基于特征点和互信息的医学图像配准研究
|
摘要
医学图像配准是医学图像处理领域的研究热点问题之一,是图像信息融合的前提和基础,医学图像的自动配准技术和理论研究对基础医学研究、临床诊断、治疗、和疗效评价等具有重要意义。
本文针对一组医学图像数据对实现自动配准的关键技术及算法进行了理论和实验研究。主要工作有:
针对目前医学图像的成像特点,对医学图像预处理方法的研究。对目前流行的灰度变换、直方图处理、滤波和色彩增强方法进行了归纳整理和实验研究,为后续的图像配准研究奠定基础。
对基于harris特征点的医学图像配准和基于互信息的医学图像配准进行重点研究。基于特征点的医学图像配准方法主要从特征点提取算子入手,从准确性和稳定性等方面进行比较研究,通过理论和实验研究对算法进行改进。文中特征点匹配以特征点邻域灰度相关性作为相似性测度,搜索空间用仿射变换空间,并用马氏距离的仿射变换不变性校正特征点的匹配,最后再对参数优化。
基于互信息的配准方法具有不需要做特征提取等预处理,需要的人机交互少,易于实现自动配准的优点。本文在对相关概念和基本原理研究的基础上,重点对插值和优化方法进行理论和实验研究,包括对双线性插值和PV(partial volume)插值以及Powell优化算法和PSO(Particle Swarm Optimization)算法进行理论和实验对比研究。
最后,是对配准结果的评估。在对评估方法和评价指标分析整理基础上,从精度,速率,抗噪性等方面对前面的两类配准方法进行了性能比较分析。结果表明:文中两种方法都具有配准精度高、速度快、鲁棒性强等特点,但是配准效果因应用对象的不同而不同。
Medical image registration is a hot topic in image processing, and is the basic issue of medieal image fusion.The research of automatic regisrraction technical and theoretical of medical images is important in the basic medical research, clinical diagnosis, treatment, and efficacy evaluation.
In this paper, theoretical and experimental research of key technology and algorithm theory of automatic registration has been made which based on a set of medical image data.Main tasks are as follows:
For the characteristics of current medical images, this thesis study the medical image preprocessing in detail.We summarize the methods of image preprocessing which were most commonly used, and verified the effect with medical images.It lay a solid foundation for the image registration.
This study focused on medical image registration based on harris feature points, and medical image registration which based on mutual information.The method based on feature points had been study begin with the operator which commonly used in feature point extraction, and then comparative them from accuracy and stability.Then we made some improvements on algorithms through theoretical and experimental research.We selection the gray of neighborhood between feature point as the measure of correlation similarity, and using the affine transformation as the search space.The affine transformation invariance of Mahalanobis distance is used to calibrate the matching of feature point. Finally, it is the parameter refinement.
The method which based on mutual information advantages in no need to feature extraction, requires less man–machine interaction, and is easy to realize automatic registration. In the beginning, we mainly study the relative concepts and principles. On this basis, we discuss the interpolation and optimization in detail. Bilinear interpolation and Parital volume interpolation, and Powell optimization and PSO algorithm has been madeed a detailed comparison.
In the last, it is the evaluation of the results. Through the analysis of assessment menthods and indicators of evaluation, we analyse the previous two methods from the precision, speed, and noise immunity. The results show that: both methods have characteristics of high registration accuracy, speed and robustness. However, the results will be varying in the different application object.
本文针对一组医学图像数据对实现自动配准的关键技术及算法进行了理论和实验研究。主要工作有:
针对目前医学图像的成像特点,对医学图像预处理方法的研究。对目前流行的灰度变换、直方图处理、滤波和色彩增强方法进行了归纳整理和实验研究,为后续的图像配准研究奠定基础。
对基于harris特征点的医学图像配准和基于互信息的医学图像配准进行重点研究。基于特征点的医学图像配准方法主要从特征点提取算子入手,从准确性和稳定性等方面进行比较研究,通过理论和实验研究对算法进行改进。文中特征点匹配以特征点邻域灰度相关性作为相似性测度,搜索空间用仿射变换空间,并用马氏距离的仿射变换不变性校正特征点的匹配,最后再对参数优化。
基于互信息的配准方法具有不需要做特征提取等预处理,需要的人机交互少,易于实现自动配准的优点。本文在对相关概念和基本原理研究的基础上,重点对插值和优化方法进行理论和实验研究,包括对双线性插值和PV(partial volume)插值以及Powell优化算法和PSO(Particle Swarm Optimization)算法进行理论和实验对比研究。
最后,是对配准结果的评估。在对评估方法和评价指标分析整理基础上,从精度,速率,抗噪性等方面对前面的两类配准方法进行了性能比较分析。结果表明:文中两种方法都具有配准精度高、速度快、鲁棒性强等特点,但是配准效果因应用对象的不同而不同。
Medical image registration is a hot topic in image processing, and is the basic issue of medieal image fusion.The research of automatic regisrraction technical and theoretical of medical images is important in the basic medical research, clinical diagnosis, treatment, and efficacy evaluation.
