基于MRI序列图像的分割方法及三维网格剖分模型的构建
|
摘要
医学图像分割和三维重建是医学图像研究领域的重要内容。本文工作的目的是探讨基于MRI序列图像的分割方法和三维网格模型的重建。分析了当前图像分割以及三维重建的各种方法和研究现状,并在此基础上综合运用阈值分割以及数学形态学算法实现对脑组织磁共振图像序列的分割。首先对图像的预处理分析了邻域平均法、中值滤波方法和维纳滤波方法,具有统计意义的维纳滤波对图像处理结果较好。对阈值选取采用迭代阈值、最大类间方差法、二维最大熵求取阈值三种方法,并对其进行了比较,同时运用数学形态学算法对MRI序列图像进行分割。实验证明该方法简单有效,运算速度快,同时能够满足感兴趣区的分割要求。在图像三维重建方面,着重研究了切片级重建,对于给定的MRI医学序列图像,通过轮廓跟踪提取边界点,再有效结合曲率法和等间距采样法提取特征点,将MRI脑图像的各层轮廓用最短对角线法约束条件来进行三角面片的拼接,实现了MRI序列图像的网格模型的建立。最后改进移动立方体算法的跟踪速度,重建了头和脑的真实感模型。
Medical image segmentation and 3D reconstruction are important in medical image research field. The major goal of this dissertation is to explore an algorithm for medical image segmentation and 3D mesh generation model reconstruction based on MRI images of the brain. We analyzed the backgound and status of above-mentioned algorithms, and based on this, we comprehensively used the threshold segmentation algorithm and mathematical morphology algorithm to realize the segmentation of the brain magnetic resonance image sequence. On the threshold selection ,we compared iterative threshold, the largest category of variance and two-dimensional maximum entropy to seek the best threshold. At the same time we used mathematical morphology algorithm to handle the sequence of the MRI images . Experiment proved that the method is high speed, simple and effective, and it can meet the requirements of separate to the interest areas. It can obtain the satisfactive segmentation result to the humanity vision system characteristic .In the three-dimensional image reconstruction, we focused on a section-level reconstruction. For a given MRI medical image sequences, through the contour track we can obtain the border of the image, and then by combining with sampling method at equal interval and the curvature method, we can obtain the feature nodes. By the shortest diagonal algorithm we can finish the contour tiling of the brain contour sequence of the MRI images, and establish 3D mesh generation model of the brain images.Finally we improved the tracking speed of MC algorithm , and reconstructed realistic models of the head and brain.
Medical image segmentation and 3D reconstruction are important in medical image research field. The major goal of this dissertation is to explore an algorithm for medical image segmentation and 3D mesh generation model reconstruction based on MRI images of the brain. We analyzed the backgound and status of above-mentioned algorithms, and based on this, we comprehensively used the threshold segmentation algorithm and mathematical morphology algorithm to realize the segmentation of the brain magnetic resonance image sequence. On the threshold selection ,we compared iterative threshold, the largest category of variance and two-dimensional maximum entropy to seek the best threshold. At the same time we used mathematical morphology algorithm to handle the sequence of the MRI images . Experiment proved that the method is high speed, simple and effective, and it can meet the requirements of separate to the interest areas. It can obtain the satisfactive segmentation result to the humanity vision system characteristic .In the three-dimensional image reconstruction, we focused on a section-level reconstruction. For a given MRI medical image sequences, through the contour track we can obtain the border of the image, and then by combining with sampling method at equal interval and the curvature method, we can obtain the feature nodes. By the shortest diagonal algorithm we can finish the contour tiling of the brain contour sequence of the MRI images, and establish 3D mesh generation model of the brain images.Finally we improved the tracking speed of MC algorithm , and reconstructed realistic models of the head and brain.
