DEPSO With DTCWT Algorithm for Multimodal Medical Image Fusion

In this paper, the authors propose an algorithm of hybrid particle swarm with differential evolution (DE) operator, termed DEPSO, with the help of a multi-resolution transform named dual tree complex wavelet transform (DTCWT) to solve the problem of multimodal medical image fusion. This hybridizing approach aims to combine algorithms in a judicious manner, where the resulting algorithm will contain the positive features of these different algorithms. This new algorithm decomposes the source images into high-frequency and low-frequency coefficients by the DTCWT, then adopts the absolute maximum method to fuse high-frequency coefficients; the low-frequency coefficients are fused by a weighted average method while the weights are estimated and enhanced by an optimization method to gain optimal results. The authors demonstrate by the experiments that this algorithm, besides its simplicity, provides a robust and efficient way to fuse multimodal medical images compared to existing wavelet transform-based image fusion algorithms.

• multimodal medical image fusion
• dual-tree complex wavelet transform
• hybrid particle swarm optimization
• differential evolution
• wavelet coefficient fusion
• weighted average fusion
• metaheuristic optimization

• Advanced Image Fusion Techniques
• Metaheuristic Optimization Algorithms Research
• Advanced Data Compression Techniques
• multimodal medical image fusion
• dual-tree complex wavelet transform
• hybrid particle swarm optimization
• differential evolution
• wavelet coefficient fusion
• weighted average fusion
• metaheuristic optimization
• Media Technology
• Artificial Intelligence
• Computer Vision and Pattern Recognition
• Engineering
• Computer Science