基于NSST与改进稀疏表示的医学图像融合方法  

Medical Image Fusion Method Based on NSST and Improved Sparse Representation

作　　者：朱宏伟 ZHU Hongwei(Network Information Center,Jilin Agricultural Science and Technology University,Jilin 132101,Jilin Province,China)

机构地区：[1]吉林农业科技学院网络信息中心,吉林吉林132101

出　　处：《吉林大学学报（理学版）》2020年第4期931-936,共6页Journal of Jilin University:Science Edition

基　　金：吉林省新兴交叉学科“数字农业”重点培育项目(批准号:吉农院合字[2020]第XSNZ002号);吉林农业科技学院青年基金(批准号:校20190420).

摘　　要：针对单一模态的医学图像无法为临床诊断提供全面、互补信息的问题,提出一种基于非下采样剪切波变换(NSST)与改进稀疏表示(ISR)的多模态医学图像融合方法.首先用NSST分解工具将待融合图像分解为一个低频子带和若干个高频子带;其次,用ISR方法融合低频子带,通过Sobel算子和引导滤波器去除低频子带的细节特征,从而提高低频子带的融合效率,同时对高频子带采用绝对值最大的融合规则进行融合;最后,将融合后的低频子带和高频子带进行逆NSST变换得到最终的融合图像.实验结果表明,该方法在主观视觉性能和客观评价上均优于其他对比融合方法.Aiming at the problem that single-modality medical images could not provide comprehensive and complementary information for clinical diagnosis,the author proposed a multimodal medical image fusion method based on nonsubsampled shearlet transform(NSST)and improved sparse representation(ISR).Firstly,the NSST tool was used to decompose the source image into a low frequency subband and several high frequency subbands.Secondly,the ISR method was used to fuse the low-frequency subbands,and the details of the low-frequency subbands were removed by the sobel operator and the guided filter,thereby improving the fusion efficiency of the low-frequency subbands.At the same time,the high-frequency subbands were fused by using the maximum absolute value fusion rule.Finally,the final fused image was obtained by the inverse NSST transform of the fused low-frequency and high-frequency subbands.Experimental results show that proposed method is superior to other fusion methods in subjective visual performance and objective evaluation.

关 键 词：医学图像融合 非下采样剪切波 改进稀疏表示 融合规则 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]