Medical image fusion with adaptive shape feature

Luo Fen, Lu Bibo and Miao Chun

Abstract

Medical image fusion is an important task for the retrieval of complementary information from medical images captured by different sensors. To improve the fusion effect, a new medical image fusion method is proposed with wavelet framework. The major contribution of our method is the construction of shape measure using structure tensor. The shape measure describes the amount of the structure information within a local region of the data and is used as an index to devise weight function for averaging. We apply the proposed approach to the fusion of medical images and the experimental results demonstrate the performance of the new method visually and quantitatively.