期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：3
页码：367-382
DOI：10.14257/ijsip.2016.9.3.32
出版社：SERSC
摘要：Medical image fusion plays an important role in clinical applications such as image-guided surgery, image-guided radiotherapy, non-invasive diagnosis, and treatment planning. In order to improve the comprehension of multiple medical image information, we consider the advantage of non-subsampled contourlet transform (NSCT) in multi-scale analysis method and multiple directions and apply it to multi-channel PCNN (m-PCNN). In this paper, a novel medical image fusion method based on m-PCNN in NSCT domain is present. The proposed method exploits the advantage of the multi-scale analysis method and multiple directions of contourlet transform, this algorithm will get the low- frequency and high- frequency sub-bands of the two source medical images by using the NSCT transform, we select different fusion rule in different frequency sub-bands. Low-frequency coefficients are fused by using the average rules, while high-frequency coefficients are fused by inputting to the m-PCNN. The performance of the proposed method is illustrated by using four pairs of medical images as our experimental objects. The experimental results show the superior performance compared with other methods, in both visual effect and objective evaluation criteria.
