Medical Image Fusion using Combined Discrete Wavelet and Ripplet Transforms

Abstract

Medical images like CT and MRI provide complementary information. These images need to be fused for proper diagnosis and also for clinical evaluation. This paper proposes a new medical image fusion based on the combined effect of Discrete Wavelet Transform (DWT) and Discrete Ripplet Transform (DRT). The images are initially transformed into multiresolution image using DWT. The approximation images are further transformed using DRT. The ripplet coefficients are applied to Pulse Coupled Neural Network (PCNN) and firing maps are produced. Applying the maximum fusion rule and inverse DRT, the fused coefficients of the approximation image are obtained. The detail images of the DWT are then fused using absolute maximum fusion rule. The fused image is obtained by applying inverse DWT to the fused coefficients. The performance of the fused image is evaluated using metrics like entropy, standard deviation and average gradient and it outperforms the other existing methods.