., Klufas R.A., Kim D., et al.,MR-angiography of the carotid bifurcation: artifacts and limitations. AJR, 1994,182:1431-7.
[25] Chan T. F., Shen J., Vese L., Variational PDE models in image processing[J]. Notices of the American Mathematical Society, 2003,50(1):14-26
[26] Li S.Z., Markov Random Field Modeling in Computer vision. 1995: Springer-Verlag.
[27]Gimelfarb, G.L., Imge Textures and Gibbs Random Fields. 1999: Kluwer Academic Publishers.
[28]Mallat S., A wavelet tour of signal processing. 1998: Academic Press.
[29] Chambolle A., Nonlinear Wavelet Image Processing: Variational Problems, Compression, and Noise Removal Through Wavelet Shrinkage[J]. IEEE Trans on Image Processing, 1998, (7): 319-335.
[30]Donoho D., Nonlinear solution of linear inverse problems by wavelet-vaguelet decomposition. Applied and Computational Harmonic Analysis, 1995. 2: 101-126.
[31] Li S.Z., Markov Random Field Modeling in Computer Vision[M]. Tokyo: Springer-Verlag, 1995.
[32]Rajapakse J.C., Statistical approach to segmentation of single-channel cerebral MR images, IEEE Trans[J]. Medical Imaging, 1997, 16(2):176-186.
[33]Pappas T. N.,An adaptive clustering algorithm for image segmentation[J]. IEEE Trans Signal Proc,1992,40 (4): 901-914.
[34]Held K, Kops E.R., Krause B.J., . et al.. Markov random field segmentation of brain MR images.IEEE Trans. Med. Imaging , 1997,16(6):878–86
[35]Li S.Z , Markov Random Field Modeling in Computer Vision. Berlin,New York: Springer-Verlag. 264 [85] 1995.
[36] Papoulis A.,Probability, Random Variables, and Stochastic Pro-cesses[M]. New York: McGraw-Hill, 1991.
[37] Derin H, Elliott H.,Modeling and segmentation of noisy and textured images using Gibbs random fields. IEEE Trans. on Pattern Anal. Machine Intell., 1987, 9(1): 39-55.
[38]Derin H., Cole W.S., Segmentation of Textured Images Using Gibbs Random Fields, Computer Vision. Computer Graphics and Image Processing,1987: 40-5.
[39]Hu R.,Fahmy M.M.,Texture Segmentation Based on a Hierarchical Markov Random Filed Model[J].Signal Processing,1992,26:285-305.
[40]Haralick R. M., Shapiro L. G.., Image segmentation techniques [J]. CVGIP, 1985,29:100-132.
[41] Kirbas C.,Quek F.,A review of vessel extraction techniques and algorithms [J].ACM Computing Surveys,2004,36(6):81-121.
[42]Kirbas C, Quek F. K. H., Vessel extraction techniques and algorithms: A survey[A]. Proceedings of the Third IEEE Symposium on Bio Informatics and Bio Engineering (BIBE'03)[C].2003: 238-245.
[43] Suri J., Liu K., Reden L. and Laxminarayan S., A review on MR vascular image processing: skeleton versus nonskeleton approaches: part II. IEEE Transactions on Information Technology in Biomedicine 2002,6(4): 338-350.
[44] Bulpitt A.J., Berry E., Spiral CT of abdominal aortic aneurysms:. Comparison of segmentation with and automatic 3D deformable model. and interactive segmentation, Proc. SPIE, 1998,3338: 938–946.
[45]Rueckert D.,Burger P., Forbat S.M., Automatic tracking of the aorta in cardiovascular MR images using deformable models. IEEE Transactions on Medical Imaging, 1997, 16(5):581-590.
[46] Toledo R., Orriols X., Radeva P., Eigensnakes for Vessel Segmentation in Angiography. ICPR 2000: 4340-4343.
[47]Wink O., Niessen W.J., Viergever M.A,, Fast Quantification of Abdominal Aortic Aneurysms from CTA Volumes. Proceeding of Medical Image Computing and Computer-Assisted Intervention 1998: 138-145.
[48]Niessen W.J., Montauban A.D., Elsman B.H.P., et al., Improved arterial visualization in blood pool agent MRA of the peripheral vasculature. Computer Assisted Radiology and Surgery ,1999:119-123.
[49]Sato Y., Shiraga N., Nakajima S., et al., Local maximum intensity projection (LMIP): A new rendering method for vascular visualization. J. comput. Assist. Tomogr. 1998, 6(22):912-919.
[50]Wilson D.L., Nobel J.A., Segmentation of cerebral vessels and aneurysms from MR angiography data, Lect. Notes Comput. Sci., 1997,1230:423–428.
[51]Masutani, Y., Kurihara, T., and Suzuki, M.,Quantitative Vascular Shape Analysis for 3D MR-Angiography Using Mathematical Morphology. Computer Vision, Virtual Reality and Robotics in Medicine, 1995: 449-454.
[52]Cline H. E., Enhanced visualization of weak image sources in the vicinity of dominant sources. U.S. Patent 6 058 218, 2000.
[53]Saha P.K.,Udupa J.K.,Odhner D.,Scale-based fuzzy connected image segmentation : theory , algorithms,and validation.Computer Vision and Image Understanding,2000,77(2):145-174.
[54]Lorigo L.M., Faugeras O.D., Grimson W.E.L., et al., Curves: Curve evolution for vessel segmentation. Medical Image Analysis, 2001,5:185-206.
[55] Armande N., Montesinos P., Monga O., et al. Thin Nets Extraction Using a Multi-scale Approach [J]. Computer Vision and Image Understanding, 1999, 73(2): 248-257.
[56]Frangi A.F., Niessen W.J., Hoogeveen R.M., et al., Model-based quantitation of 3-D magnetic resonance angiographic images. IEEE Trans. Med. Imaging, 1999,18(10): 946-956.
[57] Luo, L. M., Hamitouche, C., Dillenseger, J. L. et al., A moment-based three-dimensional edge operator[J]. IEEE Trans. BME, 1993, 40(7):693-703.
[58]Krissian K., Maladain G., Vaillant R., Trousset Y., Ayache N., Model-based. multiscale detection of 3D vessels. Proc. IEEE Conference on Computer Vision and Pattern Recognition. 1998: 722–727.
[59] Krissian K., Malandain G., Ayache N., Vaillant R., Trousset Y., Model Based Detection of Tubular Structures in 3D Images. Computer Vision and Image Understanding, 2000,80(2): 130-171.
[60]Marr D. ,Vision[M]. W. H. Freeman and Company,1982.
[61]]Witkin A., Scale space filtering. In: Proc 8th International Joint Confence Artifical Intelligence,1983:1019-1021.
[62] Koenderink J. J. ,The Structure of Images. Biological Cybernetics, 1984, 50: 363-396.
