计算机科学 ›› 2016, Vol. 43 ›› Issue (11): 291-296.doi: 10.11896/j.issn.1002-137X.2016.11.056

• 图形图像与模式识别 • 上一篇    下一篇

基于自适应云模型的多模态脑部图像融合方法

赵佳,肖斌,李伟生,王国胤   

  1. 重庆邮电大学计算智能重庆市重点实验室 重庆400065,重庆邮电大学计算智能重庆市重点实验室 重庆400065,重庆邮电大学计算智能重庆市重点实验室 重庆400065,重庆邮电大学计算智能重庆市重点实验室 重庆400065
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金:基于多模态医学图像处理的多维可视化辅助诊疗关键技术研究(U1401252),国家自然科学基金: 基于词袋模型的多特征融合物体识别方法研究(61272195),重庆市基础与前沿研究杰青项目:模式识别与图像处理基础理论及应用研究(cstc2014jcyjjq40001)资助

Fusion Method of Multi-model Brain Images Based on Adaptive Cloud Model

ZHAO Jia, XIAO Bin, LI Wei-sheng and WANG Guo-yin   

  • Online:2018-12-01 Published:2018-12-01

摘要: 多模态医学图像融合通过提取并综合不同模态的医学图像信息,获得对病灶部位更加清晰、全面、准确、可靠的图像描述,为医生对疾病的诊断和合理治疗方案的制定提供可靠的依据。云模型理论是认知科学研究的新成果,具有兼顾随机性和模糊性的优点,在图像融合中的应用较少。借助云模型理论将来自不同模态的MRI(核磁共振成像)脑部图像、MRI与PET(正电子发射断层成像)、MRI与SPECT(单光子发射断层成像)脑部图像进行融合。首先,根据脑部图像自身的灰度直方图特征,对灰度直方图进行拟合;然后,由拟合曲线的谷值点划分区间并通过逆向云发生器自适应地生成云模型;最后,设计云推理规则,得到融合后的图像。实验结果表明,相比传统融合方法,所提方法融合后的图像脑部特征更清晰,激活区域更明显,在主观融合效果与客观评价指标方面均有很大的提高。

关键词: 云模型理论,核磁共振成像,脑部图像融合,评价指标

Abstract: Through extracting and combining medical image information from different models of images,multi-model medical image fusion can obtain more clear,comprehensive,accurate and reliable image description on lesion site,and provide reliable basis for doctors to diagnosis of the disease and formulate reasonable treatment plan.Cloud model is a recently proposed theory in cognitive science,it has the advantage of taking the randomness and fuzziness into account,and has less application in image fusion at present.The paper introduced a method to fuse multi-model brain images such as two types MRI(Magnetic Resonance Imaging) brain image,MRI and PET(Positron Emission Tomography),MRI and SPECT(Single-Photon Emission Computed Tomography) using cloud model theory.Three steps are included in the proposed fusion method.At first,the histogram of input brain image with a smooth curve using the high-order spline function is fitted.Then the intervals in line with the valley point of the fitted curve are divided and cloud model is generated adaptively through reverse cloud generator.At last,cloud reasoning rules are designed and the fused image is gotten.The experimental results show that the characteristics of fused brain images gotten by the proposed method are clearer and the active regions are more significant than existing methods.The proposed method shows great improvement in both subjective effect and objective evaluation.

Key words: Cloud model theory,Magnetic resonance imaging,Brain image fusion,Evaluation index

