摘要
医学图像三维重建及可视化技术在临床诊治、远程医疗、手术规划及模拟仿真、整形及假肢外科、放射治疗规划、解剖教学等方面都有重要应用。三维重建方法主要包括面绘制和体绘制两种。
脑部不同物质的准确分类是重构三维大脑的基础,但体绘制方法中体数据的分类问题还没有提出很好的解决方法。针对这个问题,本文提出了一种基于多尺度连接模型的人脑磁共振图像模糊分类的算法,该算法建立在图像分割结果必须要在尺度内和不同尺度上同时得到优化的基础上。算法的实现过程如下:首先,对脑MR图像偏场分析,进行灰度不均匀性校正;然后,用非线性扩散连接模型来建立不同尺度间的模糊相似性,再通过非线性扩散连接模型引入新的尺度间的模糊约束,新的约束描述了高尺度和低尺度的模糊连接关系;相应地,定义了两个模糊距离来描述相邻尺度上父子像素和聚类中心的相似性,并引入到模糊聚类算法中;通过组合尺度之间和尺度内的模糊约束,定义了一个新的多分辨模糊聚类框架。
在实验中对正常人和多发性硬化疾病的脑MR图像数据用该方法进行分类并可视化,表明该方法能够准确地分类出脑白质、脑灰质和脑脊液。和常规的模糊聚类方法相比,该方法对噪声图像和低对比度图像如医学图像,有更好的鲁棒性。最后用体绘制方法对分类结果进行重建,得到了理想的三维重建结果,证明了该算法的有效性。
3D reconstruction and visualization from medical images has very important application and deep meanings in clinical diagnostic, surgery planning and simulated emulation, plastic and artificial limb surgery, radiotherapy planning, and teaching in anatomy. The technology of 3D reconstruction includes two main methods: surface rendering and volume rendering.
The accurate classification of different materials in the brain images is the basis for reconstruction of three-dimensional brain, but there is no better solution for the classification of the volume data. An effective fuzzy segmentation approach based on multi-scale linking model for brain MRI is proposed in this paper. This approach is based on the fact that the image segmentation results should be optimized simultaneously in different scales. At first, the non-uniformity of gray-scale is corrected after analyzing bias field in brain MRI. Then, a new fuzzy inner-scale constraint based on anisotropic diffusion linking model is introduced, which builds an efficient linkage relationship between the high resolution images and low resolution ones. Meanwhile, this paper develops two new fuzzy distances and then embeds them into the fuzzy clustering algorithm. Moreover, a new multi-resolution framework combining the inner-scale and inter-scale constraints is defined.
The experiment demonstrated that this method can separate the brain MR image accurately and effectively in which a large amount of brain MRI data was used. The presented framework is robust to noise images and low contrast ones, such as medical images. Finally an ideal reconstruction from the classification of brain tissues was obtained, and it is proved to be valid.
引文
[1]石教英,蔡文立.科学计算可视化算法与系统.北京:科学出版社,1996:58-68
[2]ACR-NEMA(American College of Radiology-National Electrical Manufacturers).Digital imaging and communications in medicine(DICOM3.0)International Standard.National Electrical Manufactures Association Press,2003:5-17
[3]Lorensen W.E.,Cline H.E.Marching Cubes:A High-Resolution 3D Surface Construction Algorithm.Computer Graphics,1987,21(3):163-169
[4]M.W.Jones,M,Chen.A New Approach to the Construction of Surfaces from Contour Data.Proceedings of Eurographics'94,1994,13(3):75-84
[5]Shadhidi R.Tombropoulos R.Clinical applications of three-dimensional rendering of medical data sets.Proceeding of the IEEE,1998,86(3):555-568
[6]Donald Hearn M.Pauline Bake.计算机图形学(蔡士杰,吴春镕,等译),北京:电子工业出版社,2002:387-436
[7]R.A.DrebinL,Carpenter,P.Hanrahan.Volume Rendering.Computer Graphics,1988,22(4):65-74
[8]L.J.Rosenblum.Research Issues in Scientific Visualization.IEEE Computer Graphics and Applications,March,1994:61-85
