A fusion algorithm of PET-CT based on dual-tree complex wavelet transform and self-adaption Gaussian membership function

Abstract

This article proposed a new fusion algorithm of PET/CT based on dual-tree complex wavelet transform and self-adaption Gaussian membership function. Firstly, preprocessed and registered PET and CT image of non-small cell lung cancer. Secondly, used dual-tree complex wavelet transform to decompose PET and CT image in order to get the low-frequency and high-frequency components. Thirdly, using self-adaption Gaussian membership function to fuse low-frequency components. Finally, using two experiments to verify validity and feasibility of the proposed algorithm. The experiments results shown that the algorithm is efficiency.