[1]李勇明,吕洋,李帆,等.基于磁共振影像特征集成融合的AD诊断[J].东南大学学报(自然科学版),2016,46(2):271-276.[doi:10.3969/j.issn.1001-0505.2016.02.008]
 Li Yongming,Lü Yang,Li Fan,et al.AD diagnosis based on integrated fusion of MR image features[J].Journal of Southeast University (Natural Science Edition),2016,46(2):271-276.[doi:10.3969/j.issn.1001-0505.2016.02.008]
点击复制

基于磁共振影像特征集成融合的AD诊断()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第2期
页码:
271-276
栏目:
生物医学工程
出版日期:
2016-03-20

文章信息/Info

Title:
AD diagnosis based on integrated fusion of MR image features
作者:
李勇明12吕洋1李帆1王品1邱明国2刘书君1闫瑾1
1重庆大学通信工程学院, 重庆400044; 2第三军医大学生物医学工程学院, 重庆400038
Author(s):
Li Yongming12 Lü Yang1 Li Fan1 Wang Pin1 Qiu Mingguo2 Liu Shujun1 Yan Jin1
1College of Communication Engineering, Chongqing University, Chongqing 400044, China
2College of Biomedical Engineering, The Third Military Medical University, Chongqing 400038, China
关键词:
磁共振影像 阿尔茨海默病 影像特征融合 特征选择分类集成模型 链式智能体遗传算法 支持向量机
Keywords:
magnetic resonance(MR)image Alzheimer’s disease(AD) image feature fusion feature selection classification ensemble model chain-like agent genetic algorithm(CAGA) support vector machine(SVM)
分类号:
R445.2;R741
DOI:
10.3969/j.issn.1001-0505.2016.02.008
摘要:
为了得到更高更稳定的阿尔茨海默病(AD)诊断准确率,对脑磁共振影像纹理特征进行了集成融合,并用于AD分类诊断.首先,基于病理知识提取脑磁共振影像中左右脑相关解剖结构的体积、纹理特征;然后,采用链式智能体遗传算法与支持向量机相结合的封装式特征选择分类集成模型,对提取的特征集进行特征选择,从而实现融合;最后,利用融合后的特征进行分类诊断,并将融合后的分类结果与融合前以及采用p值法特征选择的分类结果进行对比.实验结果表明,相比融合前的特征以及采用p值法进行选择的特征,利用所提算法融合后的特征具有更高且更稳定的分类准确率、灵敏度和特异度.
Abstract:
In order to obtain higher and more stable diagnostic accuracy of Alzheimer’s disease(AD), the texture features of magnetic resonance(MR)images were integrated and fused for AD diagnosis. First, the volume and texture features of the left and right parts of multiple anatomical structures were extracted based on pathological knowledge. Secondly, by combining the chain-like agent genetic algorithm(CAGA)and support vector machine(SVM), a feature selection classification ensemble model was designed to conduct deep feature selection and realize feature fusion. Finally, the fused features were used for classification and diagnosis of AD and the classification results are compared with those before fusion and those obtained by the p-value method. The experimental results show that the features fused by this proposed algorithm have higher and more stable classification accuracy, sensitivity and specificity than the features before fusion and the features selected by the p-value method.

参考文献/References:

[1] Tondelli M, Wilcock G K, Nichelli P, et al. Structural MRI changes detectable up to ten years before clinical Alzheimer’s disease[J]. Neurobiol Aging, 2012, 33(4): 825.e25-825.e36. DOI:10.1016/j.neurobiolaging.2011.05.018.
[2] Lötjönen J, Wolz R, Koikkalainen J, et al. Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer’s disease[J]. Neuroimage, 2011, 56(1): 185-196. DOI:10.1016/j.neuroimage.2011.01.062.
[3] Schoonenboom N S M, van der Flier W M, Blankenstein M A, et al. CSF and MRI markers independently contribute to the diagnosis of Alzheimer’s disease[J]. Neurobiol Aging, 2008, 29(5): 669-675. DOI:10.1016/j.neurobiolaging.2006.11.018.
[4] Salat DH. Imaging small vessel-associated white matter changes in aging[J]. Neuroscience, 2014, 276: 174-186. DOI:10.1016/j.neuroscience.2013.11.041.
[5] 李昕, 童隆正, 周晓霞, 等. 基于MR图像三维纹理特征的阿尔茨海默病和轻度认知障碍的分类[J]. 中国医学影像技术, 2011, 27(5):1047-1051.
  Li Xin, Tong Longzheng, Zhou Xiaoxia, et al. Classification of 3d texture features based on MR image in discrimination of Alzheimer disease and mild cognitive impairment from normal controls[J]. Chinese Journal of Medical Imaging Technology, 2011, 27(5):1047-1051.(in Chinese)
[6] Chincarini A, Bosco P, Calvini P, et al. Local MRI analysis approach in the diagnosis of early and prodromal Alzheimer’s disease[J]. Neuroimage, 2011, 58(2): 469-480. DOI:10.1016/j.neuroimage.2011.05.083.
[7] 夏宇. 基于不对称脑图像特征的阿尔兹海默病自动识别方法研究[D]. 重庆: 重庆大学通信工程学院, 2013.
[8] Kim J, Lee J H. Integration of structural and functional magnetic resonance imaging improves mild cognitive impairment detection[J]. Magn Reson Imaging, 2013, 31(5): 718-732. DOI:10.1016/j.mri.2012.11.009.
[9] Chen Y W, Lin C L, Mimori A. Multimodal medical image registration using particle swarm optimization[C]//2008 IEEE International Conference on Intelligent Systems Design and Applications. Kaohsiung, China, 2008:127-131.
[10] Baillard C, Hellier P, Barillot C. Segmentation of brain 3D MR images using level sets and dense registration [J]. Medical Image Analysis, 2001, 5(3):185-194.
[11] Gupta L, Sortrakul T.A Gaussian-mixture-based image segmentation algorithm [J]. Pattern Recognition, 1998, 31(3):315-325.
[12] Tsai K J, Yang C H, Lee P C, et al. Asymmetric expression patterns of brain transthyretin in normal mice and a transgenic mouse model of Alzheimer’s disease [J]. Neuroscience, 2009, 159(2):638-646. DOI:10.1016/j.neuroscience.2008.12.045.
[13] Toga A W, Thompson P M. Mapping brain asymmetry [J]. Nature Reviews Neuroscience, 2003, 4(1):37-48. DOI:10.1038/nrn1009.
[14] Li Yongming, Zeng Xiaoping, Han Liang, et al. Two coding based adaptive parallel co-genetic algorithm with double agents structure[J]. Engineering Applications of Artificial Intelligence, 2010, 23(4): 526-542. DOI:10.1016/j.engappai.2009.04.004.
[15] Petersen R C, Aisen P S, Beckett L A, et al. Alzheimer’s disease neuroimaging initiative(ADNI): clinical characterization[J]. Neurology, 2010, 74(3): 201-209. DOI:10.1212/WNL.0b013e3181cb3e25.

备注/Memo

备注/Memo:
收稿日期: 2015-06-08.
作者简介: 李勇明(1976—),男,博士,副教授;邱明国(联系人),男,博士,教授,qiumg_2002@sina.com.
基金项目: 国家自然科学基金资助项目(61108086,91438104,11304382)、 中国博士后科学基金资助项目(2013M532153)、中央高校基本科研业务费专项资金资助项目(CDJZR12160011,CDJZR13160008,CDJZR155507)、重庆市博士后科研项目特别资助项目.
引用本文: 李勇明,吕洋,李帆,等.基于磁共振影像特征集成融合的AD诊断[J].东南大学学报(自然科学版),2016,46(2):271-276. DOI:10.3969/j.issn.1001-0505.2016.02.008.
更新日期/Last Update: 2016-03-20