In this paper, theoretical and experimental research of key technology and algorithm theory of automatic registration has been made which based on a set of medical image data.Main tasks are as follows:
For the characteristics of current medical images, this thesis study the medical image preprocessing in detail.We summarize the methods of image preprocessing which were most commonly used, and verified the effect with medical images.It lay a solid foundation for the image registration.
This study focused on medical image registration based on harris feature points, and medical image registration which based on mutual information.The method based on feature points had been study begin with the operator which commonly used in feature point extraction, and then comparative them from accuracy and stability.Then we made some improvements on algorithms through theoretical and experimental research.We selection the gray of neighborhood between feature point as the measure of correlation similarity, and using the affine transformation as the search space.The affine transformation invariance of Mahalanobis distance is used to calibrate the matching of feature point. Finally, it is the parameter refinement.
The method which based on mutual information advantages in no need to feature extraction, requires less man–machine interaction, and is easy to realize automatic registration. In the beginning, we mainly study the relative concepts and principles. On this basis, we discuss the interpolation and optimization in detail. Bilinear interpolation and Parital volume interpolation, and Powell optimization and PSO algorithm has been madeed a detailed comparison.
In the last, it is the evaluation of the results. Through the analysis of assessment menthods and indicators of evaluation, we analyse the previous two methods from the precision, speed, and noise immunity. The results show that: both methods have characteristics of high registration accuracy, speed and robustness. However, the results will be varying in the different application object.
引文
1栾红霞.基于定量定性互信息的医学图像配准. [上海交通大学博士论文]. 2007:1-7
2罗述谦,周果宏.医学图像处理与分析.北京:科学出版社, 2003:15-35
3邸海涛.关于刚体图像与非刚体图像的配准.[西安电子科技大学硕士论文].2004:9-15
4郑亚琴,田心.医学图像配准技术研究进展.国际生物医学工程杂志, 2006,29(2):88-89
5 Barbara Zitova, Jan Flusser. Image Registration Methods: a Survey. Image and Vision Computing, 2003,11(21):977-1000
6刘松涛,杨绍清.图像配准技术性能评估及实现概况.电光与控制, 2007,3(14):73-77
7 Cai-fang Wang Ming Jiang. Review of Image Registration Methods for Medical Images. CT Theory and Applications, 2006,2(15):74-80
8 Samia Bouchafa, Bertrand Zavidovique.Efficient Cumulative Matching for Image Registration. Image and Vision Computing,2006,1(24):70-79
9 Ho Lee, Jeongjin Lee. Robust and Fast Shell Registration in PET and MR/CT Brain Images. Computers in Biology and Medicine, 2009,11(39):961-977
10 Tinku. Acharya, Ajoy K. Ray.数字图像处理:原理与应用.田浩等.北京:清华大学出版社, 2007:125-170
11刘哲星.医学图像回溯性配准研究. [第一军医大学博士论文] 2002:1-18
12 Josien P. W. Pluim, J. B. Antoine Maintz. Mutual-Information-Based Registration of Medical Images: A Survey. IEEE Transactions on Medical Imaging, 2003,8(22):986-999
