A Novel Medical Image Registration Method Based on Mutual Information and Genetic Algorithm

2005 ◽  
Author(s):  
Hongying Zhang ◽  
Xiaozhou Zhou ◽  
Jizhou Sun ◽  
Jiawan Zhang
Keyword(s):  
Genetic Algorithm ◽  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Medical Image Registration ◽  
Registration Method

scholarly journals A Medical Image Registration Method Based on Progressive Images

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Qian Zheng ◽  
Qiang Wang ◽  
Xiaojuan Ba ◽  
Shan Liu ◽  
Jiaofen Nan ◽  
...  
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Medical Image Analysis ◽  
Reference Image ◽  
Medical Image Registration ◽  
Registration Method ◽  
Multimodal Registration ◽  
Coarse Registration ◽  
Registration Result

Background. Medical image registration is an essential task for medical image analysis in various applications. In this work, we develop a coarse-to-fine medical image registration method based on progressive images and SURF algorithm (PI-SURF) for higher registration accuracy. Methods. As a first step, the reference image and the floating image are fused to generate multiple progressive images. Thereafter, the floating image and progressive image are registered to get the coarse registration result based on the SURF algorithm. For further improvement, the coarse registration result and the reference image are registered to perform fine image registration. The appropriate progressive image has been investigated by experiments. The mutual information (MI), normal mutual information (NMI), normalized correlation coefficient (NCC), and mean square difference (MSD) similarity metrics are used to demonstrate the potential of the PI-SURF method. Results. For the unimodal and multimodal registration, the PI-SURF method achieves the best results compared with the mutual information method, Demons method, Demons+B-spline method, and SURF method. The MI, NMI, and NCC of PI-SURF are improved by 15.5%, 1.31%, and 7.3%, respectively, while MSD decreased by 13.2% for the multimodal registration compared with the optimal result of the state-of-the-art methods. Conclusions. The extensive experiments show that the proposed PI-SURF method achieves higher quality of registration.

Rigid Medical Image Registration Based on Genetic Algorithms and Mutual Information

2014 ◽  
Vol 665 ◽  
pp. 712-717
Author(s):  
Wei Wei ◽  
Liang Liu ◽  
Zhong Qin Hu ◽  
Yu Jing Zhou
Keyword(s):  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Medical Image Registration ◽  
Rigid Registration ◽  
The Matrix ◽  
Depth Study ◽  
Stability And Accuracy

With the variety of medical imaging equipment’s application in the medical process,medical image registration becomes particularly important in the field of medical image processing,which has important clinical diagnostic and therapeutic value. This article describes the matrix conversion method of the rigid registration model, the basic concepts and principles of the mutual information algorithm ,the basic idea of genetic algorithms and algorithm’s flow , and the application of the improved genetic algorithms in practice. The rigid registration of two CT brain bones images uses mutual information as a similarity measure, genetic algorithm as the search strategy and matlab as programming environment. Using the three-point crossover technique to exchange the three parameters in the rigid transformation repeectively to produce new individuals, the genetic algorithm’s local search ability enhanced and the prematurity phenomenon can be reduced through the depth study of the basic genetic algorithm. The experiments show that the registration has high stability and accuracy.

scholarly journals Analysis and Research of Subclinical Diabetic Peripheral Vascular Lesions Based on Mutual Information-based Medical Image Registration Algorithm and Colour Ultrasound Imaging (Preprint)

2020 ◽  
Author(s):  
Nailong Jia ◽  
Long Fan ◽  
Chuanzi Li ◽  
Zhongshi Nie ◽  
Suihuang Wang ◽  
...  
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Blood Vessels ◽  
Optimization Algorithm ◽  
Peripheral Blood ◽  
Medical Image ◽  
Hybrid Optimization ◽  
Medical Image Registration ◽  
Hybrid Optimization Algorithm ◽  
Subclinical Diabetes

BACKGROUND Background: At present, the incidence of diabetes is on the rise. When doctors diagnose and treat patients' diseases, they often need to image patients to provide complementary information on patient anatomy and functional metabolism. OBJECTIVE Objective: The aim was to understand the morphological features of peripheral blood vessels of diabetes more accurately and explore its Risk factors for the occurrence of lesions for early diagnosis and early prevention. METHODS Methods: The paper selected subclinical diabetes patients admitted to our hospital from October 2013 to October 2018 as a research object. After performing colour Doppler ultrasonography on peripheral blood vessels, images of ultrasound images were taken. Then the paper proposes a multi-mode medical image registration method based on hybrid optimization algorithm for the multi-extreme problem of mutual information function. Mutual information is used as the similarity measure. The hybrid optimization algorithm is used to search for the best registration exchange parameters. The quasi-colour super images are exchanged for registration purposes. RESULTS Results: The experimental results show that the hybrid optimization algorithm can accurately analyse the colour ultrasound image of the peripheral blood vessels of subclinical diabetes, avoiding falling into the local optimal value, and the accuracy of the registration result reaches the sub-pixel level. CONCLUSIONS Conclusion: With the rapid development of imaging technology, the increasing image resolution, and the increasing amount of image data, parallel performance is high. The quasi-method has a very important significance for multi-modal medical image registration. The parameters in this algorithm can be further optimized. CLINICALTRIAL

Sign in / Sign up

Export Citation Format

Share Document