Software design and FPGA implementation of optimized medical image fusion techniques

• Published in: Multimedia tools and applications Vol. 84; no. 32; pp. 40059 - 40089
• Main Authors: Elshazly, E. A., El-Shafai, Walid, El-Hoseny, Heba, El-Rabaie, El-Sayed M, Zahran, O., Abdelwahab, Safey A. S., El-Halawany, M. M., Fikry, R. M., Elaraby, S. M., Faragallah, Osama S., Mohamed, Wael A., Mahmoud, Korany R., Abd El-Samie, Fathi E.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2025; Springer Nature B.V
• Subjects: Algorithms; Comparative studies; Computer Communication Networks; Computer Science; Computer vision; Data Structures and Information Theory; Decomposition; Discrete Wavelet Transform; Efficiency; Equalization; Field programmable gate arrays; Histograms; Image processing; Image quality; Medical diagnosis; Medical electronics; Medical imaging; Multimedia Information Systems; Optimization; Optimization algorithms; Principal components analysis; Product design; Real time; Signal to noise ratio; Software; Special Purpose and Application-Based Systems; Tomography; Track 2: Medical Applications of Multimedia; Wavelet transforms; DWT; FPGA; Local contrast; Histogram matching; MCFO; Medical applications; Image fusion; AWT; PCA
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-16622-0

Nowadays, medical image fusion plays a crucial role in enhancing the diagnosis accuracy and the clinical decision-making process in various healthcare applications. This research work presents a comprehensive study of the design and implementation of optimized medical image fusion techniques using a combination of software and Field-Programmable Gate Array (FPGA) technologies. The proposed medical image fusion strategy is based on the utilization of Discrete Wavelet Transform (DWT) and Modified Central Force Optimization (MCFO). The implementation of the proposed technique as well as the traditional medical image fusion techniques is considered using an appropriate software design and FPGA. The presented techniques aim to overcome the limitations of traditional fusion techniques by integrating advanced image processing algorithms, optimization algorithms, and parallel computing capabilities offered by FPGA platforms. The first step in the proposed framework is to match the histogram of one of the images with that of the other, so that both images will have the same dynamic range. After that, the DWT is used to decompose the images that should be fused together. Based on some constraints, the MCFO optimization algorithm is used to evaluate the optimum level of decomposition and the optimum parameters for the best fusion quality. Finally, to improve the obtained visual quality and reinforce the information in the fusion result, an additional contrast enhancement step using adaptive histogram equalization is applied to the fusion result. Comparative study between the proposed optimized DWT-based fusion framework, the traditional Principal Component Analysis (PCA), Additive Wavelet Transform (AWT), and DWT-based fusion techniques is presented. Various metrics of fusion quality are considered, including average gradient, standard deviation, local contrast, entropy, edge strength, Peak Signal-to-Noise Ratio (PSNR), Q ab/f , and processing time. The proposed optimized DWT-based fusion technique is synthesized using Spartan-3E FPGA Kit and Xilinx ISE Design Suite 14.5, and validated using MATLAB Simulink. Experimental results show that, compared to conventional fusion techniques, the proposed optimized DWT-based medical image fusion framework based on MCFO, histogram matching, and adaptive histogram equalization has high efficiency and achieves high image quality. In addition, the results demonstrate that the optimized medical image fusion techniques implemented on FPGA platforms provide superior fusion quality and computational efficiency compared to traditional software-based techniques. The FPGA-based implementation offers the potential for real-time processing and can be seamlessly integrated into existing medical imaging systems.