[63]Babaud J., Witkin A. P., Baudin M., Duds R.O., Uniqueness of the gaussian kernel for scale-space filtering. IEEE Trans Pattern Analysis and Machine Intelligence, 1986,8 (1): 26- 33.
[64]Perona P.,Malik J.Scale-space and edge detection using anisotropic diffusion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[65]Frangi A.F., Niessen W.J., Vincken K.L., Viergever M.A.,Multiscale vessel enhancement filtering. In: Proceedings of the Interantional Conference on Medical Image Computing Computerassisted Intervention. Lect. Notes Comp. Sci., 1998,1496:130–137.
[66]Sato Y., Nakajima S., Shiraga N., Atsumi H., et al., Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. Med. Image Anal. 1998, 2 (2): 143–168.
[67]Lorenz C., Carlsen I.C., Buzug T.M., et al.., A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation. In:Proceedings of the Scale-space Theories in Computer Vision. Lect. Notes Comp. Sci., 1997, 1252: 152–163.
[68]Krissian K., Malandain G., Ayache N., et al., Model based multiscale detection of 3D vessels. Proc. IEEE Int. Conf. Comp. Vision Patt. Recog., 1998: 722–727.
[69]Aylward S., Pizer S.M., Bullitt E., Eberly D., Intensity ridge and widths for 3D object segmentation and description. In: IEEE Proceedings of the Workshop Mathematical Models Biomedical Image Analysis, 1996: 131–138.
[70]Kass M., Witkin A., Terzopoulos D., Snakes: Active contour models. International Journal of Computer Vision, 1988,1(4):321-331.
[71]Amini A.A., Weymouth T.E. Using dynamic programming for solving variational problems in vision [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1990-12, 12(9): 855 -867.
[72] Cohen L.D., On active contour models and balloons, CVGIP: Imag. Under.,1991, 53(2): 211-218.
[73]Caselles V., Catte F.,Coll T.,Dibos F.A Geometric Model for Active Contours.Numerische Mathematik,1993 ,66:1-31 .
[74]Malladi R., Sethian J A, Vemuri B. Shape modeling with front propagation: A level set approach[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1995,17(2):158-175.
[75]Caselles V., Kimmel R., Sapiro G. Geodesic active contours. Int'l Journal of Computer Vision, 1997,22(1):61-79.
[76] Kimia B.B., Tannenbaum A.R., Zucker S.W., Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space, Int'l J. Comp. Vis., 1995, 15(3):189-224.
[77]Kimmel R., Amir A., Bruckstein A.M., Finding shortest paths on surfaces using level sets propagation, IEEE Trans. on Patt. Anal. Mach. Intell., 1995, 17(6):635-640.
[78]Osher S., Sethian J A. Fronts propagating with curvature -dependent speed: algorithms based on Hamilton-Jacobi formulations. J ComputationalPhysics, 1988, 79:12-49.
[79]Yim P. J., Cebral J. R., et al.., Vessel surface reconstruction with a tubular deformable model. IEEE Trans. Med. Imaging , 2001,20(12):1411 – 1421.
[80]Bruijne M.V., Ginneken B.V., Niessen W.J., Viergever M.A., Active shape model segmentation using a non-linear appearance model: application to 3D AAA segmentation. Technical Report UU-CS-2003-13, Institute of Information and Computing Sciences, Utrecht University, 2003.
[81]Aylward S.R., Bullitt E.,. Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction. IEEE Trans. Med. Imaging, 2002, 21(2): 61 – 75.
[82]Wink O., Niessen W.J., Viergever M.A., Multiscale vessel tracking. IEEE Trans. Med. Imaging, 2004, 23(1): 130 – 133.
[83]Fridman, Y., Pizer S.M., Aylward S., Bullitt E., Extracting branching tubular object geometry via cores. Med. Image. Anal. , 2004,8(3): 196 – 176.
[84]Volkau I., Weili Z., et al., Geometric modeling of the human normal cerebral arterial system. IEEE Trans. Med. Imaging, 2005, 24(4): 529 – 539.
[85]Deschamps T., Curve and shape extraction with minimal path and level-sets techniques. applications to 3D medical imaging. Ph.D. Thesis, University of Paris-Dauphine, France, 2001.
[86]Antiga L., Ene-Iordache B., Remuzzi A., Computational geometry for patient-specific reconstruction and meshing of blood vessels from MR and CT angiography. IEEE Trans. Med. Imaging 2003,22(5): 674 – 684.
[87]van Bemmel C.M., Spreeuwers L.J.,et al., Level-set-based artery-vein separation in blood pool agent CE-MR angiograms. IEEE Trans. Med. Imaging, 2003,22(10): 1224 – 1234.
[88]Hernandez M., Frangi A.F., Geodesic active regions using nonparametric statistical regional description and their application to aneurysm segmentation from CTA. Medical Imaging and Augmented Reality (MIAR’2004), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany , 2004,3150: 94 – 102.
[89]Lorigo L.M., Faugeras O., et al.,Codimension-two geodesic active contours for the segmentation of tubular structures. In: IEEE Conference on Computer Vision and Pattern Recognition, 2000,1: 444 – 451.
[90] Yan P., Kassim A., Segmentation of volumetric MRA images by using capillary active contour, Medical Image Analysis, 2006,10(3):317–329.
[91]Manniesing R., Velthuis B.K.,et al.,Level set based cerebral vasculature segmentation anddiameter quantification in CT angiography. Medical Image Analysis, 2006,10(2):200-214.
[92]Holtzman-Gazit M., Kimmel R., Peled N., Goldsher D., Segmentation of thin structures in volumetric medical images. IEEE Trans. Med. Imaging, 2006,15(2): 354 – 363.
[93]Chen J., Amini A. A., Quantifying 3D vascular structures in MRA images using hybrid pde and geometric deformable models. IEEE Trans. Med. Imaging, 2004,23 (10): 1251 – 1261.
[94]Wilson D.L., Noble J.A., An adaptive segmentation algorithm for time-of-flight MRA data. IEEE Trans. Med. Imaging 1999,18 (10):938–945.
[95]Chung A., Noble J.A., Statistical 3D vessel segmentation using a Rician distribution. In: Proceedings of the International Conference on Medical Image Computing Computer-assisted Intervention. Lect. Notes Comp. Sci., 1999,1679:82–89.
[96] Hassouna M.S., Sites C.B., Farag A.A., Hushek S., Moriarty, T.,Statistical cerebrovascular segmentation for phasecontrast MRA data. Proceedings of the International Conference on Biomedical Engineering, 2002:101–105.
[97]Chung A.C.S., Noble J.A., Summers P., Fusing speed and phase information for vascular segmentation of phase contrast MR angiograms. Med. Image Anal., 2002, 6 (2):109–128.
