[1]董志芳,李松毅,於文雪,等.一种新的基于投影矩的三维图像配准方法[J].东南大学学报(自然科学版),2003,33(2):219-221.[doi:10.3969/j.issn.1001-0505.2003.02.026]
 Dong Zhifang,Li Songyi,Yu Wenxue,et al.New way of registration using the projection moment in 3-D image data[J].Journal of Southeast University (Natural Science Edition),2003,33(2):219-221.[doi:10.3969/j.issn.1001-0505.2003.02.026]
点击复制

一种新的基于投影矩的三维图像配准方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
33
期数:
2003年第2期
页码:
219-221
栏目:
计算机科学与工程
出版日期:
2003-03-20

文章信息/Info

Title:
New way of registration using the projection moment in 3-D image data
作者:
董志芳1李松毅2 於文雪2 舒华忠2
1 东南大学电子工程系,南京 210096; 2 东南大学生物科学与医学工程系,南京 210096
Author(s):
Dong Zhifang1 Li Songyi2 Yu Wenxue2 Shu Huazhong2
1 Department of Electronic Engineering, Southeast University,Nanjing 210096, China
2 Department of Biological Science and Medical Engineering, Southeast University,Nanjing 210096, China
关键词:
投影矩 几何矩 配准 多模态图像 数据融合
Keywords:
projection moment orthogonal moments registration multi-modality image data fusion
分类号:
TP391.41
DOI:
10.3969/j.issn.1001-0505.2003.02.026
摘要:
提出一种投影矩的概念,并将其用于三维医学图像的配准.与传统的几何矩相比,投影矩不仅可以完备地描述图像的特征,而且计算量较小,因而可以将其用于三维图像的实时配准.选取待配准的2幅三维图像若干阶投影矩差的平方和为目标函数,采用Powell方法求取最优解,得到配准结果.将方法应用于一些模拟和实际数据,获得了较高精度的实验结果; 并且缩短了整个计算过程的时间.这表明投影矩在多模态医学图像的配准和融合等方面具有潜在的实用价值.
Abstract:
A new concept named projection moments, and its application to 3-D medical image registration is introduced. Compared with the method based on geometric moments, the new method needs much less computation time, so it can be used in the clinical 3-D image matching problems. A least square objective function was used to measure the difference of projection moments between the test and reference images, and the Powell method was applied to solve the optimization problem. The application of the method to some simulated and real data proved that accurate results could be obtained within a reasonable time, therefore, the new method has the potential of practical use in the medical image registration.

参考文献/References:

[1] Hu M K.Visual pattern recognition by moment invariants[J].IRE Trans Inf Theory,1962,8(1):179-187.
[2] Wahl R L,Quint L E,Cieslak R D,et al.Anatometabolic tumor imaging:fusion of FDG PET with CT or MRI to localize foci of increased activity[J]. J Nucl Med,1993,34(7):1190-1197.
[3] Wahl R L,Quint L E,Greenough R L,et al.Staging of mediastinal non-small cell lung cancer with FDG PET,CT,and fusion images:preliminary prospective evaluation[J]. Radiology,1994,191(2):371-377.
[4] Levin D N,Pelizzari C A,Chen G T Y,et al.Retrospective geometric correlation of MR,CT,and PET images[J].Radiology, 1988,169:817-823.
[5] Alpert N M,Bradshaw J F,Kenedy D,et al.The principal axes transformation:a method for image registration[J].JNM,1990,31:1717-1722.
[6] Bookstein F L.Principal warps:thin-plate splines and the decomposition of deformations[J]. IEEE Trans Pattern Anal Mach Intell,1989,11:567-585.
[7] Shu H Z,Luo L M,Yu W X,et al.A new fast method for computing Legendre moments[J].Pattern Recognition,2000,33:341-348.

备注/Memo

备注/Memo:
作者简介: 董志芳(1973—),女,硕士生; 舒华忠(联系人),男,教授,博士生导师,shu.list@seu.edu.cn.
更新日期/Last Update: 2003-03-20