Performance Comparison Of Medical Image Fusion Methods Based On Redundant Discrete Wavelet Transform, Wavelet Packet Transform And Contourlet Transform

Image fusion is the process of combining relevant information from two or more images into a single fused image. The resulting image will be more informative than any of the input images. The fusion in medical images is necessary for efficient diseases diagnosis from multimodality, multidimensional and multi parameter type of images. This paper describes a multimodality medical image fusion system using different fusion techniques and the resultant is analysed with quantitative measures. Initially, the registered images from two different modalities such as CT (anatomical information) and MRI T2, FLAIR (pathological information) are considered as input, since the diagnosis requires anatomical and pathological information. Then the fusion techniques based on Redundancy Discrete Wavelet Transform (RDWT), Wavelet Packet Transform and Contourlet Transform are applied. Further the fused image is analyzed with quantitative metrics such as Standard Deviation (SD), Entropy (EN), and Signal to Noise Ratio (SNR) for performance evaluation. From the experimental results it is observed that RDWT method provides better information quality for SD and SNR metric and the Contourlet Transform method provides better information quality using EN metric. Keywords— Contourlet Transform,Entropy, SD, SNR.