[1] George E B,et al.MRI Brain Image Enhancement Using FilteringTechniques[J].International Journal on Computer Science & Engineering,2012,3(9):399-403
[2] Balafar M A,Ramli A R,Saripan M I,et al.Review of brainMRI image segmentation methods[J].Artificial Intelligence Review,2010,33(3):261-274
[3] Huang P W,Chen C I,Lin P L,et al.PET and MRI brain image fusion using wavelet transform with structural information adjustment and spectral information patching[C]∥Proceeding of the IEEE International Symposium on Bioelectronics and Bioinformatics(ISBB).Taiwan,China,2014:1-4
[4] Wang Jing-yun,Li Shao-lin.New progress in medical image fusion technology[J].Fourth Mil Med Univ,2004,25(20):1918-1920(in Chinese) 王静云,李绍林.医学影像图像融合技术的新进展[J].第四军医大学学报,2004,25(20):1918-1920
[5] James A P,Dasarathy B V.Medical image fusion:A survey of the state of the art[J].Information Fusion,2014,19(3):4-19
[6] Tu T M,Su S C,Shyu H C,et al.A new look at IHS-like image fusion methods[J].Information Fusion,2001,2(3):177-186
[7] Bhatnagar G,Wu Q M J,Liu Z.Human visual system inspired multi-modal medical image fusion framework[J].Expert Systems with Applications,2013,40(5):1708-1720
[8] Yonghong J.Fusion of landsat TM and SAR image based on principal component analysis[J].Remote Sensing Technology and Application,1998,13(1):46-49
[9] Wang A,Sun H,Guan Y.The application of wavelet transform to multi-modality medical image fusion[C]∥Proceeding of the IEEE International Conference on Networking,Sensing and Control(ICNSC).Ft.Lauderdale,Florida,USA,2006:270-274
[10] Wang Lei.Study for the Key Algorithms in Multi-Modal Medical Image Registration and Fusion[D].Guangzhou:South China University of Technology,2013(in Chinese) 王雷.多模态医学图像配准与融合关键算法研究[D].广州:华南理工大学,2013
[11] Zheng S Z,Shi W Z,Liu L J,et al.Multisource image fusionmethod using support value transform[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2007,16(7):1831-1839
[12] Cavus N.The evaluation of Learning Management Systemsusing an artificial intelligence fuzzy logic algorithm[J].Advances in Engineering Software,2010,41(2):248-254
[13] Huang W,Jing Z.Multi-focus image fusion using pulse coupled neural network[J].Pattern Recognition Letters,2007,28(9):1123-1132
[14] Li Wen-juan,Na Yan.Medical image fusion based on cloud computing and content analysis[J].Electronic Science and Technol-ogy,2011,24(3):22-26(in Chinese) 李文娟,那彦.基于云计算及图像内容分析的医学图像融合方法[J].电子科技,2011,24(3):22-26
[15] Li De-yi,Liu Chang-yu,Du Yi,et al.Artificial intelligence with uncertainty[J].Journal of Software,2004,15(11):1583-1594(in Chinese) 李德毅,刘常昱,杜鹢,等.不确定性人工智能[J].软件学报,2004,15(11):1583-1594
[16] Wang G Y,Xu C L,Zhang Q H,et al.A multi-step backward cloud generator algorithm[C]∥Proceeding of the 8th International Conference on Rough Sets and Current Trends in Computing(RSCTC).Chengdu,China,2012:313-322
[17] Liu Gui-hua,Song Cheng-xiang,Liu Hong.Software implementation of cloud generators[J].Application Research of Compu-ters,2007,24(1):46-48(in Chinese) 刘桂花,宋承祥,刘弘.云发生器的软件实现[J].计算机应用研究,2007,24(1):46-48
[18] Chen Hao,Li Bing.Cloud Reasoning Method and its Application in Prediction[J].Computer Science,2011,38(7):209-211(in Chinese) 陈昊,李兵.云推理方法及其在预测中的应用[J].计算机科学,2011,38(7):209-211
[19] Liang Zhong-wei,Ye Bang-yan,Peng Rui-tao,et al.Multi-thre-shold dividing technology of digital image based on gray histogram fitting curves[J].Modern Manufacturing Engineering,2007(9):103-106(in Chinese) 梁忠伟,叶邦彦,彭锐涛,等.基于灰度直方图拟合曲线的数字图像多阈值分割技术研究[J].现代制造工程,2007(9):103-106
[20] Zhang Shao-hua,Sun Dao-chun.The order of derived functions of algebroidal functions[J].Acta Mathematica Scientia,2005,25(6):933-938(in Chinese) 张少华,孙道椿.代数体函数的导函数的级[J].数学物理学报,2005,25(6):933-938
[21] Qin K,Luo L,Wu T,et al.Image segmentation based on two-dimensional cloud model[C]∥Proceeding of the IEEE International Conference on Audio Language and Image Processing(ICALIP).Chongqing,China,2010:791-796
[22] Di Hong-wei,Liu Xian-feng.Image fusion quality assessmentbased on structural similarity[J].Acta Photonica Sinica,2006,35(5):766-771(in Chinese) 狄红卫,刘显峰.基于结构相似度的图像融合质量评价[J].光子学报,2006,35(5):766-771
[23] Piella G,Heijmans H.A new quality metric for image fusion[C]∥Proceeding of the IEEE International Conference on Image Processing(ICIP).Chongqing,China,2003:III-173-6
[24] Zhao J,Laganiere R,Liu Z.Performance assessment of combinative pixel-level image fusion based on an absolute feature mea-surement[J].International Journal of Innovative Computing,2006,3(6):1433-1447
[25] Jang J H,Bae Y,Ra J B.Contrast-enhanced fusion of multisensor images using subband-decomposed multiscale retinex[J].IEEE Transactions on Image Processing,2012,21(8):3479-3490

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!