引文
[1]J S Suri,S Singh,L Reden.Computer Vision and Pattern Recognition Techniques for 2D and 3D MR Cerebral Cortical Segmentation(Part I):A State-of-the-Art Review.Pattern Analysis&Application.2002,5:46-76
[2]J S Suri,S Singh,L.Reden.Fusion of Region and Boundary/Surface-Based Computer Vision and Pattern Recognition Techniques for 2D and 3D MR Cerebral Cortical Segmentation(Part II):A State-of-the-Art Review.Pattern Analysis&Application.2002,5:77-98
[3]Kapur J N,Sahoo P K,Wong A K C.A new method for gray-level picture thresholding using the entropy of the histogram.Computer Vision,Graphics and Image Processing,1985,29:273-285
[4]Abutaleb A S.Automatic thresholding of gray-level pictures using two dimension entropy.Computer Vision,Graphics and Image Processing,1989,47:22-32
[5]刘文萍,吴立德.图像分割中阈值选取方法比较研究.模式识别与人工智能,1997,10(3):274-277
[6]吴薇,赵旭,邓秋霞.基于遗传算法的二维最大熵图像分割算法.武警工程学院学报,2003,19(4):25-27
[7]张毓晋.图像分割.北京:清华大学出版社,2000
[8]Zavaljevski,AShawan,AP Gaskil et al.Multi-level Adaptive Segmentation of Multi-parameter MR Brain Image.Comput Med Imag Graph,2000,24(2):87-98
[9]Blanz W E,Gish S L.A Connectionist Classifier Architexture Applied to Image Segmentation.In:Proc of the 10th international Conference on Pattern Recognition,New Jersey,USA.1990:272-277
[10]Babaguchi,N Yamada,K Kise,K Tezuka.T Connectionist Model Binarization.In:Proc of the 10th international Conference on Pattern Recognition,New Jersey,USA.1990:51-56
[11]Zimmermann H J.Fuzzy set theory and its application.Boston,Kluwer,1991:217-240
[12]马艳,张治辉.几种边缘检测算子的比较.工矿自动化,2004,1(2):54-56
[13]Canny J.A Computational Approach to Edge Detection.IEEE Trans on Pattern Analysis and Machine Intelllgence.1986,8(6):679-698
[14]杨东华,李久贤,卞治国.Marr边缘检测算法的研究.中国图象图形学报,2006,11(6):823-826
[15]Melnerney T,Terzopoulos Z.Deformable Models in Medical Image Analysis.A Survey,Medical Image Analysis,1996,1(2):91-108
[16]S C Amartur,D Piraino,Y Takefuji.Optimization Neural Networks for the Segmentation of Magnetic Resonance Images.IEEE Trans.Medical Imaging,1992,11(2):215-220
[17]章鲁,顾顺德,陈瑛等.神经网络技术在磁共振图像分割中的应用.国外医学(生物医学工程分册),2001(5):14-19
[18]J C Ma.Segmentation of multidimension MR images using a fuzzy neural network.proceedings of SPIE2the International Society for optical Engineering,1994,2298:636-643
[19]袁野,仲崇权,秦绪佳.小波变换在三维医学图像分割中的应用.小型微型计算机系统,2003,24(6): 1081-1083
[20]宋晓东,肖李,罗迅.基于数学形态学的SAR图像分割方法.电脑与信息技术,2002(5):46-49
[21]阎平凡,张长水.人工神经网络与模拟进化计算.北京:清华大学出版社,2000
[22]BHANU B,L EE S,MINGJ.Adaptive Image Segmentation using a Genetic Algorithm.IEEE Transactions on Systems,Man,and Cybernetics,1995,25(12):1543-1567
[23]郑宏,潘励.基于遗传算法的图像阈值的自动选取.中国图象图形学报,1999,4(4):327-330
[24]郭阳,张祥德,张继武等.MRI图像信噪比提高技术.生物医学工程学杂志,2002,19(3):493-495
[25]田捷,包尚联,周明全.医学影像处理与分析.北京:电子工业出版社,2003
[26]张太发.基于CT医学图像的三维表面重建算法的研究[硕士学位论文].西安理工大学,2006
[27]李亚东.医学图像分割与三维重建的研究[硕士学位论文].国防科技大学,2003
[28]章毓晋,图像工程(上册):图像处理和分析,北京:清华大学出版社,1999
