基于特征点驱动的CT图像配准与拼接方法研究
|
摘要
医学图像配准是当前医学图像研究领域的研究热点和研究难点,在临床诊断和治疗方面具有重要的意义。医学图像配准是指对一幅医学图像寻找一种(或一系列)的空间的变换,使它与另一幅医学图像上的对应点在空间坐标中达到一致。很多学者已经提出了很多医学图像配准算法,它们大体上可分为基于灰度驱动的图像配准算法、基于模型驱动的图像配准算法和综合算法。
在医学成像过程中,往往有着被检查部位远远大于图像探测器面积的矛盾,需要将该部位分为几次拍摄,再按照一定的规则拼接起来,这就是医学图像拼接。医学图像拼接在医学领域有着广泛的应用前景。可以解决医学图像获取过程中由于视野的限制而无法得到完整的图像的问题,为诊断提供更好的依据。典型的医学图像拼接算法主要有基于变换域的方法,基于图像灰度的方法和基于特征的方法等。
随着医学影像技术、计算机科学技术的不断发展,医学图像的计算机智能化诊断是医学图像处理与分析研究的最重要的目标之一。要实现计算机智能化诊断或计算机辅助诊断,信息的可对比性和完整性是至关重要的,而其中涉及到的技术就是图像的配准技术和图像的拼接技术。医学图像配准和医学图像拼接是医学图像研究的热点和难点。
本文针对构建基于高分辨率CT图像的脑部疾病辅助诊断系统的需求,研究了基于特征点驱动的图像配准技术,并对图像拼接技术进行了初步探讨。在研究和分析特征点自动提取方法的基础上,着重研究了尺度不变特征变换(SIFT)算法,找出两幅CT图像的匹配的特征点,实现了特征点的自动匹配,为基于特征点驱动图像配准和图像拼接做好铺垫。进一步对基于模型驱动的配准算法中的基于特征点驱动的图像配准方法进行研究,采用薄板样条插值方法,实现了两幅脑CT图像的正确配准,并提出了采用区域特征向量来去除不正确匹配点的方法。论文还着重研究了基于特征的医学图像拼接方法,给出了对两幅医学图像实现正确拼接的详细算法和实施步骤,并提出了采用统计斜率最多法和随机抽样一致性法去除不正确匹配点的方案,保证了所拼接出来的图像的质量。
Medical Image Registration is one of hot research topics in the field of medical image. It has great significance in the clinical diagnosis and treatment. Medical image registration is for a medical image to find a (or a series) space transformation so that the corresponding points in this medical image will reach consistent with another medical image in the same place on both images. Many algorithms of medical image registration have been proposed. They are generally classified based on gray-driven method, modal-driven method and the hybrid algorithms.
In the imaging process,the inspected area is often far greater than the image detector, the film must be divided into several parts, and then spliced together in accordance with certain rules, that is, medical image mosaic. Medical image mosaic has wide range of applications in the field of medical image. It can be solved the problem of unable to get the whole image because of the limited vision,and provide a better basis for the diagnosis. According to their methods, the medical image mosaic can be divided into the following categories: transform domain-based approach, the method based on image intensity and feature-based methods.
As the medical imaging technology, computer science and technology continues to develop, the computer intelligent medical image diagnosis is one of the most important goals of medical image processing and analysis. To realize intelligent diagnosis or computer aided diagnosis, information comparability and information integrity are essential, of which the technology involved is image registration and image mosaic technology. Medical image registration and medical image mosaic are two hot and difficult research areas in the medical image field.
Aim at the requirement of constructing a Computer Aided Diagnosis system for brain diseases based on High Resolution CT images, the research of this thesis is focused on the feature point-driven image registration and image mosaic technology.
