基于人眼视觉特性的NSCT医学图像自适应融合

戴文战, 姜晓丽, 李俊峰

电子学报 ›› 2016, Vol. 44 ›› Issue (8) : 1932-1939.

PDF(2825 KB)
PDF(2825 KB)
电子学报 ›› 2016, Vol. 44 ›› Issue (8) : 1932-1939. DOI: 10.3969/j.issn.0372-2112.2016.08.023
学术论文

基于人眼视觉特性的NSCT医学图像自适应融合

  • 戴文战1, 姜晓丽1, 李俊峰2
作者信息 +

Adaptive Medical Image Fusion Based on Human Visual Features

  • DAI Wen-zhan1, JIANG Xiao-li1, LI Jun-feng2
Author information +
文章历史 +

摘要

医学图像融合对于临床诊断具有重要的应用价值.针对多模态医学图像特性,本文提出一种基于人类视觉特性的医学图像自适应融合方法.首先,对经配准的源图像进行非间隔采样轮廓变换((Nonsubsampled Coutourlet,NSCT)多尺度分解,得到低频子带和若干高频方向子带;其次,根据低频子带集中了大部分源图像能量和决定图像轮廓的特点,采用区域能量与平均梯度相结合的方法进行融合;根据人眼对图像对比度及边缘、纹理的高敏感度,在高频子带系数的选取时提出区域拉普拉斯能量、方向对比度与脉冲耦合神经网络(Pulse Coupled Neural Network,PCNN)相结合的融合策略;进而,提出了把与人类视觉高度一致的加权结构相似度(Weighted Structure Similarity,WSSIM)作为图像融合目标函数,自适应地获取各子带的最优权值;最后,对灰度图像和彩色图像进行了大量融合比较实验,并对不同融合方法进行分析对比.实验结果表明:本文算法不仅可以有效保留源图像的信息,而且可以使融合图像灰度级更分散,更好地保留了图像边缘信息,具有更好的视觉效果.

Abstract

Medical image fusion has very important application value for medical image analysis and diseases diagnosis.According to the characteristics of multi modality medical image and human visual features,a new medical image fusion algorithm in NSCT (nonsubsampled coutourlet,NSCT) domain is proposed.Firstly,source images after registration are decomposed into low and high frequency sub-bands using NSCT.According to the low frequency subbands concentrating the majority energy of the source image and determining the image coutour,a fusion rule based on weighted region average energy combined with average gradient is adopted in low frequency subband coefficients.Moreover,according to human visual system which is more sensitive to contrast and edge,texture of image,the fusion strategy based on directive contrast integrated with the improved energy of Laplacian and PCNN (Pulse Coupled Neural Network,PCNN) are used to fuse high-frequency subbands.Furthermore,a closed loop feedback is introduced into the fusion rules of low and high frequency subbands to obtain optimal fused weights adaptively by using WSSIM (Weighted Structure Similarity,WSSIM) which highly consistent with the HVS(human visual features,HVS) as objective function.Finally,a lot of experiments of fusion of images including gray images and color images based on different fusion methods are conducted.The experiment results are analyzed in terms of visual quality and objective evaluation.The experiment results show that the proposed algorithm can effectively preserve information and significantly improve the performance of fusion image in terms of quantity of information,dispersed gray scale,visual quality and objective evaluation index.

关键词

医学图像融合 / 人类视觉特征 / 加权结构相似度 / 非间隔采样轮廓变换 / 拉普拉斯能量和方向对比度 / 脉冲耦合神经网络

Key words

medical image fusion / HVF (Human Visual Features) / WSSIM (Weighted Structure Similarity) / NSCT (Nonsubsampled Coutourlet) / directive contrast integrated with the improved energy of Laplacian / PCNN (Pulse Coupled Neural Network)

引用本文

导出引用
戴文战, 姜晓丽, 李俊峰. 基于人眼视觉特性的NSCT医学图像自适应融合[J]. 电子学报, 2016, 44(8): 1932-1939. https://doi.org/10.3969/j.issn.0372-2112.2016.08.023
DAI Wen-zhan, JIANG Xiao-li, LI Jun-feng. Adaptive Medical Image Fusion Based on Human Visual Features[J]. Acta Electronica Sinica, 2016, 44(8): 1932-1939. https://doi.org/10.3969/j.issn.0372-2112.2016.08.023
中图分类号: TP391.4   

