Paper Info
Title
A novel approach using structure tensor for medical image fusion
Abstract
Medical image fusion has been shown to be effective in supporting clinicians make better clinical diagnoses. Although many algorithms have been proposed for synthesis, they still have certain limitations. Some limitations can be seen as the synthesized image is reduced in contrast or details are not preserved. In this paper, we propose an image fusion algorithm to solve the problems mentioned above. Firstly, an image decomposition method is proposed to decompose the image into two components. This method is based on the Gaussian filter and the Weighted mean curvature filter. Secondly, a fusion method for high-frequency components is based on local energy function using Structure tensor saliency. Finally, we create an adaptive fusion rule using the Marine Predators Algorithm optimization method to fuse low-frequency components. Five latest algorithms and five evaluation indexes have been used to test the proposed algorithm’s effectiveness. The obtained experimental results show that the composite image is significantly improved in quality as well as well preserved the information from the input image.
Year
DOI
Venue
2022
10.1007/s11045-022-00829-9
Multidimensional Systems and Signal Processing
Keywords
DocType
Volume
Marine predators algorithm (MPA), Two-component decomposition (TCD), Maximum local energy (MLE), Structure tensor saliency (STS)
Journal
33
Issue
ISSN
Citations 
3
0923-6082
0
PageRank 
References 
Authors
0.34
44
1
Name
Order
Citations
PageRank
Dinh, Phu-Hung100.34