Research of CT / MRI Tumor Image Registration Based on Least Square Support Vector Machines

Authors:
Zeqing Yang;Libing Liu;Weiling Liu;Weidong Yang
Affiliations:
School of Mechanical Engineering, Hebei University of Technology, Tianjin, China 300130;School of Mechanical Engineering, Hebei University of Technology, Tianjin, China 300130;School of Mechanical Engineering, Hebei University of Technology, Tianjin, China 300130;School of Mechanical Engineering, Hebei University of Technology, Tianjin, China 300130
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Year:
2008

Citing 4
Cited 0

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Efficient computations for large least square support vector machine classifiers

Pattern Recognition Letters
Fast parametric elastic image registration

IEEE Transactions on Image Processing
Support vector machine with adaptive parameters in financial time series forecasting

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In view of the characteristics of the local nonlinear distortion about medical CT and MRI tumor image registration, the method of Least Square Support Vector Machines (LS-SVM) was used to register the images. The verge point of tumor was marked using vector machine weights in this algorithm, and the eigenvalues of tumor images were obtained. The difference of corresponding feature points between CT and MRI tumor image was eliminated adopting the least square algorithm, which not only can effectively remove geometric deformation of the images, but also can be adaptive correct the errors caused by the positioning of feature points. Finally, we had experimented on the Matlab platform, the results show that the algorithm has higher registration accuracy and can meet medical tumor registration requirements. It also play guidance role in image fusion and tumor targeted therapy, which has important application in clinical medicine.