Based on the deep discussion and analysis for the methods of feature point automatic extraction, this paper put emphasis on the Scale Invariant Feature Transform (SIFT) algorithm. The matched points of two images were found, and paved the way for feature-driven image registration and image mosaic. These matched points were found by SIFT algorithm, achieving automatic matching feature points. For the image registration, we focused the research on the method of feature point-driven image registration. Based on the thin-plate spline interpolation algorithm, we realized the registration of two CT brain images, and also designed a globe feature vector based method to remove the error matched points of images that required for registration. Finally, primary research on medical images mosaic was conducted by using the method of feature point-driven image mosaic, and complete algorithm and programming procedures were proposed for two CT chest images mosaic. In accordance with the characteristics of medical images, the error matched points of images that required for mosaic were removed by random sample consensus (RANSAC) algorithm and statistics slope algorithm.
在医学成像过程中,往往有着被检查部位远远大于图像探测器面积的矛盾,需要将该部位分为几次拍摄,再按照一定的规则拼接起来,这就是医学图像拼接。医学图像拼接在医学领域有着广泛的应用前景。可以解决医学图像获取过程中由于视野的限制而无法得到完整的图像的问题,为诊断提供更好的依据。典型的医学图像拼接算法主要有基于变换域的方法,基于图像灰度的方法和基于特征的方法等。
随着医学影像技术、计算机科学技术的不断发展,医学图像的计算机智能化诊断是医学图像处理与分析研究的最重要的目标之一。要实现计算机智能化诊断或计算机辅助诊断,信息的可对比性和完整性是至关重要的,而其中涉及到的技术就是图像的配准技术和图像的拼接技术。医学图像配准和医学图像拼接是医学图像研究的热点和难点。
本文针对构建基于高分辨率CT图像的脑部疾病辅助诊断系统的需求,研究了基于特征点驱动的图像配准技术,并对图像拼接技术进行了初步探讨。在研究和分析特征点自动提取方法的基础上,着重研究了尺度不变特征变换(SIFT)算法,找出两幅CT图像的匹配的特征点,实现了特征点的自动匹配,为基于特征点驱动图像配准和图像拼接做好铺垫。进一步对基于模型驱动的配准算法中的基于特征点驱动的图像配准方法进行研究,采用薄板样条插值方法,实现了两幅脑CT图像的正确配准,并提出了采用区域特征向量来去除不正确匹配点的方法。论文还着重研究了基于特征的医学图像拼接方法,给出了对两幅医学图像实现正确拼接的详细算法和实施步骤,并提出了采用统计斜率最多法和随机抽样一致性法去除不正确匹配点的方案,保证了所拼接出来的图像的质量。
Medical Image Registration is one of hot research topics in the field of medical image. It has great significance in the clinical diagnosis and treatment. Medical image registration is for a medical image to find a (or a series) space transformation so that the corresponding points in this medical image will reach consistent with another medical image in the same place on both images. Many algorithms of medical image registration have been proposed. They are generally classified based on gray-driven method, modal-driven method and the hybrid algorithms.
In the imaging process,the inspected area is often far greater than the image detector, the film must be divided into several parts, and then spliced together in accordance with certain rules, that is, medical image mosaic. Medical image mosaic has wide range of applications in the field of medical image. It can be solved the problem of unable to get the whole image because of the limited vision,and provide a better basis for the diagnosis. According to their methods, the medical image mosaic can be divided into the following categories: transform domain-based approach, the method based on image intensity and feature-based methods.
As the medical imaging technology, computer science and technology continues to develop, the computer intelligent medical image diagnosis is one of the most important goals of medical image processing and analysis. To realize intelligent diagnosis or computer aided diagnosis, information comparability and information integrity are essential, of which the technology involved is image registration and image mosaic technology. Medical image registration and medical image mosaic are two hot and difficult research areas in the medical image field.
Aim at the requirement of constructing a Computer Aided Diagnosis system for brain diseases based on High Resolution CT images, the research of this thesis is focused on the feature point-driven image registration and image mosaic technology.