参考文献

[1] Bhatnagar G,Wu Q M J.Directive contrast based multimodal medical image fusion in NSCT domain[J].IEEE Transactions on multimedia,2013,15(5):1014-1024.
[2] Prakash C,Rajkumar S,Mouli P C.Medical image fusion based on redundancy DWT and Mamdani type min-sum mean-of-max techniques with quantitative analysis[A].International Conference on Recent Advances in Computing and Software Systems 2012[C].Chennai,India:IEEE Computer Society,2012.54-59.
[3] Shen Y,Ren E,Dang G H,et al.A nonsubsampled contourlet transform based medical image fusion method[J].Information Technology Journal,2013,12(4):749-755.
[4] 陶观群,李大鹏,陆光华.小波分析方法在医学图像融合中的应用[J].西安电子科技大学学报(自然科学版),2004,31(1):82-86.TAO G Q,LI D P,LU G H.Application of wavelet analysis in medical image fusion[J].Journal Of Xidian University,2004,31(1):82-86.(in Chinese)
[5] Ling T,Qian Z Y.An improved medical image fusion algorithm based on wavelet transform[A].Seventh International Conference on Natural Computation (ICNC)2011[C].Shanhai,China:IEEE Computer Society,2011.76-78.
[6] Barmas,Shirin Mahmoudi,Kasaei,Shohreh.Contourlet-based multispectral image fusion[A].7th IASTED International Conference on Visualization,Imaging,and Image Processing VⅡP 2007[C].Canada.Acta Press,2007.11-14.
[7] 杨艳春,王晓明,党建武,等.基于非下采样Coutourlet变换的医学图像融合方法[J].计算机科学,2013,40(3):310-313.Yang Y C,Wang X M,Dang J W,et.Method of medical image fusion based on nonsubsample coutourlet transform[J].Computer Science,2013,40(3):310-313.(in Chinese)
[8] 焦李成,侯彪,王爽,等.图像多尺度几何分析理论与应用-后小波分析理论与应用[M].西安:西安电子科技大学出版社,2008:280-288.
[9] Cunha A L,Zhou J P,Minh Do N.The nonsubsampled contourlet transform:theory,design and applications[J].IEEE Transactions on Image Processing.2006,15(10):3089-3101.
[10] 郝文超,贾年.NSCT域内基于自适应PCNN的红外与可见光图像融合算法[J].西华大学学报(自然科学版),2014,33(3):11-15.Hao W C,Jia N.Fusion algorithm of infrared and visible images based on adaptive PCNN in NSCT domain[J].Journal of Xihua University (Natural Science),2014,33(3):11-15.(in Chinese)
[11] 江平,张强,李静,等.基于NSST和自适应PCNN的图像融合算法[J].激光与红外,2014,44(1):108-113.Jiang P,Zhang Q,Li J,et.Fusion algorithm for infrared and visible image bansed on NSST and adaptive PCNN[J].Laser&Infraerd,2014,44(1):108-113.(in Chinese)
[12] Chang X,Jiao L C,Liu F,et.Multicoutourlet-based adaptive fusion of infrared and visible remote sensing images[J].IEEE Geosicience and Remote Sensing Letters,2010,7(3):549-553.
[13] Liu F,Yang B,Gang K.Image fusion using adaptive dual-tree discrete wavelet packets based on the noise distribution estimation[A].International Conference on Audio,Language and image 2012[C].Shanghai,China:IEEE Computer Society,2012.475-479.
[14] 杨晓慧,贾建,焦李成.基于活性测度和闭环反馈的非下采样Contourlet域图像融合[J].电子与信息学报,2010,32(2):422-426.Yang X H,Jia J,Jiao L C.Image fusion algorithm in nonsubsample coutourlet domain based on activity measure and closed loop feedback[J].Journal of Electronics&Information Technology,2012,32(2):422-426.(in Chinese)
[15] 任仙怡,刘秀坚,胡涛,等.基于视觉注意机制与区域结构相似度的图像融合质量评价[J].计算机应用,2011,31(11):3022-3026.Ren X Y,Liu X J,Hu T,et al.Objective quality evaluation of image based on visual attention mechanism and regional structural similarity[J].Journal of Computer Applications,2011,31(11):3022-3026.(in Chinese)