[98]Hassouna M.S., Farag A.A., Hushek S., Mori- arty T., Cerebrovascular segmentation from TOF using stochastic models, Medical Image Analysis, 2006,10: 2-18.
[99] Wong W.C.K., Chung A.C.S., Bayesian Image Segmentation. Using Local Iso-intensity Structural Orientation, IEEE Trans. Image. Processing, 2005,14 (10):1512–1523.
[100]Gan R., Chung A.C.S., Wong W.C.K., Yu S.C.H., Vascular segmentation in three-dimensional rotational angiography based on maximum intensity projections. ISBI, 2004:133–136.
[101]Parker D.L., Chapman B.E., Roberts J.A., Alexander A.L., Enhanced Image Detail Using Continuity in the MIP Z-Buffer: Applications to Magnetic Resonance Angiography. JMRI 2000,11:378-388.
[102] Chapman B.E., Stapelton J.O., Parker D.L.,Intracranial vessel segmentation from time-of-.flight MRA using pre-processing of the MIP Z-buffer: accuracy of the ZBS algorithm. Med Image Analysis, 2004,8(2):113-126.
[103]Reuze P., Coatrieux J.L., Luo L.M., Dillenserger J.L., A 3-d moment based. approach for blood vessel detection and quantification in MRA, Technology and Health Care, 1993,1:181-188.
[104] Hernandez-Hoyos M., et al., Inertia-Based Vessel Axis Extraction and Stenosis Quantification in 3D MRA images, Proc. Comp. Assisted Radiology and Surgery (CARS), Paris, France, 1999: 189-193.
[105] Verdonck B., et al., A new system for blood vessel segmentation and visualization in 3D MR and spiral CT angiography. Comput. Assisted Radiol. Surg., 1995: 177–182.
[106]Summers P., Bhalerao A.H., et.al.,. Multiresolution, model based segmentation of MR angiograms. J. Magn. Reson. Imaging, 1997, 7: 950–957.
[107]Masutani Y., Schiemann T., et al.,. Vascular shape segmentation and structure extraction using a shape-based region-growing model. In: Proceedings MICCAI, 1998,1242–1249.
[108]Farag A.A., Hassan H., Falk R., Hushek S.G., 3D volume segmentation of MRA data sets using level sets: image processing and display. Acad. Radio,2004,l: 419–435.
[109]Chen T., Metaxas, Dimitris N., Image segmentation based on the integration of Markovrandom fields and deformable models. Proceedings of the MICCAI, Pittsburgh, PA, 2000: 256–265.
[110]Chen T., Metaxas, Dimitris N., Gibbs Prior Models, Marching Cubes, and Deformable Models: A Hybrid Framework for 3D Medical Image Segmentation, MICCAI, Montre′al, Que′bec, Canada 2003, 2: 703–710.
[111]Zhang Y.J., A survey on evaluation methods for image segmentation. Pattern Recognition, 1996; 29 (80):1335
[112]Zhang, Y.J., Evaluation and Comparison of Different Segmentation Algorithms, Pattern Recognition Letters,1997,10(18): 963-974.
[113]Geman S.,Geman D.,Stochastic Relaxation,Gibbs Distributions,and the Bayesian Restoration of Images [J].IEEE Trans on PAMI,1984,6(6):721-741.
[114]Besag J. ,On the statistical analysis of dirty pictures[J]. J R Statist Soc B, 1986, 48(3):259-302.
[115]Jain A.K. ,Duin R.P.W., Mao J.C., Statistical pattern recognition:a review, IEEE Transactions on Pattern Analysis and Machine Intelligence,2000;22(1):4-37.
[116]Mclachlan G. J.,Basford K E.Mixture models:inference and applications to clustering[M].New York:Marcel Dekker,1988.
[117]Pearson K., Contributions to the mathematical theory of evolution.Phil.Trans.Soc.London, Series A, 1894, 185: 71-78.
[118] Dempster A.P., Laird N.M., Rubin, D.B.,Maximum likelihood from incomplete data via EM algorithm ( with discussion). JRSSB, 1997, 39: 1-38.
[119]Biernacki C., Celeux G., Govaert G.,Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate gaussian mixture models. Computational Statistics & Data Analysis ,2003,41: 561-575.
[120] Ueda, N. and Nakano, R., Deterministic annealing EM algorithm. Neural Networks, 1998,vol. 11:271-282.
[121]Ueda N., Nakano R., et al., SMEM algorithm for mixture models [J]. Neural Computation, 2000, 12(9): 2109-2128.
[122]Frigui H., Krishnapuram R., Clustering by competitive agglomeration[J]. Pattern Recognition,1997, 30(7):1109-1119.
[123]Roberts S. J., Bayesian Approaches to Gaussian Mixture Modeling [J]. IEEE Trans on Pattern Analysis and Machines Intelligence, 1998, 20(11): 1133-1142.
[124] Mario A T Figueiredo, Jose M N Leitao, Anil K Jain. On fitting mixture models [ J ], Energy Minimization Methods in Computer Vision and Pattern Recognition, Springer-Verlag,1999:54- 69.
[125] Fraley C., Algorithms for model-based Gaussian hierarchical clustering. SIAM Journal on Scientific Computing, 1999,20:270-281.
[126]Dave R N, Krishnapuram R. Robust clustering methods: A unified view. IEEE Transactions on Fuzzy Systems, 1997,5(2): 270-293.
[127]Banfield J.D.,Raftery A.E.,Model-based Gaussian and non-Gaussian clustering[J]. Biometrics,1993, 49:803-821.
[128]Huber, P.J., Robust Statistics, John Wiley, New York, 1981.
[129]Neal R, Hinton G.,A View of the EM Algorithm That Justifies Incremental, Sparse and Other Variants. Technical Report, Dept. of Statistics, University of Toronto, 1993.
[130] Celeux G..,Govaert G.., Comparison of the mixture and the classification maximum likelihood in cluster analysis. J. Statis. Comput. Simul.,1993, 47:127-146.
[131]McLachlan G., Peel D.,Finite Mixture Models[M].New York:Wiley,2000.
[132]Biernacki C.,Celeux G.,Govaert G.,Choosing Starting Values for the EM Algorithm for Getting the Highest Likelihood in Multivariate Gaussian Mixture Models[J].Computational Statistics and Data analysis,2003:561-575。
[133]Schwarz G., Estimating the Dimension of a Model[M]. Ann. Statist., 1978: 461-464.
[134]Burnham K.P., Anderson D.R., Model Selection and Inferrence: a Practical Information Theoretic Approach. New York: Springer-Verlag, 1998.
[135]Fraley C., Raflery A.E., How many clusters? Which Clustering method? Answers vis model-based cluster analysis. The Computer Journal, 1998, 41:578-588.
[136]Biemacki C., Celeux G., Govaelt G., Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood. IEEE Trans. on. PAMI,2000, 221:719-725.