[9]A.Konig,E.Groller.Mastering Transfer Function Specification by using Volume Projection Technology.Vienna University of Technology.Technical Report TR-186-2-00-07,2000
[10]J.Wilhelms,A.V.Gelder.A coherent projection approach to direct volume rendering.Computer Graphics,1991,25(4):275-284
[11]M.Bister,J.Cornelis,A.Rosenfeld.A Critical View of Pyramid Segmentation Algorithms Pattern Recognition Letters,1990,11:605-617
[12]L.M.Lifshitz,S.M.Pizer.A Multiresolution Hierarchical Approach to Image Segmentation Based on Intensity Extrema.IEEE Trans.Pattern Analysis and Machine Intelligence,1990,12(6):529-541
[13]S.G.Mallat.A Theoty for Mutiresolution Signal Decomposition:The Wavelet Representation.IEEE Trans.Pattern Analysis and Machine Intelligence,1989,11(7):674-694
[14]K.L.Vincken.Probabilistic Multiscale Image Segmentation by the Hyperstack. PhD thesis, Utrecht Univ, The Netherlands, 1995
[15] K.L. Vincken, C.N. de Graaf, A.S.E. Koster, M.A. Viergever, F.J.R. Appleman and G.R. Timmens. Multiresolution Segmentation of 3D Images by the Hyperstack. Proc. First Conf. Visualization in Biomedical Computing, 1990:115-122
[16] Koen L.V.. Probabilistic Multiscale Image Segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence, 1997,19(2): 109-120
[17] Mahmound R. R., Pieter M. J., Boudewijn P. E., etal. A Multiresolution Image Segmentation Technique Based on Pyramidal Segmentation and fuzzy Clustering. IEEE Transactions on Image Processing, 2000, 9(7): 1239-1248
[18] Thitimajshima, P. Multiresolution Fuzzy Clustering for SAR image Segmentation. Geoscience and Remote Sensing Symposium. IGARSS '99 Proceedings, 1995, 5: 2507-2509
[19] Sokratis M. Segmentation of Color Images Using Multiscale Clustering and Graph Theoretic Region Synthesis. IEEE Transactions on Systems, Man and Cybernetics-Pare A: Systems and Humans, 2005, 35(2): 224-238
[20] Zhigang W., Dong W., Wei W., et al. Pyramidal Edge Detector Based on Adaptive Weighed Fuzzy Mean Filters. Proceedings of SPIE-The International Society for Optical Engineering, 2001,4550: 46-51
[21] M. Buerki, K. O. Lovblad, H. Oswald, et al. Multiresolution fuzzy clustering of functional MRI data. Neuroradiology, 2003,45: 691-699
[22] S. Sentelle, C. Sentelle and M.A. Sutton. Multiresolution-based segmentation of calcifications for the early detection of breast cancer. Real-Time Imaging 8,2002: 237-252
[23] Iijima T. Basic theory on normalization of figures. Electronics and Communications in Japan, 1962, 54(12): 106-112
[24] Witkin A.P, Badaud J, Baudin M. Uniqueness of the Gaussian Kernel for Scale-Space Filtering. IEEE Transactions on Pattern Analysis and Machine Interlligence, 1986, 8(1): 26-33
[25] Koenderink J J. The Structure of Images. Biological Cybernetics, 1984, 50:363-370
[26] Lindeberg T. Scale-space theory: A basic tool for analysing structures at different scales. Journal Applied Statistics, 1994, 21(2): 223-226
[27] Lindeberg T. Feature Detection With Automatic Scale Selection. International Journal of Computer Vision,1998,30(2):79-116
[28]Lindeberg T,ter Haar Romeny BM.Linear scale space.Netherlands:Kluwer Academic Publishers,1994
