Mutual information-based CT-MR brain image registration using generalized partial volume joint histogram estimation

2003 ◽  
Vol 22 (9) ◽  
pp. 1111-1119 ◽  
Author(s):  
Hua-mei Chen ◽  
P.K. Varshney
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Brain Image ◽  
Partial Volume ◽  
Joint Histogram ◽  
Histogram Estimation ◽  
Mr Brain

Voxel similarity measures for 3-D serial MR brain image registration

2000 ◽  
Vol 19 (2) ◽  
pp. 94-102 ◽  
Author(s):  
M. Holden ◽  
D.L.G. Hill ◽  
E.R.E. Denton ◽  
J.M. Jarosz ◽  
T.C.S. Cox ◽  
...  
Keyword(s):  
Image Registration ◽  
Similarity Measures ◽  
Brain Image ◽  
Mr Brain

scholarly journals Robust anatomical landmark detection with application to MR brain image registration

2015 ◽  
Vol 46 ◽  
pp. 277-290 ◽  
Author(s):  
Dong Han ◽  
Yaozong Gao ◽  
Guorong Wu ◽  
Pew-Thian Yap ◽  
Dinggang Shen
Keyword(s):  
Image Registration ◽  
Anatomical Landmark ◽  
Landmark Detection ◽  
Brain Image ◽  
Mr Brain

scholarly journals Multimodal Medical Image Registration Based on an Information-Theory Measure with Histogram Estimation of Continuous Image Representation

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Bicao Li ◽  
Guanyu Yang ◽  
Zhoufeng Liu ◽  
Jean Louis Coatrieux ◽  
Huazhong Shu
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Medical Images ◽  
Image Representation ◽  
Superior Performance ◽  
Geometric Transformation ◽  
Medical Image Registration ◽  
Continuous Image ◽  
Joint Histogram ◽  
Histogram Estimation

This work presents a novel method for multimodal medical registration based on histogram estimation of continuous image representation. The proposed method, regarded as “fast continuous histogram estimation,” employs continuous image representation to estimate the joint histogram of two images to be registered. The Jensen–Arimoto (JA) divergence is a similarity measure to measure the statistical dependence between medical images from different modalities. The estimated joint histogram is exploited to calculate the JA divergence in multimodal medical image registration. In addition, to reduce the grid effect caused by the grid-aligning transformations between two images and improve the implementation speed of the registration method, random samples instead of all pixels are extracted from the images to be registered. The goal of the registration is to optimize the JA divergence, which would be maximal when two misregistered images are perfectly aligned using the downhill simplex method, and thus to get the optimal geometric transformation. Experiments are conducted on an affine registration of 2D and 3D medical images. Results demonstrate the superior performance of the proposed method compared to standard histogram, Parzen window estimations, particle filter, and histogram estimation based on continuous image representation without random sampling.

Effect of Measure and Interpolation Methods for Intensity-Based Medical Image Registration

2013 ◽  
Vol 647 ◽  
pp. 612-617
Author(s):  
Guo Dong Zhang ◽  
Xiao Hu Xue ◽  
Wei Guo
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Medical Image Registration ◽  
Registration Accuracy ◽  
Partial Volume ◽  
Interpolation Methods ◽  
Registration Algorithm ◽  
Image Registration Algorithm ◽  
Local Extreme

The local extreme is main reason to hamper the optimization process and influence the registration accuracy in medical image registration algorithm. In general, the accuracy of image registration based on mutual information is afforded by interpolation methods. In this paper, we analyze the effect of the measure and interpolation methods for medical image registration and present a medical image registration algorithm using mutual strictly concave function measure and partial volume (PV) interpolation methods. The experiment results show that for images with low local correlation the algorithm has the ability to reduce the local extreme, the registration accuracy is improved, and the algorithm expended less time than mutual information based registration method with partial volume (PV) or generalized partial volume estimation (GPVE).

Sign in / Sign up

Export Citation Format

Share Document