Medical Image Fusion using Feature Extraction cum Feature Optimization based on Swarm Intelligence

  • Mitesh Kumar, Dr. Nikhil Ranjan, Dr. Bharti Chourasia

Abstract

The accurate medical image fusion methods enhance the capacity of critical disease detection. The enhanced ability of diseases detection increases the survival rate of human life. The feature optimization and selection of features of raw medical images are essential phases for image fusion processing. Most authors reported that swarm intelligence-based feature optimization contributes more in MRI and CT based medical image fusion processes. This paper proposed a feature optimization-based medical image fusion method that applies to MRI and CT images. The proposed algorithm uses an ant colony optimization algorithm. Ant colony optimization is a well-known swarm-based algorithm to reduce artefacts and improve the quality of low-intensity MRI images. The proposed algorithm uses a derived support vector machine for the processing of the fusion approach. The derived support vector machine is an extension of the support vector machine algorithm and increases the area of the support vector and enhances the fusion algorithm's capacity. The proposed algorithm is very efficient in terms of image quality index and SSIM concerning PSNR. The proposed algorithm has been simulated in MATLAB software and tested with a reputed dataset such as a medical image dataset. The evaluation process measures standard parameters and compares them with deep learning (DL) and SVM algorithm. Our experimental results show better performance instead of DP and SVM.

Published
2021-12-02
How to Cite
Mitesh Kumar, Dr. Nikhil Ranjan, Dr. Bharti Chourasia. (2021). Medical Image Fusion using Feature Extraction cum Feature Optimization based on Swarm Intelligence. Design Engineering, 1961 - 1969. Retrieved from http://www.thedesignengineering.com/index.php/DE/article/view/7142
Section
Articles