13陈武凡,秦安.医学图像分析的现状与展望.中国生物医学工程学报, 2008,2(27):175-179
14 Markus Mǔller, Wolfgang Krǔger. Robust Image Registration for Fusion. Information Fusion, 2007,4(8):347-353
15 Xuan Nie, Rongchun. Zhao. A New Image Registration Method for Grey Images, Journal of Electronics, 2004,5(21):426-428
16张春美,龚志辉,黄艳.几种特征点提取算法的性能评估及改进.测绘科学技术学报, 2008,3(25):231-234
17 Yang-Ming Zhu, Steven M. Cochoff. An Object-oriented Framework for Medical ImageRegistration, Fusion, and Visualization. Computer Methods and Programs in Biomedicine, 2006,3(82):258-267
18 Wolfgang Wein, Shelby Brunke. Automatic CT-ultrasound Registration for Diagnostic Imaging and Image-guided Intervention. Medical Image Analysis, 2008,5(12):577-585
19 Zhiyong Gao, Bin Gu, Jiarui Lin. Monomodal Image Registration Using Mutual Information Based Methods. Image and Vision Computing, 2008,2(26):164-173
20 Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins.数字图像处理:MATLAB版/(美).阮秋琦等.北京:电子工业出版社,2005:30-52
21隋美蓉,胡俊峰,时梅林,等. MATLAB在医学图像配准中的应用.生物医学工程与临床, 2009,6(13):562-565
22赵明昌,田捷,薛健.医学影像处理与分析开发包MITK的设计与实现.软件学报, 2005,4(16):486-489
23王家文,李仰军. MATLAB 7.0图形图像处理.北京:国防工业出版社, 2006:25-57
24 John Wiley, Inc. 2-D and 3-D Image Registration. United States: Clearance Center, Inc., 222 Rosewood Drive, Danvers, 2005:7-60
25张小洪,李博,杨丹.一种新的Harris多尺度角点检测.电子与信息学报,2007,29(7): 1735-1738
26张春森.基于点特征匹配的SUSAN,Harris算子比较.西安科技大学学报, 2007,4(27):608-611
27王崴,唐一平.一种改进的Harris角点提取算法.光学精密工程. 2008,16(10):1997- 2000
28周亚军,陶声祥.一种基于Harris角点特征的稳像算法.激光与红外, 2009,5(39):555-557
29 Le Yu, Dengrong Zhang. A Fast and Fully Automatic Registration Approach Based on Point Features for Multi-source Remote-sensing Images. Computers & Geosciences, 2008,7(34):838-848
30 Ulas Bagci, Jayaram K. The Role of Intensity Standardization in Medical Image Registration. Pattern Recognition Letters, 2010,4(31):315-520
31 Ho Lee, Jeongjin Lee.Robust. Feature-based Registration Using a Gaussian Weighted Distance Map and Brain Feature Points for Brain PET/CT Image. Computers in Biology and Medicine, 2008,9(38):945-961
32 Lee Cooper, Olcay Sertel, Jun Kong. Feature-based Registration of HistopathologyImages With Different Stains: An Application for Computerized Follicular Lymphoma Prognosis. Computer Methods and Programs in Biomedicine, 2009,3(96):182-192
33 Takeshi Masuda. Log-polar Height Maps for Multiple Range Image Registration. Computer Vision and Image Understanding,2009,11(113):1158-1168
34 Wenjun Li, Irina Kezele, D. Louis Collins. Voxel-based Modeling and Quantification of The Proximal Femur Using Inter-subject Registration of Quantitative CT Images.Bone, 2008,5(41):888-895
35王玉珠,杨丹,张小洪.基于B样条的改进型Harris角点检测算法.计算机应用研究, 2007,2:192-193
36朱秋煜,王朔中.图像特征检测和马氏距离中的数据融合与置信度.电子与信息学报, 2008,3(30):534-538
37 Alexander Wong, Paul Fieguth. Fast Phase-based Registration of Multimodal Image Data. Signal Processing, 2009,5(89):724-735
38陈贤巧.基于特征的图像配准算法研究. [中国科学技术大学硕士论文]. 2009.50-57
39 Matthew Mellor, Michael Brady. Phase Mutual Information as a Similarity Measure for Registration. Medical Image Analysis, 2005,4(9):330-340
40王小根,须文波.基于最大互信息和量子粒子群优化算法的医学图像配准研究.计算机应用研究, 2008,12(25):3685-3688
