Paper Title
Spine Image Fusion Using NSCT And Pixel Level Fusion

Abstract
In medical science image fusion technique is very important. The main motivation is to capture most relevant information from sources into a single output, which plays an important task in medical diagnosis. In medical image fusion the most important information is edges and outlines of interested objects than any other. Therefore edge-like features is needed to be preserved. In medical diagnosis computed tomography (CT), magnetic resonance image (MRI), scan provides different types of information that is soft tissue and bony detail respectively, by fusing them we can get accurate information for better clinical diagnosis. The project proposed a new medical image fusion based on non subsampled contourlet transform (NSCT).The Spine image fusion algorithm based on NSCT is used to fuse both CT and MR images thereby making easy for physicians to visually assess corresponding soft tissue and bony detail on a single image. The shift-invariance is required in image analysis applications, such as edge detection, Contour characterization, and image fusion. The NSCT provide shift-invariant property along with multiscale, multidirection property that has a fast performance. The nonsubsampled contourlet transform consist of nonsubsampled pyramids which provide multiscale decomposition and nonsubsampled directional filter banks for directional decomposition. The NSCT has proven to be very efficient in image denoising and image enhancement. Index Terms— Image Fusion, Nonsubsampled Contourlet Transform, Nonsubsampled Pyramid, Nonsubsampled Directional Filter Bank.