Fusion of Medical Images Using Adaptive Pulse Coupled Neural Networks Based on QCSA Optimization

The goal for fusion of image is to incorporate descriptions of the same scene from multiple images. A new image that is more appropriate for human and machine interpretation or more image-processing tasks such as segmentation, extraction of features and object detection is the result of image fusion. In this article, fusion of MRI and CT images are proposed and new model is designed to approach the fusion based on neural networks and Optimization technique which works better and gives good results. In this a paper, an adaptive pulse coupled neural networks (PCNN) is used to determine the right parameters, these parameters are optimized using Quantum Cuckoo Search Algorithm (QCSA). The reliability and accuracy of the image is increased by performing optimization technique. The fitness function of the proposed optimization technique is defined using image entropy (EN), average gradient (AG) and spatial frequency (SF) of image for finding the optimal solution. Various parametric values are being tested to show that the suggested QCSA-PCNN is superior compared with other current technique like QPSO-PCNN. The PSNR obtained using QPSO-PCNN is 40.82, the proposed QCSA-PCNN the Peak signal to noise ratio (PSNR) value is 43.79. The QCSA-PCNN method has good Structural Similarity Index (SSIM) with 0.99 compared to QPSO which has 0.96. The experimental results are conducted using MAT Lab method.