[137]Biernacki C.,Celeux G.,Govaert G.., An improvement of the NEC criterion for assessing the number of components arising from a mixture,'' Pattern Recognition letters, 1999,No. 20: 267-272.
[138]Celeux G., Soromenho G., An entropy criterion for assessing the number of clusters in a mixture model. Journal of Classification, 1996,13:195–212.
[139]Zhang J., The mean field theory in EM procedures for markov random fields[J].IEEE Trans on Signal Processing,1992,40:2570-2583.
[140]Besag J.,Spatial interaction and the statistical analysis of lattice systems(with discussion)[J].J R Stat Soc B-36,1974:192-236.
[141]Moussouris J.,Gibbs and Markov systems with constraints. Journal of statistical physics, 1974,10:11-33.
[142]Kindermann R., Snell J.L.,Markov Random Fields and Their Applications. American Mathematical Society, Providence, R.I, 1980.
[143]Griffeath, D., Introduction to random fields. Springer-Verlag, New York, 2nd edition,1976, chapter 12:425-458.
[144] Panjwani, D.K., Healey, G.,Markov Random Field Models for Unsupervised Segmentation of Textured Color Images[J]. IEEE Trans. Pattern Anal. Machine Intell., 1995,10(17):939-954.
[145]Geman S. and McClure D.,Bayesian image analysis: An application to single photon emission tomography. In Proceedings of the Statistical Computing Section, Washington, DC.,1985, 12-18.
[146]Besag, J.,Towards Bayesian image analysis, Journal of Applied Statistics, 1989,16(3):395-406.
[147]Geman, D. and Gidas, B. ,Image analysis and computer vision', 1991,chapter 2, 9-36. National Academy Press.
[148]Besag J.,Statistical analysis of non-lattice data, The Statistician, 1975,24(3):179-195.
[149]Besag J.,Efficiency of pseudo-likelihood estimation for simple Gaussian fields, Biometrika, 1977,64:616-618.
[150]Geman S., Graffigne C., Markov random field image models and their applications to computer vision. In Proc. of the Intl Congress of Mathematicians, Berkeley, California.1986,1496–1517,.
[151] Forbes F,Peyrard N.,Hidden Markov Random Field Model Selection Criteria based on MeanField-like Approximations, in: in IEEE trans. PAMI, August 2003, vol. 25(9): 1089–1101.
[152]Zhang J.,The mean field theory in EM procedures for blind Markov random field image restoration, IEEE Trans. Image Processing, 1993,vol. 2: 27–40.
[153]Derin H., Elliott H., Modeling and segmentation of noisy and textured images using Gibbs random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(1):39-55.
[154]Nain D, Yezzi A, and Turk G, “Vessel Segmentation Using a Shape. Driven Flow”, MICCAI 2004, LNCS 3216, (2004) pp. 51-59.
[155].Marr D. ,Vision[M]. W. H. Freeman and Company,1982.
[156]Witkin A. Scale space filtering. In: Proc 8th International Joint Confence Artifical Intelligence,1983,1019-1021
[157]Koenderink J. J. The Structure of Images. Biological Cybernetics, 1984, 50: 363-396.
[158]Babaud J., Witkin A. P., Baudin M., Duds R.O., Uniqueness of the gaussian kernel for scale-space filtering. IEEE Trans Pattern Analysis and Machine Intelligence, 1986, 8 (1): 26- 33.
[159]Perona P, Malik J.Scale-space and edge detection using anisotropic diffusion [J].IEEE Trans.Pattern Anal.Mach.Intell,1990,12(7):629-639.
[160]Lorenz C., et al.. Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. Proc. CVRMed-MRCAS’97, Lecture Notes in Computer Science, 1997,233–242.
[161]Lindeberg T., Edge detection and ridge detection with automatic scale selection. In Proc. Conf.on Comp. Vis. and Pat. Recog., San Francisco, CA, June 1996,465–470,.
[162]Haralick R., Shapiro L., Computer and robot vision. Lecture Notes in Computer Science. 1992,Vol. 1, Addison Wesley.
[163] Sole, A.F., Crease Enhancement Diffusion. Computer Vision and Image Understanding, 2001, 84: 241-248.
[164]Besag, J.,. Efficiency of pseudo-likelihood estimation for simple Gaussian fields. Biometrika , 1977,64: 616–618.
[165]贾富仓, 生物医学图像组织统计分类研究, 中国科学院计算技术研究所, 博士学位论文,2004.
[166]Kirkpatrick S., Gelatt C.D.,Vecchi M.P.,Optimization by Simulated Annealing, Science, 220, 1983,4598: 671-680,.
[2]Group E.C.S.T.C., Randomised trial of endarterectony for recently carotid stenosis: Final results of MRC European Carotid Surgery(ECST). Lancet, 1998. 351(9113): 1379-1387.
[3]Coatrieux J. L., Collorec M.G., R., Roux C., Computer vision approaches for the three dimensional reconstruction of coronary arteries: Review and prospects. Critical Rev. Biomed. Eng.,1994. 22(1): 1-38.
[4]Higgins W.E., Spyra W.J.T., Karwoski R.A., Ritman E.L., System for analyzing high-resolution three dimensional coronary angiograms. IEEE Trans. Med. Imag., 1996. 15: 377-385.
[5]Stafford Johnson D.B.,Prince M.R.,Chenevert T.L.,Magnetic resonance angiography: a review[J].Acad Radiol,1998,5(4):289-305.
[6] Nishimura D.G., et al., Magnetic resonance angiography. IEEE Trans. Med. Imag, 1986. 5: 140-151.
[7] Kawata Y., Niki N., and Kumazaki, T., Computer-assisted analysis and 3D visualization of blood vessels based on cone-beam CT images. Image Analysis Applications and Computer Graphics. Berlin, Germany: Springer-Verlag,1995.
[8] Marks M.P., Napel S., Jordan J.E., et al., Diagnosis of carotid artery disease: Preliminary experience with MIP spiral CT angiography. Amer. J. Radiol., 1993. 160(6): 1267-1271.
[9]Rosenfield J.K.,Pieczek A.M., Human coronary and peripheral arteries: On-line three-dimensional reconstruction from 2-D intravascular US scans: Work in progress. Radiology, 1992, 184(3): 823-832.
[10] Shekhar R., Cothren R.M., Vince D.G.et al., Three dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images. Computerized Medical Imaging and Graphics, 1999. 23(6): 299-309.
[11]Cothren R.M., Shekhar R., Tuzcu E.M., et al., Three dimensional reconstruction of the coronary artery wall by image fusion of intravascular ultrasound and bi-plane angiography,Int. J. Card. Imaging, 2000. 16(2): 69-85.
[12]罗述谦,周果宏. 医学图象处理与分析[M].北京:科学出版社,2003.
[13] Pal N.R.,Pals K., A Review on image segmentation techniques. Pattern Recognition. 1999 ,(24):131-137 .