41火元莲,齐永锋,宋海声.基于轮廓特征点最大互信息的多模态医学图像配准.激光与红外, 2008,55(6): 96-98
42李晓光,谭建豪.邻域互信息在磁共振颅脑图像配准的应用.计算机工程与应用, 2009,45(10):154-156
43 E.B. Gulsoy, J.P.Simmons, M. De Graef. Application of Joint Histogram and Mutual Information to Registration and Data Fusion Problems in Serial Sectioning Microstructure Studies.Scripta Materialia, 2009,6(60):381-384
44赵秀影,苏耘.一种基于小波与双三次插值的CCD图像超分辨方法.计算机应用研究, 2009,6(26):2366-2367
45何元烈,田联房,陈萍.基于三次样条层间插值的多模态医学图像配准.生物医学工程学杂志, 2007,24(6):1241-1245
46彭景林,章兢,李树涛.基于改进PV插值和混合优化算法的医学图像配准.电子学报, 2006,5(34):962-965
47 Zhen-ming Yuan, Fei Wu. Multi-sensor Image Registration Using Multi- ResolutionShape Analysis. Journal of Zhe jiang University SCIENCE A, 2006,7(4):549-555
48 Eric R. Smith, Bradford J. King. Registration of Combined Range–intensity Scans: Initialization Through Verification. Computer Vision and Image Understanding, 2008,2(110):226-244
49 Yong Sun Kim, Jae Hak Lee, Jong Beom Ra. Multi-sensor Image Registration Based on Intensity and Edge Orientation Information. Pattern Recognition, 2008,11(41): 3356-3365
50 Yuru Wang, Jianhua Huang. An Efficient Image-registration Method Based on Proba- biliy Density and Global Parallax. Int. J. Electron. Commun. (AEU), 2009,5(11):1-3
51 Ravi Bansal, Lawrence H. Staib. Calculation of The Confidence Intervals for Transformation Parameters in The Registration of Medical images. Medical Image Analysis, 2009,2(13):215-230
52 Souha Aouadi, Laurent Sarry. Accurate and Precise 2D–3D Registration Based on X-ray Intensity. Computer Vision and Image Understanding, 2008,1(110):134-151
53 Harold S. Stone, Bo Tao. Analysis of Image Registration Noise Due to Rotationally Dependent Aliasing.Visual Communication and Image Representation, 2003, 2(14):114-135
54 A. Isamber, G. Bonniaud, G. Malandain. A Phantom Study of The Accuracy of CT, MR and PET Image Registrations with a Block Matching-based Algorithm. Cancer/Radiothérapie, 2008,8(12):800-808
55 Joaquim Salvi, Carles Matabosch. A Review of Recent Range Image Registration Method with Accuracy Evaluation. Image and Vision Computing, 2007,5(25): 578-596
56 Cynthia Jongen, Josien P. W. Pluim, Paul J. Construction and Evaluation of an Average CT Brain Image for Inter-subject Registration. Computers in Biology and Medicine, 2004,8(34):647-662
57 Stefania Pallotta, Marta Bucciolini, Serenella Russo. Accuracy Evaluation of Image Registration and Segmentation Tools Used in Conformal Treatment Planning of Prostate Cancer. Computerized Medical Imaging and Graphics,2006,1(30):1-7
58韦春荣,周永健.利用统计特性进行医学图像配准效果定量评.广西物理, 2007,2(28):18-22
59廖秀秀,梁礼健.医学图像配准技术研究.计算机应用技术, 2009,16:107-109
2罗述谦,周果宏.医学图像处理与分析.北京:科学出版社, 2003:15-35
3邸海涛.关于刚体图像与非刚体图像的配准.[西安电子科技大学硕士论文].2004:9-15
4郑亚琴,田心.医学图像配准技术研究进展.国际生物医学工程杂志, 2006,29(2):88-89
5 Barbara Zitova, Jan Flusser. Image Registration Methods: a Survey. Image and Vision Computing, 2003,11(21):977-1000
6刘松涛,杨绍清.图像配准技术性能评估及实现概况.电光与控制, 2007,3(14):73-77
7 Cai-fang Wang Ming Jiang. Review of Image Registration Methods for Medical Images. CT Theory and Applications, 2006,2(15):74-80
