Medical Image Fusion Using a New Entropy Measure Between Intuitionistic Fuzzy Sets Joint Gaussian Curvature Filter
Qian Jiang, Jinfang Huang, Xin Jin, Puming Wang, Wei Zhou, Shaowen Yao
Abstract
Medical image fusion can provide a synthetical presentation of human tissue by fusing the complementary features of different source images, such as computerized tomography (CT) and magnetic resonance imaging (MRI), which contributes to clinical diagnosis and treatment. How to measure the key features of medical image is the most important issue in image fusion, intuitionistic fuzzy set (IFS) is a classical computation theory that can be employed to handle the task of feature extraction. In this work, we propose a medical image fusion method based on a new entropy measure of IFSs joint Gaussian curvature filter (GCF). First, GCF is employed to separate the medical image into a set of detailed subimages and a base subimage. Second, the detailed subimages is transformed into IFSs, so that the entropy measure of IFSs is then used to present image features. Third, two specific fusion rules are, respectively, utilized to integrate the detailed and base subimages. Finally, the fused image is produced by the fused subimages based on the regulation of GCF. Several specific experiments are performed on our entropy measure to test the performance, and the existing image fusion methods are also performed to verify the performance of our image fusion method.