[14]Pham D. L., Xu C., Prince J.L., Current Methods in Medical Image Segmentation [J]. Annual Review of Biomedical Engineering, 2000,2:315-338
[15]Kapur T., Model-based three-dimensional medical image segmentation, Ph.D. thesis, Artif. Intell. Lab., Massachusetts Inst. Technol., Cambridge, 1999.
[16]Nakajima S, Atsumi H, Kikinis R, et al.,Use of cortical surface vessel registration for image-guided neurosurgery. Neurosurgery, 1997. 6(40): 1201-1210.
[17]Kikinis R.,Gleason L.,Moriarty T.M.,et al., Computer-assisted interactive three dimensionalplanning for neurosurgical procedures. Neurosurgery, 1996. 38(4): 640-651.
[18] Broeders I.A., Blankensteijn J.D., Olree M., et al. Preoperative sizing of grafts for transfemoral endovascular aneurysm management: A prospective comparative study of spiral CT angiography, arteriography and conventional CT imaging. J. Endovascular Surgery,, 1997. 4(3): 252-261.
[19] Lanzino G.,Kaptain G.,Kallems D.F., et al. Intracranial dissecting aneurysm causing subarachnoid hemorrhage: The role of computerized tomographic angiography and magnetic resonance angiography. Surg. Neurol., 1997. 48(5): 477-481.
[20] Guglielmi G., Vinuela F., Sepetka I., et al. Electrothrombosis of saccular aneurysms via endovascular approach. Part 1: Electrochemical basis, technique, and experimental results. J Neurosurg 1991,75:1-7.
[21]Masutani Y., Kurihara T., Suzuki M., Dohi T., Quantitative vascular shape analysis for 3-D MR-angiography using mathematical morphology in Computer Vision, Virtual Reality, and Robotics in Medicine,. 1995: 449-454.
[22] Anderson C.M., Lee R.E., Levin D.L., et al., Measurement of internal carotid artery stenosis from source MR angiograms. Radiology 1994, 193:219-226.
[23] Yim P.J., Mullick R., Summers R.M.,et al., Measurement of stenosis from magnetic resonance angiography using vessel skeletons. Proceedings of SPIE,2000 ,3978, 245.
[24]Patel M.R., Klufas R.A., Kim D., et al.,MR-angiography of the carotid bifurcation: artifacts and limitations. AJR, 1994,182:1431-7.
[25] Chan T. F., Shen J., Vese L., Variational PDE models in image processing[J]. Notices of the American Mathematical Society, 2003,50(1):14-26
[26] Li S.Z., Markov Random Field Modeling in Computer vision. 1995: Springer-Verlag.
[27]Gimelfarb, G.L., Imge Textures and Gibbs Random Fields. 1999: Kluwer Academic Publishers.
[28]Mallat S., A wavelet tour of signal processing. 1998: Academic Press.
[29] Chambolle A., Nonlinear Wavelet Image Processing: Variational Problems, Compression, and Noise Removal Through Wavelet Shrinkage[J]. IEEE Trans on Image Processing, 1998, (7): 319-335.
[30]Donoho D., Nonlinear solution of linear inverse problems by wavelet-vaguelet decomposition. Applied and Computational Harmonic Analysis, 1995. 2: 101-126.
[31] Li S.Z., Markov Random Field Modeling in Computer Vision[M]. Tokyo: Springer-Verlag, 1995.
[32]Rajapakse J.C., Statistical approach to segmentation of single-channel cerebral MR images, IEEE Trans[J]. Medical Imaging, 1997, 16(2):176-186.
[33]Pappas T. N.,An adaptive clustering algorithm for image segmentation[J]. IEEE Trans Signal Proc,1992,40 (4): 901-914.
[34]Held K, Kops E.R., Krause B.J., . et al.. Markov random field segmentation of brain MR images.IEEE Trans. Med. Imaging , 1997,16(6):878–86
[35]Li S.Z , Markov Random Field Modeling in Computer Vision. Berlin,New York: Springer-Verlag. 264 [85] 1995.
[36] Papoulis A.,Probability, Random Variables, and Stochastic Pro-cesses[M]. New York: McGraw-Hill, 1991.
[37] Derin H, Elliott H.,Modeling and segmentation of noisy and textured images using Gibbs random fields. IEEE Trans. on Pattern Anal. Machine Intell., 1987, 9(1): 39-55.
[38]Derin H., Cole W.S., Segmentation of Textured Images Using Gibbs Random Fields, Computer Vision. Computer Graphics and Image Processing,1987: 40-5.
[39]Hu R.,Fahmy M.M.,Texture Segmentation Based on a Hierarchical Markov Random Filed Model[J].Signal Processing,1992,26:285-305.
[40]Haralick R. M., Shapiro L. G.., Image segmentation techniques [J]. CVGIP, 1985,29:100-132.
[41] Kirbas C.,Quek F.,A review of vessel extraction techniques and algorithms [J].ACM Computing Surveys,2004,36(6):81-121.
[42]Kirbas C, Quek F. K. H., Vessel extraction techniques and algorithms: A survey[A]. Proceedings of the Third IEEE Symposium on Bio Informatics and Bio Engineering (BIBE'03)[C].2003: 238-245.
[43] Suri J., Liu K., Reden L. and Laxminarayan S., A review on MR vascular image processing: skeleton versus nonskeleton approaches: part II. IEEE Transactions on Information Technology in Biomedicine 2002,6(4): 338-350.
[44] Bulpitt A.J., Berry E., Spiral CT of abdominal aortic aneurysms:. Comparison of segmentation with and automatic 3D deformable model. and interactive segmentation, Proc. SPIE, 1998,3338: 938–946.
[45]Rueckert D.,Burger P., Forbat S.M., Automatic tracking of the aorta in cardiovascular MR images using deformable models. IEEE Transactions on Medical Imaging, 1997, 16(5):581-590.
[46] Toledo R., Orriols X., Radeva P., Eigensnakes for Vessel Segmentation in Angiography. ICPR 2000: 4340-4343.
[47]Wink O., Niessen W.J., Viergever M.A,, Fast Quantification of Abdominal Aortic Aneurysms from CTA Volumes. Proceeding of Medical Image Computing and Computer-Assisted Intervention 1998: 138-145.
[48]Niessen W.J., Montauban A.D., Elsman B.H.P., et al., Improved arterial visualization in blood pool agent MRA of the peripheral vasculature. Computer Assisted Radiology and Surgery ,1999:119-123.
[49]Sato Y., Shiraga N., Nakajima S., et al., Local maximum intensity projection (LMIP): A new rendering method for vascular visualization. J. comput. Assist. Tomogr. 1998, 6(22):912-919.