Based on the deep discussion and analysis for the methods of feature point automatic extraction, this paper put emphasis on the Scale Invariant Feature Transform (SIFT) algorithm. The matched points of two images were found, and paved the way for feature-driven image registration and image mosaic. These matched points were found by SIFT algorithm, achieving automatic matching feature points. For the image registration, we focused the research on the method of feature point-driven image registration. Based on the thin-plate spline interpolation algorithm, we realized the registration of two CT brain images, and also designed a globe feature vector based method to remove the error matched points of images that required for registration. Finally, primary research on medical images mosaic was conducted by using the method of feature point-driven image mosaic, and complete algorithm and programming procedures were proposed for two CT chest images mosaic. In accordance with the characteristics of medical images, the error matched points of images that required for mosaic were removed by random sample consensus (RANSAC) algorithm and statistics slope algorithm.
引文
李传富.2005.颅脑CT病变的计算机自动化检出方法研究[D].中国科技大学博士学位论文.
陈白帆,蔡自兴. 2005.基于尺度空间理论的HARRIS角点检测[J].中南大学学报(自然科学版), vol.36(05) 751-754.
冯海波. 2007.虚拟全景空间生成技术研究与实现.电子科技大学硕士学位论.
贾云德. 2000.机器视觉[M].北京:科学出版社. 97-100.
李晓娟. 2007.图像拼接技术研究.西安电子科技大学硕士学位论文.
李艳丽. 2007.全景图生成技术研究,山东大学硕士学位论文.
宋小丽. 2007.宽基线立体图像的区域匹配及应用.中科院自动化所硕士学位论文.
孙涛. 2009.基于特征向量的二维颅脑CT图像配准与分割.中国科学技术大学硕士学位论文.
徐挺. 2009.基于Demons算法的医学图像非刚性配准研究. .中国科学技术大学硕士学位论文
章毓晋. 2005.图像工程(中):图像分析(第2版).北京:清华大学出版社.
Amit Y, Grenander U, Piccioni M. 1991. Structural image restoration through deformable templates[J].J. Amer. Stat. Assoc. vol.86(414):376-386
Arsigny V, Commowick O, Pennec X, et al. 2006. A Log-Euclidean framework for statistics on diffeomorphisms[C]. MICCAI 2006, LNCS 4190: 924-931.
A.Savi, M.C.Gilardi, G.Rizzo, M.Pepi, C.Landoni, et al. 1995. Spatial Registration of Echocardiographic and Positron Emission Tomgraphic Heart Studies. Eupropean Journal of Nuclear Medicine. vol.22(3):243-247.
Bajcsy R, Kovacic S.1989 Multiresolution elastic matching[J]. Computer Vision, Graphics and Image Processing, vol.46:1-21.
Bookstein.F.L, 1978. The Measurement of Biological Shape and Shape Change.Lecture Notes in Biomathematics. New York: Springer-Verlag. vol.24.
Bookstein FL. 1989. Principal warps:Thin-plate splines and the decomposition of deformation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. vol. 11(6): 567-585.
Bookstein FL, Green WDK. 1993. A feature space for edges in images with landmarks[J]. J.Math. Imaging and Vision, 3:312-323.
Bookstein FL. 1999. Linear methods for nonlinear maps: Procrustes fits, thin-platesplines, and the biometric analysis of shape variability[M]. In Toga Aw(ed), Brain Warping: 157-181.
Bro-Nielsen M, Gramkow C. 1996. Fast fluid registration of medical images. In Proc. Visualization in Biomedical Computing (VBC'96), Hamburg, Germany, September, Springer Lecture Notes in Computer Science, vol.1131:265-276.
Brown M, Lowe D. 2007. Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision. vol.74(1):59-73.
Burt P, Adelson E. 1983. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics, vol.2(4):217-236
Canny. 1986. A computational approach to edge detection [J]. IEEE Trans Pattern Analysis and Machine Intelligence. vol.8(6):679-698.
Chen S. 1995. Quick Time VR An image-based approach to virtual environment navigation. In SIGGRAPH 95, vol.29:29-38.
Choi Y, Lee S. 2000. Injectivity conditions of 2D and 3D uniform cubic B-spline functions[j]. Graphical Models, 62(6):411-427.
