Anatomical and functional image fusion with guided filtering

Abstract

Multi-modal medical image fusion (MMIF) technology is playing an increasingly important role in many clinical applications. In this paper, a novel anatomical and functional image fusion method based on guided filtering (GF) is proposed. In our proposed method, GF is firstly used to decompose the anatomical image into a base image and a detail image. Then the base image and the Y channel of the functional image are combined according to the local energy maximum fusion rule, and the detail image is used to enhance the details of the anatomical image. The proposed method has potential practical value for clinical applications due to its high computational efficiency. Experimental results demonstrate that the proposed method can achieve better results in term of subjective observation and objective metrics.