[50]Wilson D.L., Nobel J.A., Segmentation of cerebral vessels and aneurysms from MR angiography data, Lect. Notes Comput. Sci., 1997,1230:423–428.
[51]Masutani, Y., Kurihara, T., and Suzuki, M.,Quantitative Vascular Shape Analysis for 3D MR-Angiography Using Mathematical Morphology. Computer Vision, Virtual Reality and Robotics in Medicine, 1995: 449-454.
[52]Cline H. E., Enhanced visualization of weak image sources in the vicinity of dominant sources. U.S. Patent 6 058 218, 2000.
[53]Saha P.K.,Udupa J.K.,Odhner D.,Scale-based fuzzy connected image segmentation : theory , algorithms,and validation.Computer Vision and Image Understanding,2000,77(2):145-174.
[54]Lorigo L.M., Faugeras O.D., Grimson W.E.L., et al., Curves: Curve evolution for vessel segmentation. Medical Image Analysis, 2001,5:185-206.
[55] Armande N., Montesinos P., Monga O., et al. Thin Nets Extraction Using a Multi-scale Approach [J]. Computer Vision and Image Understanding, 1999, 73(2): 248-257.
[56]Frangi A.F., Niessen W.J., Hoogeveen R.M., et al., Model-based quantitation of 3-D magnetic resonance angiographic images. IEEE Trans. Med. Imaging, 1999,18(10): 946-956.
[57] Luo, L. M., Hamitouche, C., Dillenseger, J. L. et al., A moment-based three-dimensional edge operator[J]. IEEE Trans. BME, 1993, 40(7):693-703.
[58]Krissian K., Maladain G., Vaillant R., Trousset Y., Ayache N., Model-based. multiscale detection of 3D vessels. Proc. IEEE Conference on Computer Vision and Pattern Recognition. 1998: 722–727.
[59] Krissian K., Malandain G., Ayache N., Vaillant R., Trousset Y., Model Based Detection of Tubular Structures in 3D Images. Computer Vision and Image Understanding, 2000,80(2): 130-171.
[60]Marr D. ,Vision[M]. W. H. Freeman and Company,1982.
[61]]Witkin A., Scale space filtering. In: Proc 8th International Joint Confence Artifical Intelligence,1983:1019-1021.
[62] Koenderink J. J. ,The Structure of Images. Biological Cybernetics, 1984, 50: 363-396.
[63]Babaud J., Witkin A. P., Baudin M., Duds R.O., Uniqueness of the gaussian kernel for scale-space filtering. IEEE Trans Pattern Analysis and Machine Intelligence, 1986,8 (1): 26- 33.
[64]Perona P.,Malik J.Scale-space and edge detection using anisotropic diffusion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[65]Frangi A.F., Niessen W.J., Vincken K.L., Viergever M.A.,Multiscale vessel enhancement filtering. In: Proceedings of the Interantional Conference on Medical Image Computing Computerassisted Intervention. Lect. Notes Comp. Sci., 1998,1496:130–137.
[66]Sato Y., Nakajima S., Shiraga N., Atsumi H., et al., Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. Med. Image Anal. 1998, 2 (2): 143–168.
[67]Lorenz C., Carlsen I.C., Buzug T.M., et al.., A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation. In:Proceedings of the Scale-space Theories in Computer Vision. Lect. Notes Comp. Sci., 1997, 1252: 152–163.
[68]Krissian K., Malandain G., Ayache N., et al., Model based multiscale detection of 3D vessels. Proc. IEEE Int. Conf. Comp. Vision Patt. Recog., 1998: 722–727.
[69]Aylward S., Pizer S.M., Bullitt E., Eberly D., Intensity ridge and widths for 3D object segmentation and description. In: IEEE Proceedings of the Workshop Mathematical Models Biomedical Image Analysis, 1996: 131–138.
[70]Kass M., Witkin A., Terzopoulos D., Snakes: Active contour models. International Journal of Computer Vision, 1988,1(4):321-331.
[71]Amini A.A., Weymouth T.E. Using dynamic programming for solving variational problems in vision [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1990-12, 12(9): 855 -867.
[72] Cohen L.D., On active contour models and balloons, CVGIP: Imag. Under.,1991, 53(2): 211-218.
[73]Caselles V., Catte F.,Coll T.,Dibos F.A Geometric Model for Active Contours.Numerische Mathematik,1993 ,66:1-31 .
[74]Malladi R., Sethian J A, Vemuri B. Shape modeling with front propagation: A level set approach[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1995,17(2):158-175.
[75]Caselles V., Kimmel R., Sapiro G. Geodesic active contours. Int'l Journal of Computer Vision, 1997,22(1):61-79.
[76] Kimia B.B., Tannenbaum A.R., Zucker S.W., Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space, Int'l J. Comp. Vis., 1995, 15(3):189-224.
[77]Kimmel R., Amir A., Bruckstein A.M., Finding shortest paths on surfaces using level sets propagation, IEEE Trans. on Patt. Anal. Mach. Intell., 1995, 17(6):635-640.
[78]Osher S., Sethian J A. Fronts propagating with curvature -dependent speed: algorithms based on Hamilton-Jacobi formulations. J ComputationalPhysics, 1988, 79:12-49.
[79]Yim P. J., Cebral J. R., et al.., Vessel surface reconstruction with a tubular deformable model. IEEE Trans. Med. Imaging , 2001,20(12):1411 – 1421.
[80]Bruijne M.V., Ginneken B.V., Niessen W.J., Viergever M.A., Active shape model segmentation using a non-linear appearance model: application to 3D AAA segmentation. Technical Report UU-CS-2003-13, Institute of Information and Computing Sciences, Utrecht University, 2003.
[81]Aylward S.R., Bullitt E.,. Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction. IEEE Trans. Med. Imaging, 2002, 21(2): 61 – 75.
[82]Wink O., Niessen W.J., Viergever M.A., Multiscale vessel tracking. IEEE Trans. Med. Imaging, 2004, 23(1): 130 – 133.
[83]Fridman, Y., Pizer S.M., Aylward S., Bullitt E., Extracting branching tubular object geometry via cores. Med. Image. Anal. , 2004,8(3): 196 – 176.
[84]Volkau I., Weili Z., et al., Geometric modeling of the human normal cerebral arterial system. IEEE Trans. Med. Imaging, 2005, 24(4): 529 – 539.
[85]Deschamps T., Curve and shape extraction with minimal path and level-sets techniques. applications to 3D medical imaging. Ph.D. Thesis, University of Paris-Dauphine, France, 2001.
[86]Antiga L., Ene-Iordache B., Remuzzi A., Computational geometry for patient-specific reconstruction and meshing of blood vessels from MR and CT angiography. IEEE Trans. Med. Imaging 2003,22(5): 674 – 684.
[87]van Bemmel C.M., Spreeuwers L.J.,et al., Level-set-based artery-vein separation in blood pool agent CE-MR angiograms. IEEE Trans. Med. Imaging, 2003,22(10): 1224 – 1234.
