A Secure Method for Medical Image Fusion

Medical image fusion has been used to derive useful information from multimodality medical image data. The idea is to improve the image content by fusing complimentary images like computer tomography (CT) and magnetic resonance imaging (MRI) images, so as to provide more information to the doctor and clinical treatment planning system. However in existing image fusion software, there is no element of image authentication and security, vital for fields like forensics. We have proposed a unique method in which we perform watermarking on input images of MRI and CT, fuse them using an efficient fusion algorithm and hide the fused image using a suitable steganographic technique, thus authenticating and securing the fused image. Our work covers the selection of best frequency domain based fusion algorithms for medical image fusion, implementation of fusion rules and the fusion image quality evaluation, with special emphasis on the 2-D wavelet transform for images. The fusion performance is evaluated on the basis of the root mean square error (RMSE) and peak signal to noise ratio (PSNR).