Hybrid pixel based method for multimodal image fusion based on Integration of Pulse Coupled Neural Network (PCNN) and Genetic Algorithm (GA) using Empirical Mode Decomposition (EMD)

Medical diagnosis using images is critical for defining the patient’s condition and assisting the decision process for treatment by the physician. Certain infections and conditions like Colorectal Cancer, lung lesion, brain tumor, Metastasis can be ambiguous and the diagnosis cannot be accurately determined using single image. Image fusion is phenomena that helps to alleviate this underlying problem. Image fusion is the process of integrating complementary information from two or more distinct images into a single image without loss of information. It has the capability to process the information from each pixel in the input image and endure the information from source images thereby improving the readability of information, thus aiding the physicians to diagnose the health conditions in a much efficient manner. In this paper, we propose a novel image fusion strategy that is the amalgamation of Pulse Coupled Neural Network (PCNN) and Genetic Algorithm (GA) using Empirical mode Decomposition (EMD). We compared our technique to some of the classic and novel image fusion strategies in our performance evaluation.Hybridization of PCNN with GA using EMD improves the fusion effect, image detail clarity, and time efficiency considerably than existing state of art strategies. Our quantitative analysis illustrates the effectiveness of the proposed strategy in terms of entropy, Percentage Residual Difference (PRD), Root Mean Square Error (RMSE) and Peak Signal to Noise Ratio (PSNR).