[16] Wang Z,Bovik A C.A universal image quality index[J].IEEE Signal Processing Letters,2002,9(3):81-84.
[17] Yang C,Zhang J Q,Wang X R,et al.A novel similarity based quality metric for image fusion[J].Information Fusion,2008,9(2):156-160.
[18] Wang Z,Simoncelli E.P,Bovik A.C.Multi-scale structural similarity for image quality assessment[A].37th Asilomar Conference on Signals,Systems and Computers[C].United States:IEEE Institute of Electrical and Electronics Engineers Computer Society,2003.1398-1402.
[19] 李美丽,李言俊,王红梅,等.基于NSCT和PCNN的红外与可见光图像融合方法[J].光电工程,2010,37(6):90-95.Li M L,Li Y J,Wang H M,et.Fusion algorithm of infrared and visible image based on NSCT ans PCNN[J].Opto-Electronic Engineering,2010,37(6):90-95.(in Chinese)
[20] 杨艳春,党建武,王阳萍.基于提升小波变换与自适应PCNN的医学图像融合方法[J].计算机辅助设计与图形学学报,2012,24(4):494-499.Yang Y C,Dang J W,Wang Y P.A medical image fusion method based on lifting wavelet transform and adaptive PCNN[J].Journal of Computer-Aided Design&Computer Graphics,2012,24(4):494-499.(in Chinese)
[21] 郝爱枝,郑晟.基于NSCT-PCNN变换的多传感器图像融合[J].科学技术与工程,2014,14(1):45-48.Hao A Z,Zheng S.Multi-sensor image fusion based on NSCT-PCNN transform[J].Science Technology and Engineering,2014,14(1):45-48.(in Chinese)
[22] 廖勇,黄文龙,尚琳,等.Shearlet与改进PCNN相结合的图像融合[J].计算机工程与应用,2014,50(2):142-146.Liao Y,Huang W L,Shang L,et.Image fusion based on Shearlet and improved PCNN[J].computer Engineering and Applications,2014,50(2):142-146.(in Chinese)
[23] 屈小波,闫敬文,杨贵德.改进拉普拉斯能量和的尖锐频率局部化Coutourlet域多聚焦图像融合[J].光电精密工程,2009,17(5):1203-1212.Qu X B,Yan J W,Yang G D.Multifocus image fusion method of shape frequency localized contourlet transform domain based on sum-modified-laplacian[J].Optic and Precision Engineering,2009,17(5):1203-1212.(in Chinese)
[24] 敬忠良,肖刚,李振华.图像融合-理论与应用[M].北京:高等教育出版社,2007:194-204.
[25] 胡俊峰,唐鹤云,钱建生.基于小波变换医学图像融合算法的对比分析[J].中国生物医学工程学报,2011,30(2):196-205.Hu Junfeng,Tang Heyun,Qian Jiansheng.Comparison and analysis of medical fusion algorithms based on wavelet transform[J].Chinese Journal of Biomedical Engineering,2011,30(2):196-205.(in Chinese)
[26] Zhou L J.A Gradient-based Multi-focus image fusion method using multiwavelets transform[A].International Conference on Industrial Control and Electronics Engineering (ICICEE)2012[C].Xi'an,China:IEEE Computer Society,2012.392-395.
[27] 王昕,李玮琳,刘富.小波域CT/MRI医学图像融合新方法[J].吉林大学学报(工学版),2013,43(S1):25-28.Wang X,Li W L,Liu F.New algorithm of CT/MRI medical image fusion based on wavelet domain[J].Journal of Jilin University (Engineering and Technology Edition),2013,43(S1):25-28.(in Chinese)
[28] 李超,李光耀,谭云兰,等.基于非下采样Contourlet变换和区域特征的医学图像融合[J].计算机应用,2013,33(6):1727-1731.Li C,Li G Y,Tan Y L,et al.Medical image fusion of nonsubsample coutourlet transform and region feature[J].Journal of Computer Applications,2013,33(6):1727-1731.(in Chinese)
[29] 覃征,鲍复民,李爱国,等.数字图像融合[M].西安:西安交通大学出版社,2004.10-12.

基金

国家自然科学基金 (No.61374022)
PDF(2825 KB)

文章所在专题

机器学习与智慧医疗

1902

Accesses

0

Citation

Detail

段落导航
相关文章

/