基于多小波变换的医学图像融合算法研究

摘要

Obective: To present a medical image fusion algorithm based on multiwavelet transform. Methods: PET and CT images were decomposed using multiwavelet transform firstly. Then, we usd average gradient fusion in the low-frequency part and auto adapted weighted fusion in the high-frequency part. Finally, we could obtain the ater inverse transformation and postfiltering. Rusults: The fusion image combines information of the source images, adds more details and texture information, and achieves a good fusion result. Couclusions: Experimental results show that based on the proposed algorithm we can obtain the best result.%目的:研究一种基于多小波变换的医学影像融合的算法.方法:对已配准的PET图像和CT图像进行预滤波后进行多小波分解,对分解后的图像低频分量采用平均梯度法及高频分量采用自适应加权法的融合规则进行图像融合,经过多小波重构及后滤波得到融合图像.结果:融合图像通过结合源图像的信息,增加了更多的细节和纹理信息,从而得到了良好的融合效果.结论:实验证明,基于该算法,可以得到图像的最佳融合结果.