[29]Jui Cheng Yen,Fu Juay Chang, Shyang Chang. A New Criterion for Automatic Multilevel Thresholding. IEEE Trans On Image Processing,1995,4(3):370-377
[30]Papamarks N.A New Approach for Multilevel Threshold Selection.Graphic Models and Image Processing,1994,56:357-370
[31]Huang L K..Image Thresholding by Minimizing the Measures Fuzziness.Pattern Recognition,1995, 28(1):41-51
[32]郭英凯,基于模糊和遗传算法的阈值分割方法.红外与激光工程,2000,l(5):15-18
[33]A Pikaz,A Averbuch.Digital Image Thresholding Based on Topological Stable State..Pattern Recognition,1996,29(5):829-843
[34]G Corneloup,J Moysan,I E Maynin.BSCAN Image Segmentation by Thresholding Using Cooccurrence Matrix Analysis.Pattern Recognition,1996,29(2):281-296
[35]P Sahoo,C Wilkins,J Yeager.Threshold Selection Using Renyis Entropy.Pattern Recognition,1997, 30(1):71-84
[36]Li L,Gong J, Chen W.Grey-level Image Thresholding Based on Fisher Linear Projection of Two-dimensional Histogram.Pattern Recognition,1997,30(5):743-750
[37]吕炜.医学图像三维重建技术研究[硕士学位论文].南京航空航天大学,2003
[38]秦绪佳.医学图像三维重建及可视化研究[硕士学位论文].大连理工大学,2003
[39]韦巍,王国容,姜立军.医学X射线图像三维重建技术.北京生物医学工程,2004,23(3):236-238
[40]黄绍辉,王博亮,黄晓阳.基于表面与基于体素的医学图像三维重建方法研究.厦门大学学报,2002,41(6):744-746
[41]王青,王融清,鲍虎军等.散乱数据点的增量快速曲面重建算法.软件学报,2000,11(9):1221-1227
[42]何晖光,田捷,赵明昌等.基于分割的三维医学图像表面重建算法.软件学报,2002,13(2):219-225
[43]阎丽被,石教英.一种新的分层模型四面体重构算法.计算机辅助设计与图形学学报,2001,13(7):626-630
[44]孙国辉,包宏,勒风荣.三维物体表面重建方法的分析.计算机应用研究,2004(4):253-255
[45]吕最眠,杨勋年,汪国昭.海量数据的曲面分层重建算法.软件学报,2003,14(8):l448-1455
[46]杨文,柳俊波,廖明生等.下领骨CT序列图像的三维重建.中国图象图形学报,2002,7(9):911-917
[47]吕维雪,段会龙.三维医学图像可视化及应用.杭州:浙江大学出版社,2001
[48]王祖喜,周焰,李德华等.基于局部分块三维物体表面三角划分算法.华中理工大学学报,1999,27(12):4-7
[49]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京:清华大学出版社,2006
[50]Keppel E.Approximating complex surface by triangulation of contour lines.IBM Journal of Research and Development.1975,9:2-11
[51]Fuchs H,Kedem Z.Optimal surface reconstruction from planar contours.Communications of the ACM.1977,10:693-702
[52]Cook.L T,Dwyer S.A three dimensional display system for diagnostic imaging applications.IEEE Computer Graphics Applications.1983,4:13-19
[53]Xu S B,Lu W X..Surface Reconstruction of 3D Objects in Computerized Tomography.Compute Vis. Grap Image Proc,1988,44(3):270-278
[54]王强,马利庄,鲍虎军.基于骨架的断层间复杂轮廓线的三角片曲面重构.计算机学报,2000,23(8):842-846
[55]Boissonnat J D.Shape Reconstruction from Planar Cross Section.Compuer Vision,Graphics and Image Processing,1988,1:1-29
[56]柯映林,李江雄,肖尧先.反求工程CAD建模技术研究.21世纪新产品快速开发技术论文集,2000,5:30-36
[57]Goshtasby A,Turner D A.Matching of tomographic slice for interpolation.IEEE Transaction on Medical Imaging,1992,4:507-516
[58]Dong Y,Hillman G R.Three-dimensional reconstruction of irregular shapes based on a fitted mesh of contours.Image and Vision Computing,2001,9:165-176
[59]李衷怡,赵新方.三角网格剖切算法的研究.计算机与数字工程,2007,35(3):4-33
[60]徐明海、张俨彬、陶文铨.一种改进的Delaunay三角形化剖分方法.石油大学学报(自然科学版), 2001,25(2):100-105