Christensen GE, Rabbit RD, Miller MI. 1993. A deformable neuroanatomy textbook based on viscous fluid mechanics[C]. 27th Ann. Conf. on Inf. Sciences and Systems. 211-216.
Declerck J, Subsol G, Thirion JP. 1995. Automatic Retrieval of Anatomical Structures in 3D Medical Images[J]. INRIA Technical Report 2485. 151-162
Feldmar J, Declerck J, Malandain G, Ayache N. 1997. Extension of the ICP Algorithm to Nonrigid Intensity-Based Registration of 3D Volumes[J]. Computer Vision and Image Understanding. vol.66(2): 193-206.
Fernando R. 2004. GPU Gems[M]. Boston: Addison Wesley.
Harris C and Stephens M. A combined corner and edge detector. In Fourth Alvey Vision Conference. 147-151.
Joshi.S.C, Miller.M.I, Christensen.G.E, Banerjee.A, Coogan.T.A, and Grenander.U. 1995. Hierarchical brain mapping via a generalized Dirichlet solution for mapping brain manifolds. Proc. SPIE, Melter.R.A, Wu.A.Y, Bookstein.F.L, and Green.W.D, Eds. vol.2573, Vision Geometry IV, pp. 278-289.
Koenderink,J.J. 1984. The structure of images. Biological Cybernetics, 50:363-396
Lindeberg,T.1994. Scale-space theory: A basic tool for analyzing structures at different scales. Journal of Applied Statistics,21(2):224-270.
Lindeberg T, Garding . 1997. Shape-adapted smoothing in estimation of 3D shape cuesfrom affine deformations of local 2D brightness structure[J]. Image and Vision Computing. vol. 15(6):415-434
Lindeberg T. 1998. Feature detection with automatic scale selection. International Journal of Computer Vision. vol30(2):79-116.
Lisa Gottesfeld Brown. 1992. A survey of image registration techniques. ACM Computing Surveys(CSUR). vol.10: 325-376.
Lowe, D.G. 1991. Fitting parameterized three-dimensional models to images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(5):441-450.
Lowe, D.G. 1999. Object recognition from local scale-invariant features. In International Conference on Computer Vision, Corfu, Greece. 1150-1157.
Lowe, D.G. 2001. Local feature view clustering for 3D object recognition. IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii. 682-688.
Lowe.D.G. 2004. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal on Computer Vision 60(2): 91-110.
Marr D, Hildreth E. 1980. Theory of edged etection. Proceedings of the Royal Society of London. Series B, Biological Sciences, vol. 207(1167): 187-217
Martin Urschler, Joachim Bauer, Hendrik Ditt, and Horst Bischof. 2006. SIFT and Shape Context for Feature-Based Nonlinear Registration of Thoracic CT Images[J]. Computer Vision Approaches to Medical Image Analysis 4241: 73-84.
Mikolajczyk K, Schmid C. 2005. A performance evalution of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27(10): 1615-1630.
Moravec.H.P. 1979. Visual Mapping by a Robot Rover[J]. International Joint Conference on Artificial Intelligence, 598-600.
Richard Szeliski. 1996. Matching 3-D anatomical surfaces with non-rigid deformations using octree-splines[J]. International Journal of Computer Vision. vol.18(2):171-186.
Richard Hartley and Andrew Zisserman. 2006. Multiple View Geometry in Computer Vision Scale-Invariant Features, ISCV.
Smith.S.M, Brady,J.M. 1997. SUSAN-A new approach to low level image processing[J]. International Journal of Computer Vision, 23(1):45-78
Thirion J-P. 1996. Non-rigid matching using demons[J]. In Computer Vision and Pattern Recognition, Proceedings CVPR '96, 1996 IEEE Computer Society Conference,vol 245-251.
Torr P.H, Zisserman A. 2000. MLESAC: a new robust estimator with application toestimating image geometry[J]. Computer Vision and Image Understanding, vol.78(3):138-156.
