The art of medical image fusion: A survey

Abstract

Medical image fusion is the idea to improve the image content by fusing images taken from different imaging tools like Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET) and single photon emission computed tomography (SPECT). The objective of image fusion is to combine more useful information and remove redundant information from source registered images. In this survey paper, image fusion techniques are broadly classified into two categories; Pixel level image fusion and transform based image fusion. Various approaches in each category are discussed in detail. Comparative analysis is done based on the limitations and advantages of each method and quantitative analysis is conducted using entropy, UIQI, fusion factor, fusion symmetry and processing time. For analysis purpose we have considered the combination of CT and MRI images. It is very hard to select one method for all applications. But from visual perspective, fused images obtained from fuzzy inference system give better result.