[61]陈越、裴玉茹.基于照片序列快速三维表面网格模型的生成算法,浙江大学学报工学版,2003,37(5):537-542
[62]周宴,肖沙里,姚富光等.面跟踪算法在快速三维重建中的应用研究.微型机与应用,2005,3:46-48
[2]J S Suri,S Singh,L.Reden.Fusion of Region and Boundary/Surface-Based Computer Vision and Pattern Recognition Techniques for 2D and 3D MR Cerebral Cortical Segmentation(Part II):A State-of-the-Art Review.Pattern Analysis&Application.2002,5:77-98
[3]Kapur J N,Sahoo P K,Wong A K C.A new method for gray-level picture thresholding using the entropy of the histogram.Computer Vision,Graphics and Image Processing,1985,29:273-285
[4]Abutaleb A S.Automatic thresholding of gray-level pictures using two dimension entropy.Computer Vision,Graphics and Image Processing,1989,47:22-32
[5]刘文萍,吴立德.图像分割中阈值选取方法比较研究.模式识别与人工智能,1997,10(3):274-277
[6]吴薇,赵旭,邓秋霞.基于遗传算法的二维最大熵图像分割算法.武警工程学院学报,2003,19(4):25-27
[7]张毓晋.图像分割.北京:清华大学出版社,2000
[8]Zavaljevski,AShawan,AP Gaskil et al.Multi-level Adaptive Segmentation of Multi-parameter MR Brain Image.Comput Med Imag Graph,2000,24(2):87-98
[9]Blanz W E,Gish S L.A Connectionist Classifier Architexture Applied to Image Segmentation.In:Proc of the 10th international Conference on Pattern Recognition,New Jersey,USA.1990:272-277
[10]Babaguchi,N Yamada,K Kise,K Tezuka.T Connectionist Model Binarization.In:Proc of the 10th international Conference on Pattern Recognition,New Jersey,USA.1990:51-56
[11]Zimmermann H J.Fuzzy set theory and its application.Boston,Kluwer,1991:217-240
[12]马艳,张治辉.几种边缘检测算子的比较.工矿自动化,2004,1(2):54-56
[13]Canny J.A Computational Approach to Edge Detection.IEEE Trans on Pattern Analysis and Machine Intelllgence.1986,8(6):679-698
[14]杨东华,李久贤,卞治国.Marr边缘检测算法的研究.中国图象图形学报,2006,11(6):823-826
[15]Melnerney T,Terzopoulos Z.Deformable Models in Medical Image Analysis.A Survey,Medical Image Analysis,1996,1(2):91-108
[16]S C Amartur,D Piraino,Y Takefuji.Optimization Neural Networks for the Segmentation of Magnetic Resonance Images.IEEE Trans.Medical Imaging,1992,11(2):215-220
[17]章鲁,顾顺德,陈瑛等.神经网络技术在磁共振图像分割中的应用.国外医学(生物医学工程分册),2001(5):14-19
[18]J C Ma.Segmentation of multidimension MR images using a fuzzy neural network.proceedings of SPIE2the International Society for optical Engineering,1994,2298:636-643
[19]袁野,仲崇权,秦绪佳.小波变换在三维医学图像分割中的应用.小型微型计算机系统,2003,24(6): 1081-1083
[20]宋晓东,肖李,罗迅.基于数学形态学的SAR图像分割方法.电脑与信息技术,2002(5):46-49
[21]阎平凡,张长水.人工神经网络与模拟进化计算.北京:清华大学出版社,2000
[22]BHANU B,L EE S,MINGJ.Adaptive Image Segmentation using a Genetic Algorithm.IEEE Transactions on Systems,Man,and Cybernetics,1995,25(12):1543-1567
[23]郑宏,潘励.基于遗传算法的图像阈值的自动选取.中国图象图形学报,1999,4(4):327-330
[24]郭阳,张祥德,张继武等.MRI图像信噪比提高技术.生物医学工程学杂志,2002,19(3):493-495
[25]田捷,包尚联,周明全.医学影像处理与分析.北京:电子工业出版社,2003
[26]张太发.基于CT医学图像的三维表面重建算法的研究[硕士学位论文].西安理工大学,2006
[27]李亚东.医学图像分割与三维重建的研究[硕士学位论文].国防科技大学,2003
[28]章毓晋,图像工程(上册):图像处理和分析,北京:清华大学出版社,1999
[29]Jui Cheng Yen,Fu Juay Chang, Shyang Chang. A New Criterion for Automatic Multilevel Thresholding. IEEE Trans On Image Processing,1995,4(3):370-377