Yan Ke, Rahul Sukthankar. 2004. PCA-SIFT: A More Distinctive Representation for Local Image Descriptors[J]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 506-513.
Zheng Ming-ling. 2003. Liu Heng-zhu. Study on High Performance Algorithm of Image Registration for Remode Sensing[D]. Changsha: School of Computer, National University of Defense Technology.
陈白帆,蔡自兴. 2005.基于尺度空间理论的HARRIS角点检测[J].中南大学学报(自然科学版), vol.36(05) 751-754.
冯海波. 2007.虚拟全景空间生成技术研究与实现.电子科技大学硕士学位论.
贾云德. 2000.机器视觉[M].北京:科学出版社. 97-100.
李晓娟. 2007.图像拼接技术研究.西安电子科技大学硕士学位论文.
李艳丽. 2007.全景图生成技术研究,山东大学硕士学位论文.
宋小丽. 2007.宽基线立体图像的区域匹配及应用.中科院自动化所硕士学位论文.
孙涛. 2009.基于特征向量的二维颅脑CT图像配准与分割.中国科学技术大学硕士学位论文.
徐挺. 2009.基于Demons算法的医学图像非刚性配准研究. .中国科学技术大学硕士学位论文
章毓晋. 2005.图像工程(中):图像分析(第2版).北京:清华大学出版社.
Amit Y, Grenander U, Piccioni M. 1991. Structural image restoration through deformable templates[J].J. Amer. Stat. Assoc. vol.86(414):376-386
Arsigny V, Commowick O, Pennec X, et al. 2006. A Log-Euclidean framework for statistics on diffeomorphisms[C]. MICCAI 2006, LNCS 4190: 924-931.
A.Savi, M.C.Gilardi, G.Rizzo, M.Pepi, C.Landoni, et al. 1995. Spatial Registration of Echocardiographic and Positron Emission Tomgraphic Heart Studies. Eupropean Journal of Nuclear Medicine. vol.22(3):243-247.
Bajcsy R, Kovacic S.1989 Multiresolution elastic matching[J]. Computer Vision, Graphics and Image Processing, vol.46:1-21.
Bookstein.F.L, 1978. The Measurement of Biological Shape and Shape Change.Lecture Notes in Biomathematics. New York: Springer-Verlag. vol.24.
Bookstein FL. 1989. Principal warps:Thin-plate splines and the decomposition of deformation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. vol. 11(6): 567-585.
Bookstein FL, Green WDK. 1993. A feature space for edges in images with landmarks[J]. J.Math. Imaging and Vision, 3:312-323.
Bookstein FL. 1999. Linear methods for nonlinear maps: Procrustes fits, thin-platesplines, and the biometric analysis of shape variability[M]. In Toga Aw(ed), Brain Warping: 157-181.
Bro-Nielsen M, Gramkow C. 1996. Fast fluid registration of medical images. In Proc. Visualization in Biomedical Computing (VBC'96), Hamburg, Germany, September, Springer Lecture Notes in Computer Science, vol.1131:265-276.
Brown M, Lowe D. 2007. Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision. vol.74(1):59-73.
Burt P, Adelson E. 1983. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics, vol.2(4):217-236
Canny. 1986. A computational approach to edge detection [J]. IEEE Trans Pattern Analysis and Machine Intelligence. vol.8(6):679-698.
Chen S. 1995. Quick Time VR An image-based approach to virtual environment navigation. In SIGGRAPH 95, vol.29:29-38.
Choi Y, Lee S. 2000. Injectivity conditions of 2D and 3D uniform cubic B-spline functions[j]. Graphical Models, 62(6):411-427.
Christensen GE, Rabbit RD, Miller MI. 1993. A deformable neuroanatomy textbook based on viscous fluid mechanics[C]. 27th Ann. Conf. on Inf. Sciences and Systems. 211-216.