8 Samia Bouchafa, Bertrand Zavidovique.Efficient Cumulative Matching for Image Registration. Image and Vision Computing,2006,1(24):70-79
9 Ho Lee, Jeongjin Lee. Robust and Fast Shell Registration in PET and MR/CT Brain Images. Computers in Biology and Medicine, 2009,11(39):961-977
10 Tinku. Acharya, Ajoy K. Ray.数字图像处理:原理与应用.田浩等.北京:清华大学出版社, 2007:125-170
11刘哲星.医学图像回溯性配准研究. [第一军医大学博士论文] 2002:1-18
12 Josien P. W. Pluim, J. B. Antoine Maintz. Mutual-Information-Based Registration of Medical Images: A Survey. IEEE Transactions on Medical Imaging, 2003,8(22):986-999
13陈武凡,秦安.医学图像分析的现状与展望.中国生物医学工程学报, 2008,2(27):175-179
14 Markus Mǔller, Wolfgang Krǔger. Robust Image Registration for Fusion. Information Fusion, 2007,4(8):347-353
15 Xuan Nie, Rongchun. Zhao. A New Image Registration Method for Grey Images, Journal of Electronics, 2004,5(21):426-428
16张春美,龚志辉,黄艳.几种特征点提取算法的性能评估及改进.测绘科学技术学报, 2008,3(25):231-234
17 Yang-Ming Zhu, Steven M. Cochoff. An Object-oriented Framework for Medical ImageRegistration, Fusion, and Visualization. Computer Methods and Programs in Biomedicine, 2006,3(82):258-267
18 Wolfgang Wein, Shelby Brunke. Automatic CT-ultrasound Registration for Diagnostic Imaging and Image-guided Intervention. Medical Image Analysis, 2008,5(12):577-585
19 Zhiyong Gao, Bin Gu, Jiarui Lin. Monomodal Image Registration Using Mutual Information Based Methods. Image and Vision Computing, 2008,2(26):164-173
20 Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins.数字图像处理:MATLAB版/(美).阮秋琦等.北京:电子工业出版社,2005:30-52
21隋美蓉,胡俊峰,时梅林,等. MATLAB在医学图像配准中的应用.生物医学工程与临床, 2009,6(13):562-565
22赵明昌,田捷,薛健.医学影像处理与分析开发包MITK的设计与实现.软件学报, 2005,4(16):486-489
23王家文,李仰军. MATLAB 7.0图形图像处理.北京:国防工业出版社, 2006:25-57
24 John Wiley, Inc. 2-D and 3-D Image Registration. United States: Clearance Center, Inc., 222 Rosewood Drive, Danvers, 2005:7-60
25张小洪,李博,杨丹.一种新的Harris多尺度角点检测.电子与信息学报,2007,29(7): 1735-1738
26张春森.基于点特征匹配的SUSAN,Harris算子比较.西安科技大学学报, 2007,4(27):608-611
27王崴,唐一平.一种改进的Harris角点提取算法.光学精密工程. 2008,16(10):1997- 2000
28周亚军,陶声祥.一种基于Harris角点特征的稳像算法.激光与红外, 2009,5(39):555-557
29 Le Yu, Dengrong Zhang. A Fast and Fully Automatic Registration Approach Based on Point Features for Multi-source Remote-sensing Images. Computers & Geosciences, 2008,7(34):838-848
30 Ulas Bagci, Jayaram K. The Role of Intensity Standardization in Medical Image Registration. Pattern Recognition Letters, 2010,4(31):315-520
31 Ho Lee, Jeongjin Lee.Robust. Feature-based Registration Using a Gaussian Weighted Distance Map and Brain Feature Points for Brain PET/CT Image. Computers in Biology and Medicine, 2008,9(38):945-961
32 Lee Cooper, Olcay Sertel, Jun Kong. Feature-based Registration of HistopathologyImages With Different Stains: An Application for Computerized Follicular Lymphoma Prognosis. Computer Methods and Programs in Biomedicine, 2009,3(96):182-192
33 Takeshi Masuda. Log-polar Height Maps for Multiple Range Image Registration. Computer Vision and Image Understanding,2009,11(113):1158-1168
34 Wenjun Li, Irina Kezele, D. Louis Collins. Voxel-based Modeling and Quantification of The Proximal Femur Using Inter-subject Registration of Quantitative CT Images.Bone, 2008,5(41):888-895