[88]Hernandez M., Frangi A.F., Geodesic active regions using nonparametric statistical regional description and their application to aneurysm segmentation from CTA. Medical Imaging and Augmented Reality (MIAR’2004), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany , 2004,3150: 94 – 102.
[89]Lorigo L.M., Faugeras O., et al.,Codimension-two geodesic active contours for the segmentation of tubular structures. In: IEEE Conference on Computer Vision and Pattern Recognition, 2000,1: 444 – 451.
[90] Yan P., Kassim A., Segmentation of volumetric MRA images by using capillary active contour, Medical Image Analysis, 2006,10(3):317–329.
[91]Manniesing R., Velthuis B.K.,et al.,Level set based cerebral vasculature segmentation anddiameter quantification in CT angiography. Medical Image Analysis, 2006,10(2):200-214.
[92]Holtzman-Gazit M., Kimmel R., Peled N., Goldsher D., Segmentation of thin structures in volumetric medical images. IEEE Trans. Med. Imaging, 2006,15(2): 354 – 363.
[93]Chen J., Amini A. A., Quantifying 3D vascular structures in MRA images using hybrid pde and geometric deformable models. IEEE Trans. Med. Imaging, 2004,23 (10): 1251 – 1261.
[94]Wilson D.L., Noble J.A., An adaptive segmentation algorithm for time-of-flight MRA data. IEEE Trans. Med. Imaging 1999,18 (10):938–945.
[95]Chung A., Noble J.A., Statistical 3D vessel segmentation using a Rician distribution. In: Proceedings of the International Conference on Medical Image Computing Computer-assisted Intervention. Lect. Notes Comp. Sci., 1999,1679:82–89.
[96] Hassouna M.S., Sites C.B., Farag A.A., Hushek S., Moriarty, T.,Statistical cerebrovascular segmentation for phasecontrast MRA data. Proceedings of the International Conference on Biomedical Engineering, 2002:101–105.
[97]Chung A.C.S., Noble J.A., Summers P., Fusing speed and phase information for vascular segmentation of phase contrast MR angiograms. Med. Image Anal., 2002, 6 (2):109–128.
[98]Hassouna M.S., Farag A.A., Hushek S., Mori- arty T., Cerebrovascular segmentation from TOF using stochastic models, Medical Image Analysis, 2006,10: 2-18.
[99] Wong W.C.K., Chung A.C.S., Bayesian Image Segmentation. Using Local Iso-intensity Structural Orientation, IEEE Trans. Image. Processing, 2005,14 (10):1512–1523.
[100]Gan R., Chung A.C.S., Wong W.C.K., Yu S.C.H., Vascular segmentation in three-dimensional rotational angiography based on maximum intensity projections. ISBI, 2004:133–136.
[101]Parker D.L., Chapman B.E., Roberts J.A., Alexander A.L., Enhanced Image Detail Using Continuity in the MIP Z-Buffer: Applications to Magnetic Resonance Angiography. JMRI 2000,11:378-388.
[102] Chapman B.E., Stapelton J.O., Parker D.L.,Intracranial vessel segmentation from time-of-.flight MRA using pre-processing of the MIP Z-buffer: accuracy of the ZBS algorithm. Med Image Analysis, 2004,8(2):113-126.
[103]Reuze P., Coatrieux J.L., Luo L.M., Dillenserger J.L., A 3-d moment based. approach for blood vessel detection and quantification in MRA, Technology and Health Care, 1993,1:181-188.
[104] Hernandez-Hoyos M., et al., Inertia-Based Vessel Axis Extraction and Stenosis Quantification in 3D MRA images, Proc. Comp. Assisted Radiology and Surgery (CARS), Paris, France, 1999: 189-193.
[105] Verdonck B., et al., A new system for blood vessel segmentation and visualization in 3D MR and spiral CT angiography. Comput. Assisted Radiol. Surg., 1995: 177–182.
[106]Summers P., Bhalerao A.H., et.al.,. Multiresolution, model based segmentation of MR angiograms. J. Magn. Reson. Imaging, 1997, 7: 950–957.
[107]Masutani Y., Schiemann T., et al.,. Vascular shape segmentation and structure extraction using a shape-based region-growing model. In: Proceedings MICCAI, 1998,1242–1249.
[108]Farag A.A., Hassan H., Falk R., Hushek S.G., 3D volume segmentation of MRA data sets using level sets: image processing and display. Acad. Radio,2004,l: 419–435.
[109]Chen T., Metaxas, Dimitris N., Image segmentation based on the integration of Markovrandom fields and deformable models. Proceedings of the MICCAI, Pittsburgh, PA, 2000: 256–265.
[110]Chen T., Metaxas, Dimitris N., Gibbs Prior Models, Marching Cubes, and Deformable Models: A Hybrid Framework for 3D Medical Image Segmentation, MICCAI, Montre′al, Que′bec, Canada 2003, 2: 703–710.
[111]Zhang Y.J., A survey on evaluation methods for image segmentation. Pattern Recognition, 1996; 29 (80):1335
[112]Zhang, Y.J., Evaluation and Comparison of Different Segmentation Algorithms, Pattern Recognition Letters,1997,10(18): 963-974.
[113]Geman S.,Geman D.,Stochastic Relaxation,Gibbs Distributions,and the Bayesian Restoration of Images [J].IEEE Trans on PAMI,1984,6(6):721-741.
[114]Besag J. ,On the statistical analysis of dirty pictures[J]. J R Statist Soc B, 1986, 48(3):259-302.
[115]Jain A.K. ,Duin R.P.W., Mao J.C., Statistical pattern recognition:a review, IEEE Transactions on Pattern Analysis and Machine Intelligence,2000;22(1):4-37.
[116]Mclachlan G. J.,Basford K E.Mixture models:inference and applications to clustering[M].New York:Marcel Dekker,1988.
[117]Pearson K., Contributions to the mathematical theory of evolution.Phil.Trans.Soc.London, Series A, 1894, 185: 71-78.
[118] Dempster A.P., Laird N.M., Rubin, D.B.,Maximum likelihood from incomplete data via EM algorithm ( with discussion). JRSSB, 1997, 39: 1-38.
[119]Biernacki C., Celeux G., Govaert G.,Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate gaussian mixture models. Computational Statistics & Data Analysis ,2003,41: 561-575.
[120] Ueda, N. and Nakano, R., Deterministic annealing EM algorithm. Neural Networks, 1998,vol. 11:271-282.
[121]Ueda N., Nakano R., et al., SMEM algorithm for mixture models [J]. Neural Computation, 2000, 12(9): 2109-2128.
[122]Frigui H., Krishnapuram R., Clustering by competitive agglomeration[J]. Pattern Recognition,1997, 30(7):1109-1119.
