2D/3D rigid registration by integrating intensity distance

被引：5

作者：

Wang, Lei ^{[1
,2
,3
]}

Gao, Xin ^{[1
]}

Cui, Xue-Li ^{[1
,2
,3
]}

Liang, Zhi-Yuan ^{[4
]}

机构：

[1] Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou

[2] Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun

[3] University of Chinese Academy of Sciences, Beijing

[4] College of Biomechanical Engineering, Capital Medical University, Beijing

来源：

Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2014年 / 22卷 / 10期

关键词：

2D/3D image registration; Image-guided surgery; Intensity distance; Similarity measure;

D O I：

10.3788/OPE.20142210.2815

中图分类号：

学科分类号：

摘要：

For image-guided surgery, a novel 2D/3D image rigid registration method is proposed by integrating intensity distances of images. The method uses a new intensity distance information to restrict the most commonly used similarity measures(Mutual Information (MI), Cross Correlation (CC) and Pattern Intensity (PI)) and to construct a kind of novel similarity measures(distance MI, distance CC and distance PI). These novel measures are evaluated by using the porcine skull phantom datasets from the Medical University of Vienna. The experiments show that novel measures are better than traditional measures, i.e., the mean and standard deviation of mean Target Registration Errors (mTRE) by novel measures are respectively lower by at least 28.15% and 61.17% than those by traditional measures. When setting mTRE less than 2 mm as successful registration, the success rate with novel measures increases by at least 25.56% on average. Meanwhile, the average iteration times of novel measures also reduce by 35.59% than those of traditional measures. This results suggest that the novel registration method using novel measures has better performance of registration than intensity-based methods using traditional measures in terms of the accuracy and robustness for 2D/3D rigid registration. ©, 2014, Guangxue Jingmi Gongcheng/Optics and Precision Engineering. All right reserved.

引用

页码：2815 / 2824

页数：9

共 27 条

[1]

Markelj P., Tomazevic D., Likar B., Et al., A review of 3D/2D registration methods for image-guided interventions , Medical Image Analysis, 16, pp. 642-661, (2012)

[2]

Birkfellner W., Stock M., Figl M., Et al., Stochastic rank correlation: A robust merit function for 2D/3D registration of image data obtained at different energies , Medical Physics, 36, pp. 3420-3432, (2009)

[3]

Hipwell J.H., Penney G.P., Mclaughlin R.A., Et al., Intensity-based 2D/3D registration of cerebral angiograms , IEEE Transactions on Medical Imaging, 22, pp. 1417-1426, (2003)

[4]

Penney G.P., Weese J., Little J.A., Et al., A comparison of similarity measures for use in 2D/3D medical image registration , IEEE Transactions on Medical Imaging, 17, pp. 586-595, (1998)

[5]

Yu X.C., Lv Z.H., Hu D., Review of remote sensing image registration techniques , Opt. Precision Eng, 21, 11, pp. 2960-2972, (2013)

[6]

Ji H., SIFT features matching algorithm with global information , Opt. Precision Eng, 17, 2, pp. 439-444, (2009)

[7]

Markelj P., Tomazevic D., Pernus F., Et al., Robust gradient-based 3-D/2-D registration of CT and MR to X-ray images , IEEE Transactions on Medical Imaging, 27, pp. 1704-1714, (2008)

[8]

Myronenko A., Song X., Point set registration: Coherent point drift , IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, pp. 2262-2275, (2010)

[9]

Fitzgibbon A.W., Robust registration of 2D and 3D point sets , Image and Vision Computing, 21, pp. 1145-1153, (2003)

[10]

Tomazevic D., Likar B., Slivnik T., Et al., 3-D/2-D registration of CT and MR to X-ray images , IEEE Transactions on Medical Imaging, 22, pp. 1407-1416, (2003)

← 1 2 3 →