35王玉珠,杨丹,张小洪.基于B样条的改进型Harris角点检测算法.计算机应用研究, 2007,2:192-193
36朱秋煜,王朔中.图像特征检测和马氏距离中的数据融合与置信度.电子与信息学报, 2008,3(30):534-538
37 Alexander Wong, Paul Fieguth. Fast Phase-based Registration of Multimodal Image Data. Signal Processing, 2009,5(89):724-735
38陈贤巧.基于特征的图像配准算法研究. [中国科学技术大学硕士论文]. 2009.50-57
39 Matthew Mellor, Michael Brady. Phase Mutual Information as a Similarity Measure for Registration. Medical Image Analysis, 2005,4(9):330-340
40王小根,须文波.基于最大互信息和量子粒子群优化算法的医学图像配准研究.计算机应用研究, 2008,12(25):3685-3688
41火元莲,齐永锋,宋海声.基于轮廓特征点最大互信息的多模态医学图像配准.激光与红外, 2008,55(6): 96-98
42李晓光,谭建豪.邻域互信息在磁共振颅脑图像配准的应用.计算机工程与应用, 2009,45(10):154-156
43 E.B. Gulsoy, J.P.Simmons, M. De Graef. Application of Joint Histogram and Mutual Information to Registration and Data Fusion Problems in Serial Sectioning Microstructure Studies.Scripta Materialia, 2009,6(60):381-384
44赵秀影,苏耘.一种基于小波与双三次插值的CCD图像超分辨方法.计算机应用研究, 2009,6(26):2366-2367
45何元烈,田联房,陈萍.基于三次样条层间插值的多模态医学图像配准.生物医学工程学杂志, 2007,24(6):1241-1245
46彭景林,章兢,李树涛.基于改进PV插值和混合优化算法的医学图像配准.电子学报, 2006,5(34):962-965
47 Zhen-ming Yuan, Fei Wu. Multi-sensor Image Registration Using Multi- ResolutionShape Analysis. Journal of Zhe jiang University SCIENCE A, 2006,7(4):549-555
48 Eric R. Smith, Bradford J. King. Registration of Combined Range–intensity Scans: Initialization Through Verification. Computer Vision and Image Understanding, 2008,2(110):226-244
49 Yong Sun Kim, Jae Hak Lee, Jong Beom Ra. Multi-sensor Image Registration Based on Intensity and Edge Orientation Information. Pattern Recognition, 2008,11(41): 3356-3365
50 Yuru Wang, Jianhua Huang. An Efficient Image-registration Method Based on Proba- biliy Density and Global Parallax. Int. J. Electron. Commun. (AEU), 2009,5(11):1-3
51 Ravi Bansal, Lawrence H. Staib. Calculation of The Confidence Intervals for Transformation Parameters in The Registration of Medical images. Medical Image Analysis, 2009,2(13):215-230
52 Souha Aouadi, Laurent Sarry. Accurate and Precise 2D–3D Registration Based on X-ray Intensity. Computer Vision and Image Understanding, 2008,1(110):134-151
53 Harold S. Stone, Bo Tao. Analysis of Image Registration Noise Due to Rotationally Dependent Aliasing.Visual Communication and Image Representation, 2003, 2(14):114-135
54 A. Isamber, G. Bonniaud, G. Malandain. A Phantom Study of The Accuracy of CT, MR and PET Image Registrations with a Block Matching-based Algorithm. Cancer/Radiothérapie, 2008,8(12):800-808
55 Joaquim Salvi, Carles Matabosch. A Review of Recent Range Image Registration Method with Accuracy Evaluation. Image and Vision Computing, 2007,5(25): 578-596
56 Cynthia Jongen, Josien P. W. Pluim, Paul J. Construction and Evaluation of an Average CT Brain Image for Inter-subject Registration. Computers in Biology and Medicine, 2004,8(34):647-662
57 Stefania Pallotta, Marta Bucciolini, Serenella Russo. Accuracy Evaluation of Image Registration and Segmentation Tools Used in Conformal Treatment Planning of Prostate Cancer. Computerized Medical Imaging and Graphics,2006,1(30):1-7
58韦春荣,周永健.利用统计特性进行医学图像配准效果定量评.广西物理, 2007,2(28):18-22
59廖秀秀,梁礼健.医学图像配准技术研究.计算机应用技术, 2009,16:107-109