[29]Witkin A P.Scale Space Filtering.Proc.Of Int.Jiont Conf.Artificial Intelligence,1983:1019-1020
[30]Perona P,Malik J.Scale-space and Edge Detection Using Anisotropic Diffusion.IEEE Trans.on Pattern Anal.Machine Intell.,1990,12(7):629-639
[31]Alvarez L,et al.Axioms and Fundamental Equations of Image Processing.Arch.Rational Mech.Anal,1993,123:199-257
[32]Guichard F,Morel J M.Image iterative smoothing and RD.E's.Lecture Notes,Beijing,1999
[33]Guillermo S.Geometric Partial Differential Equations and Image Analysis.Cambridge:Cambridge University Press,2001
[34]Park K R,Lee C N.Scale-space using mathematical morphology.IEEE Trans.Pattern Analysis and Machine Intelligence,1996,18(11):1121-1126
[35]Canny J.A computational approach to edge detection.IEEE Trans.Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[36]Lindeberg T,Romeny B.H.Linear Scale-Space.Netherlands:Kluwer Academic Publishers,1994:23-40
[37]Perona R Malik J.Scale-space and edge detection using anisotropic diffusion.IEEE Trans.Pattern Analysis and Machine Intelligence,1990,12(7):1163-1173
[38]张亶,陈刚.基于偏微分方程的图像处理.北京:高等教育出版社,2004:126-130
[39]L.A.Zadeh.Fuzzy sets.Information and Control,1965,8:338-353
[40]M.M.Trivedi and J.C.Bezdek.Low-level segmentation of aerial images with fuzzy clustering.IEEETrans.SMC,1986,16(4):589-598
[41]丁震,胡钟山等.一种基于模糊聚类的图象分割方法.计算机研究与进展,1997,34(7):536-541
[42]王培珍,陈震南.基于二维阂值化与FCM相混合的图像快速分割方法[J].中国图形图像学报,1998,3(19):735-738
[43]A.Rosenfeld.The Fuzzy Geometry of Image Subset,Pattern Recognition Letter 2,1984,311-317
[44]林瑶,田捷,张晓鹏.基于模糊连接度的FCM分割方法在医学图像分析中 的应用.中国体视学与图像分析,2001,6(2):103-108
[45]张敏,于剑.基于划分的模糊聚类算法.软件学报,2004,15(6):858-868
[46]J.Bezdek and J.Harris.Fuzzy partitions and relations:an axiomatic basis for clustering,Fuzzy Sets Syst.,1978,1:111-127
[47]C.Bezdek.Pattern Recognition with Fuzzy Objective Function Algorithm.Plenum,New York,1981
[48]边肇祺,张学工.模式识别(第二版).北京:清华大学出版社,2000:235-237
[49]H.Rusinek,M.E.Noz,G.Q.Maguire,et al.Quantitative and Qualitative Comparison of Volumetric and Surface Rendering Techniques.IEEE Transactions on Nuclear Science,1991,38(2):659-662
[50]L.Westover.Footprint Evaluation for Volume Rendering,Computer Graphics,1990,24(4):367-376
[51]C.Upson,M.Keeler.V-Buffer:Visible volume rendering,Computer Graphics,1988,22(4):59-64
[52]M.Levoy.Display of surfaces from Volume Data.IEEE Computer Graphics and Applications,1988,8(5):29-37
[53]RSabella.A Rendering Algorithm for Visualizing 3D Scalar Field,Computer Graphics,1988,22(4):51-58
[54]J.T.Kajiya,B.P.Von Herzen.Ray tracing volume densities.Computer Graphics,1984,20(4):165-174
[55]Akimoto.T.,Mase.K.and Suenaga.Y.Pixel-selected ray tracing.IEEE Computer Graphics&Applications,1991,11(4):14-22
[56]Glassner.A..Space subdivision for fast ray tracing.IEEE Computer Graphics&Applications,1984,4(10):15-22
[57]Levoy M..Effcient Ray Tracing of Volume Data.ACM Transaction on Graphics,1990,9(3):245-261
[58]Phong B.T.Illumination for Computer Generated Images.Ph.D Dissertation,University of Utah,1993
[59]贾艾晨,魏小鹏,韩国城.数据场体视化方法综述.大连大学学报,2000,21(2):1-6
[60]Westover L.Footprint evaluation for volume rendering.Computer Graphics,1990,24(4):367-376.