[123]Roberts S. J., Bayesian Approaches to Gaussian Mixture Modeling [J]. IEEE Trans on Pattern Analysis and Machines Intelligence, 1998, 20(11): 1133-1142.
[124] Mario A T Figueiredo, Jose M N Leitao, Anil K Jain. On fitting mixture models [ J ], Energy Minimization Methods in Computer Vision and Pattern Recognition, Springer-Verlag,1999:54- 69.
[125] Fraley C., Algorithms for model-based Gaussian hierarchical clustering. SIAM Journal on Scientific Computing, 1999,20:270-281.
[126]Dave R N, Krishnapuram R. Robust clustering methods: A unified view. IEEE Transactions on Fuzzy Systems, 1997,5(2): 270-293.
[127]Banfield J.D.,Raftery A.E.,Model-based Gaussian and non-Gaussian clustering[J]. Biometrics,1993, 49:803-821.
[128]Huber, P.J., Robust Statistics, John Wiley, New York, 1981.
[129]Neal R, Hinton G.,A View of the EM Algorithm That Justifies Incremental, Sparse and Other Variants. Technical Report, Dept. of Statistics, University of Toronto, 1993.
[130] Celeux G..,Govaert G.., Comparison of the mixture and the classification maximum likelihood in cluster analysis. J. Statis. Comput. Simul.,1993, 47:127-146.
[131]McLachlan G., Peel D.,Finite Mixture Models[M].New York:Wiley,2000.
[132]Biernacki C.,Celeux G.,Govaert G.,Choosing Starting Values for the EM Algorithm for Getting the Highest Likelihood in Multivariate Gaussian Mixture Models[J].Computational Statistics and Data analysis,2003:561-575。
[133]Schwarz G., Estimating the Dimension of a Model[M]. Ann. Statist., 1978: 461-464.
[134]Burnham K.P., Anderson D.R., Model Selection and Inferrence: a Practical Information Theoretic Approach. New York: Springer-Verlag, 1998.
[135]Fraley C., Raflery A.E., How many clusters? Which Clustering method? Answers vis model-based cluster analysis. The Computer Journal, 1998, 41:578-588.
[136]Biemacki C., Celeux G., Govaelt G., Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood. IEEE Trans. on. PAMI,2000, 221:719-725.
[137]Biernacki C.,Celeux G.,Govaert G.., An improvement of the NEC criterion for assessing the number of components arising from a mixture,'' Pattern Recognition letters, 1999,No. 20: 267-272.
[138]Celeux G., Soromenho G., An entropy criterion for assessing the number of clusters in a mixture model. Journal of Classification, 1996,13:195–212.
[139]Zhang J., The mean field theory in EM procedures for markov random fields[J].IEEE Trans on Signal Processing,1992,40:2570-2583.
[140]Besag J.,Spatial interaction and the statistical analysis of lattice systems(with discussion)[J].J R Stat Soc B-36,1974:192-236.
[141]Moussouris J.,Gibbs and Markov systems with constraints. Journal of statistical physics, 1974,10:11-33.
[142]Kindermann R., Snell J.L.,Markov Random Fields and Their Applications. American Mathematical Society, Providence, R.I, 1980.
[143]Griffeath, D., Introduction to random fields. Springer-Verlag, New York, 2nd edition,1976, chapter 12:425-458.
[144] Panjwani, D.K., Healey, G.,Markov Random Field Models for Unsupervised Segmentation of Textured Color Images[J]. IEEE Trans. Pattern Anal. Machine Intell., 1995,10(17):939-954.
[145]Geman S. and McClure D.,Bayesian image analysis: An application to single photon emission tomography. In Proceedings of the Statistical Computing Section, Washington, DC.,1985, 12-18.
[146]Besag, J.,Towards Bayesian image analysis, Journal of Applied Statistics, 1989,16(3):395-406.
[147]Geman, D. and Gidas, B. ,Image analysis and computer vision', 1991,chapter 2, 9-36. National Academy Press.
[148]Besag J.,Statistical analysis of non-lattice data, The Statistician, 1975,24(3):179-195.
[149]Besag J.,Efficiency of pseudo-likelihood estimation for simple Gaussian fields, Biometrika, 1977,64:616-618.
[150]Geman S., Graffigne C., Markov random field image models and their applications to computer vision. In Proc. of the Intl Congress of Mathematicians, Berkeley, California.1986,1496–1517,.
[151] Forbes F,Peyrard N.,Hidden Markov Random Field Model Selection Criteria based on MeanField-like Approximations, in: in IEEE trans. PAMI, August 2003, vol. 25(9): 1089–1101.
[152]Zhang J.,The mean field theory in EM procedures for blind Markov random field image restoration, IEEE Trans. Image Processing, 1993,vol. 2: 27–40.
[153]Derin H., Elliott H., Modeling and segmentation of noisy and textured images using Gibbs random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(1):39-55.
[154]Nain D, Yezzi A, and Turk G, “Vessel Segmentation Using a Shape. Driven Flow”, MICCAI 2004, LNCS 3216, (2004) pp. 51-59.
[155].Marr D. ,Vision[M]. W. H. Freeman and Company,1982.
[156]Witkin A. Scale space filtering. In: Proc 8th International Joint Confence Artifical Intelligence,1983,1019-1021
[157]Koenderink J. J. The Structure of Images. Biological Cybernetics, 1984, 50: 363-396.
[158]Babaud J., Witkin A. P., Baudin M., Duds R.O., Uniqueness of the gaussian kernel for scale-space filtering. IEEE Trans Pattern Analysis and Machine Intelligence, 1986, 8 (1): 26- 33.
[159]Perona P, Malik J.Scale-space and edge detection using anisotropic diffusion [J].IEEE Trans.Pattern Anal.Mach.Intell,1990,12(7):629-639.
[160]Lorenz C., et al.. Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. Proc. CVRMed-MRCAS’97, Lecture Notes in Computer Science, 1997,233–242.
[161]Lindeberg T., Edge detection and ridge detection with automatic scale selection. In Proc. Conf.on Comp. Vis. and Pat. Recog., San Francisco, CA, June 1996,465–470,.
[162]Haralick R., Shapiro L., Computer and robot vision. Lecture Notes in Computer Science. 1992,Vol. 1, Addison Wesley.
[163] Sole, A.F., Crease Enhancement Diffusion. Computer Vision and Image Understanding, 2001, 84: 241-248.
[164]Besag, J.,. Efficiency of pseudo-likelihood estimation for simple Gaussian fields. Biometrika , 1977,64: 616–618.
[165]贾富仓, 生物医学图像组织统计分类研究, 中国科学院计算技术研究所, 博士学位论文,2004.
[166]Kirkpatrick S., Gelatt C.D.,Vecchi M.P.,Optimization by Simulated Annealing, Science, 220, 1983,4598: 671-680,.