[30]Papamarks N.A New Approach for Multilevel Threshold Selection.Graphic Models and Image Processing,1994,56:357-370
[31]Huang L K..Image Thresholding by Minimizing the Measures Fuzziness.Pattern Recognition,1995, 28(1):41-51
[32]郭英凯,基于模糊和遗传算法的阈值分割方法.红外与激光工程,2000,l(5):15-18
[33]A Pikaz,A Averbuch.Digital Image Thresholding Based on Topological Stable State..Pattern Recognition,1996,29(5):829-843
[34]G Corneloup,J Moysan,I E Maynin.BSCAN Image Segmentation by Thresholding Using Cooccurrence Matrix Analysis.Pattern Recognition,1996,29(2):281-296
[35]P Sahoo,C Wilkins,J Yeager.Threshold Selection Using Renyis Entropy.Pattern Recognition,1997, 30(1):71-84
[36]Li L,Gong J, Chen W.Grey-level Image Thresholding Based on Fisher Linear Projection of Two-dimensional Histogram.Pattern Recognition,1997,30(5):743-750
[37]吕炜.医学图像三维重建技术研究[硕士学位论文].南京航空航天大学,2003
[38]秦绪佳.医学图像三维重建及可视化研究[硕士学位论文].大连理工大学,2003
[39]韦巍,王国容,姜立军.医学X射线图像三维重建技术.北京生物医学工程,2004,23(3):236-238
[40]黄绍辉,王博亮,黄晓阳.基于表面与基于体素的医学图像三维重建方法研究.厦门大学学报,2002,41(6):744-746
[41]王青,王融清,鲍虎军等.散乱数据点的增量快速曲面重建算法.软件学报,2000,11(9):1221-1227
[42]何晖光,田捷,赵明昌等.基于分割的三维医学图像表面重建算法.软件学报,2002,13(2):219-225
[43]阎丽被,石教英.一种新的分层模型四面体重构算法.计算机辅助设计与图形学学报,2001,13(7):626-630
[44]孙国辉,包宏,勒风荣.三维物体表面重建方法的分析.计算机应用研究,2004(4):253-255
[45]吕最眠,杨勋年,汪国昭.海量数据的曲面分层重建算法.软件学报,2003,14(8):l448-1455
[46]杨文,柳俊波,廖明生等.下领骨CT序列图像的三维重建.中国图象图形学报,2002,7(9):911-917
[47]吕维雪,段会龙.三维医学图像可视化及应用.杭州:浙江大学出版社,2001
[48]王祖喜,周焰,李德华等.基于局部分块三维物体表面三角划分算法.华中理工大学学报,1999,27(12):4-7
[49]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京:清华大学出版社,2006
[50]Keppel E.Approximating complex surface by triangulation of contour lines.IBM Journal of Research and Development.1975,9:2-11
[51]Fuchs H,Kedem Z.Optimal surface reconstruction from planar contours.Communications of the ACM.1977,10:693-702
[52]Cook.L T,Dwyer S.A three dimensional display system for diagnostic imaging applications.IEEE Computer Graphics Applications.1983,4:13-19
[53]Xu S B,Lu W X..Surface Reconstruction of 3D Objects in Computerized Tomography.Compute Vis. Grap Image Proc,1988,44(3):270-278
[54]王强,马利庄,鲍虎军.基于骨架的断层间复杂轮廓线的三角片曲面重构.计算机学报,2000,23(8):842-846
[55]Boissonnat J D.Shape Reconstruction from Planar Cross Section.Compuer Vision,Graphics and Image Processing,1988,1:1-29
[56]柯映林,李江雄,肖尧先.反求工程CAD建模技术研究.21世纪新产品快速开发技术论文集,2000,5:30-36
[57]Goshtasby A,Turner D A.Matching of tomographic slice for interpolation.IEEE Transaction on Medical Imaging,1992,4:507-516
[58]Dong Y,Hillman G R.Three-dimensional reconstruction of irregular shapes based on a fitted mesh of contours.Image and Vision Computing,2001,9:165-176
[59]李衷怡,赵新方.三角网格剖切算法的研究.计算机与数字工程,2007,35(3):4-33
[60]徐明海、张俨彬、陶文铨.一种改进的Delaunay三角形化剖分方法.石油大学学报(自然科学版), 2001,25(2):100-105
[61]陈越、裴玉茹.基于照片序列快速三维表面网格模型的生成算法,浙江大学学报工学版,2003,37(5):537-542
[62]周宴,肖沙里,姚富光等.面跟踪算法在快速三维重建中的应用研究.微型机与应用,2005,3:46-48