Declerck J, Subsol G, Thirion JP. 1995. Automatic Retrieval of Anatomical Structures in 3D Medical Images[J]. INRIA Technical Report 2485. 151-162
Feldmar J, Declerck J, Malandain G, Ayache N. 1997. Extension of the ICP Algorithm to Nonrigid Intensity-Based Registration of 3D Volumes[J]. Computer Vision and Image Understanding. vol.66(2): 193-206.
Fernando R. 2004. GPU Gems[M]. Boston: Addison Wesley.
Harris C and Stephens M. A combined corner and edge detector. In Fourth Alvey Vision Conference. 147-151.
Joshi.S.C, Miller.M.I, Christensen.G.E, Banerjee.A, Coogan.T.A, and Grenander.U. 1995. Hierarchical brain mapping via a generalized Dirichlet solution for mapping brain manifolds. Proc. SPIE, Melter.R.A, Wu.A.Y, Bookstein.F.L, and Green.W.D, Eds. vol.2573, Vision Geometry IV, pp. 278-289.
Koenderink,J.J. 1984. The structure of images. Biological Cybernetics, 50:363-396
Lindeberg,T.1994. Scale-space theory: A basic tool for analyzing structures at different scales. Journal of Applied Statistics,21(2):224-270.
Lindeberg T, Garding . 1997. Shape-adapted smoothing in estimation of 3D shape cuesfrom affine deformations of local 2D brightness structure[J]. Image and Vision Computing. vol. 15(6):415-434
Lindeberg T. 1998. Feature detection with automatic scale selection. International Journal of Computer Vision. vol30(2):79-116.
Lisa Gottesfeld Brown. 1992. A survey of image registration techniques. ACM Computing Surveys(CSUR). vol.10: 325-376.
Lowe, D.G. 1991. Fitting parameterized three-dimensional models to images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(5):441-450.
Lowe, D.G. 1999. Object recognition from local scale-invariant features. In International Conference on Computer Vision, Corfu, Greece. 1150-1157.
Lowe, D.G. 2001. Local feature view clustering for 3D object recognition. IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii. 682-688.
Lowe.D.G. 2004. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal on Computer Vision 60(2): 91-110.
Marr D, Hildreth E. 1980. Theory of edged etection. Proceedings of the Royal Society of London. Series B, Biological Sciences, vol. 207(1167): 187-217
Martin Urschler, Joachim Bauer, Hendrik Ditt, and Horst Bischof. 2006. SIFT and Shape Context for Feature-Based Nonlinear Registration of Thoracic CT Images[J]. Computer Vision Approaches to Medical Image Analysis 4241: 73-84.
Mikolajczyk K, Schmid C. 2005. A performance evalution of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27(10): 1615-1630.
Moravec.H.P. 1979. Visual Mapping by a Robot Rover[J]. International Joint Conference on Artificial Intelligence, 598-600.
Richard Szeliski. 1996. Matching 3-D anatomical surfaces with non-rigid deformations using octree-splines[J]. International Journal of Computer Vision. vol.18(2):171-186.
Richard Hartley and Andrew Zisserman. 2006. Multiple View Geometry in Computer Vision Scale-Invariant Features, ISCV.
Smith.S.M, Brady,J.M. 1997. SUSAN-A new approach to low level image processing[J]. International Journal of Computer Vision, 23(1):45-78
Thirion J-P. 1996. Non-rigid matching using demons[J]. In Computer Vision and Pattern Recognition, Proceedings CVPR '96, 1996 IEEE Computer Society Conference,vol 245-251.
Torr P.H, Zisserman A. 2000. MLESAC: a new robust estimator with application toestimating image geometry[J]. Computer Vision and Image Understanding, vol.78(3):138-156.
Yan Ke, Rahul Sukthankar. 2004. PCA-SIFT: A More Distinctive Representation for Local Image Descriptors[J]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 506-513.
Zheng Ming-ling. 2003. Liu Heng-zhu. Study on High Performance Algorithm of Image Registration for Remode Sensing[D]. Changsha: School of Computer, National University of Defense Technology.