Fusion of CT And MRI Images Using Non-Sub Sampled Rotated Complex Wavelet Transform (NSRCXWT)

Multimodal medical image fusion technique isone of the current researches in the field of medical imagingand radiation medicine and is widely recognized by medicaland engineering fields. A multimodality medical imagefusion technique plays a vital role in biomedical research andmedical disease analysis.Image fusion is the process of combining relevant information from two or more images into a single image. In this project, we use the Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) data images of the same patient such that the tumors can be better visualized using the feature based Fusion of CT and MRI. This paper presents a novel approach to Multimodality Medical Image Fusion (MMIF) which is a technique of combining CT and MRI data of the same patient into a new slice using a Non-sub sampled Rotated Complex Wavelet Transform (NSRCxWT) and Discrete Wavelet Transform (DWT). The forward NSRCxWT and DWT is applied on both the CT and MRI images separately to extract the complementary and edge related features. These features are then combined to form a composite spectral plane using Average and Maximum value selection fusion rules. Then the inverse transformation is applied which results into a new, visually better and enriched fused image. The quality of these fused images is measured using Objective and Subjective evaluation metrics. Objective evaluation is performed by estimating some fusion parameters. The proposal method improves the quality of fused images when compared to the previous methods which is useful in diagnosis, analysis of stages of the disease and treatment review