[61]孙志刚,张加万等.一种改进的Splatting体绘制方法.天津大学学报,2003, 36(5):626-630
[62]周璐,李晓梅.空间相关脚印方法:一种快速体绘制方法.计算机辅助设计与图形学学报,1998,10(1):80-86
[63]肖娴.基于体绘制的医学可视化应用研究[硕士学位论文]西北工业大学,2004
[64]Philippe Lacroute and Marc Levoy.Fast Volume Rendering Using a Shear-Warp Factorization of the Viewing Transformation,Proc.SIGGRAPH'94,Orlando,Florida,1994,451-458
[65]陈寅秋,董金详.一种新的基于3D纹理映射及Shear-warp变换的快速体绘制方法.计算机工程,1998,24(8):14-15
[66]Kostas A,Tim T A.4D volume rendering with shear warp factorization extensions and quantitative results.In:Information Visualization,Proceedings,Fifth International Conference,New York:IEEE Computer Society Press,2001,435-443
[67]Hanspeter Pfister,Jan Harderbergh.The Volume Pro-Real Time Ray_Casting System.Computer Graphics Proceedings,Annual Conference Series,1999:24-26
[68]H-H Ehricke,G Daiber,W Straber.The Vision Camera:An Interactive Tool for Volume Data Exploration and Navigation.Visualization'93,1993
[69]Jan Koenderink.Design of the hyperstack.Visualization in Biomedical Computing,IEEE Computer Society Press,1990,115-122
[70]E.J Pauwels,L J Van Gool,P.Fiddelaers,T.Moons.An extended class of scale invariant and recursive scale space filters.IEEE Trans.Pattern Analysis and Machine Intelligence,1995,17:691-701
[71]Jungke M,Seelen Wvon,Bielke G,et al.A system for the diagnostic use of tissue characterizing parameters in NMR-tomography.Proc of Information Processing in Medical Imaging,IPMI'87,1987,39:471-481
[72]Collewet G,Davenel A,Toussaint C,et al.Correction of intensity nonuniformity in spin-echo T1-weighted images.Magn Reson Imag,2002,20(4):365-373
[73]Tinchet M,Meyer C R,Gupta R,et al.Polynomial modeling and reduction of RF body coil spatial inhomogeneity in MRI.IEEE Trans.Med Imag,1993,12(2):361-365
[74]Brinkmann B H,Manduea A,Robb R A.Optimized homomorphic unsharp masking for MR grayscale inhomogeneity correction. IEEE Trans. Med Imag,1998,17(2): 161-171
[75] Cohen S M, DuBois R M, Zeineh M M. Rapid and effective correction of RF inhomogeneity for high field magnetic resonance imaging. Hum Brain Mapp,2000,10(4): 204-211
[76] Han C, Hatsukami T S, Yuan C. A multi-scale method for automatic correction of intensity nommiformity in MR images. Journal of Magn Reson Imag, 2001,13(3): 428-436
[77] Vokurka E A, Thacker N A, Jackson A. A fast model independent method for automatic correction of intensity nonuniformity in MRI data. Journal of Magnetic Resonance Imaging, 1999,10(4): 550-562
[78] Van Leemput K, Maes F, Vandermeulen D. Automated model-based bias field correction of MR images of the brain. IEEE Trans Med Imag, 1999, 18(10):885-896
[79] Styner M, Brechbuhler C, Szckely G. Parametric estimate of intensity inhomogeneities applied to MRI. IEEE Trans Med Imag, 2000,19(3): 153-165
[80] Ashburner J, Friston K J. Voxel-bnsed morphometry: the methods.Neuroimage, 2000, 11(6): 805-821
[81] Marroquin J L, Vemuri B C, Botello S. An accurate and efficient Bayesian method for automatic segmentation of brain MRI. IEEE Trans Med Imag, 2002,21(8): 934-945
[82] Liew A W C, Yah H. An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation. IEEE Trans Med Imag, 2003, 22(9): 1063-1075
[83] Mangin J F. Entropy minimization for automatic correction of intensity nonuniformity. Proc IEEE Workshop Mathematical Methods in Biomedical Image Analysis, Hilton Head Island, SC, 2000: 162-169
[84] Salvado O, Hillenbrand C, Zhang S. MR signal inhomogeneity correction for visual and computerized atherosclerosis lesion assessment. Proceeding of 2004 IEEE International Symposium on Biomedical imaging, 2004: 1143-1146
[85] Pham D L, Prince J L. Adaptive fuzzy segmentation of magnetic resonance images. IEEE Trans Med Imag, 1999, 18(9): 737-752
[86] Sled J G, Zijdenbos A P, Evans A C. A nonparametric method for automatic correction of intensity nonuniformity in MRI data [J]. IEEE Trans Med Imag,1998, 17(1): 87-97
[87]W.M.Wells,R.Kikinis,W.E.L Grimson,etal.Adaptive segmentation of MRI data.IEEE Trans on Medical Imaging,1996,15(5):429-442
[88]http://www.bic.mni.mcgill.ca/brainweb
