A Novel Approach Using Structure Tensor for Medical Image Fusion

Multidimensional Systems and Signal Processing（2022）

Cited 16|Views2

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.

Translated text

Key words

Marine predators algorithm (MPA),Two-component decomposition (TCD),Maximum local energy (MLE),Structure tensor saliency (STS)

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper