用户名: 密码: 验证码:
基于海马纹理特征的阿尔茨海默病早期识别
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Early classification of Alzheimer's Disease based on hippocampal texture features
  • 作者:赵坤 ; 丁艳辉 ; 张增强 ; 周波 ; 姚洪祥 ; 王盼 ; 冯枫 ; 郑元杰 ; 刘勇 ; 张熙
  • 英文作者:ZHAO Kun;DING Yanhui;ZHANG Zengqiang;ZHOU Bo;YAO Hongxiang;WANG Pan;FENG Feng;ZHENG Yuanjie;LIU Yong;ZHANG Xi;School of Information Science and Engineering,Shandong Normal University;Department of Internal Neurology, Chinese PLA General Hospital;Radiology Department, Chinese PLA General Hospital;Institute of Automation,Chinese Academy of Sciences;
  • 关键词:阿尔茨海默病 ; 海马 ; 影像组学特征 ; 支持向量机
  • 英文关键词:Alzheimer's Disease;;hippocampus;;texture feature;;Support Vector Machines
  • 中文刊名:XXYD
  • 英文刊名:Journal of Terahertz Science and Electronic Information Technology
  • 机构:山东师范大学信息科学与工程学院;解放军总医院南楼神经内科;解放军总医院南楼放射科;中国科学院自动化研究所;
  • 出版日期:2019-02-28
  • 出版单位:太赫兹科学与电子信息学报
  • 年:2019
  • 期:v.17
  • 基金:国家自然科学基金资助项目(81471120);; 山东省重点研发计划资助项目(2017GGX10112);; 山东省高等学校科技计划资助项目(J15LN24)
  • 语种:中文;
  • 页:XXYD201901031
  • 页数:5
  • CN:01
  • ISSN:51-1746/TN
  • 分类号:139-143
摘要
阿尔茨海默病(AD)是一种神经退行性疾病。随着脑医学影像的发展,对AD诊断的精确度也在进一步提高,但对AD的诊断,客观上仍缺少好的生物标记。为寻找到AD的更稳定的生物标记,利用海马的影像组学特征对海马的信号强度、形状、灰度阶梯分布等特征进行刻画,通过方差分析(ANOVA)和事后检验,在统计学上寻找出正常对照(NC)、AD、轻度认知损害(MCI)之间存在差异的特征;通过与被试的简易智能状况检查(MMSE)评分进行相关性分析,找寻与MMSE评分相关性较高的特征;利用支持向量机(SVM)构建一个对AD和NC分类的模型,交叉验证得到的正确率为86%。结果表明,海马的影像组学特征是一个很好的生物标记,能对AD进行有效的早期识别。
        Alzheimer's Disease(AD) is a neurodegenerative disease. With the development of brain imaging, the accuracy of AD diagnosis has been well improved. However, there still lack of good markers to early diagnosis of AD. In order to find more stable biomarkers of AD, the hippocampus intensity, shape,grayscale gradient distribution and other characteristics are investigated by an Analysis Of Variance and post-hoc analysis so as to identify the alteration in AD and Mild Cognitive Impairment(MCI) in comparison to Normal Controls(NC). The results show that the Mini-Mental State Examination(MMSE) scores are significantly associated with the radiomic features of the bilateral hippocampus. The classification analysis with the Support Vector Machine(SVM) shows that an accuracy of 86% can be obtained with leaving one out cross validation, which indicates that the hippocampal texture might be taken as one of the potential markers for AD.
引文
[1]QUERFURTH H W,LAFERLA F M.Alzheimer's disease[J].The New England Journal of Medicine,2010(362):329-344.
    [2]PETERSEN R C,KNOPMAN D S,BOEVE B F,et al.Mild cognitive impairment:ten years later[J].Archives of Neurology,2009,66(12):1447-1455.
    [3]GUO Y,ZHANG Z Q,ZHOU B,et al.Grey-matter volume as a potential feature for the classification of Alzheimer's disease and mild cognitive impairment:an exploratory study[J].Neurosci Bull,2014,30(3):477-489.doi:10.1007/s12264-013-1432-x.
    [4]HAMPEL H,BURGER K,TEIPEL S J,et al.Core candidate neurochemical and imaging biomarkers of Alzheimer's disease[J].Alzheimer's&Dementia:the Journal of the Alzheimer's Association,2008,4(1):38-48.doi:10.1016/j.jalz.2007.08.006.
    [5]BEHESHTI I,DEMIREL H.Feature-ranking-based Alzheimer's disease classification from structural MRI[J].Magnetic Resonance Imaging,2016,34(3):252-263.doi:10.1016/j.mri.2015.11.009.
    [6]JIE B,ZHANG D,CHENG B,et al.Manifold regularized multitask feature learning for multimodality disease classification[J].Human Brain Mapping,2015,36(2):489-507.doi:10.1002/hbm.22642.
    [7]RITTER K,SCHUMACHER J,WEYGANDT M,et al.Multimodal prediction of conversion to Alzheimer's disease based on incomplete biomarkers[J].Alzheimer's&Aementia,2015,1(2):206-215.doi:10.1016/j.dadm.2015.01.006.
    [8]BRAAK H,BRAAK E.Staging of Alzheimer's disease-related neurofibrillary changes[J].Neurobiology of Aging,1995,16(3):271-278.doi:10.1016/0197-4580(95)00021-6.
    [9]PASQUINI L,SCHERR M,TAHMASIAN M,et al.Link between hippocampus'raised local and eased global intrinsic connectivity in AD[J].Alzheimer's&Dementia:the Journal of the Alzheimer's Association,2015,11(15):475-484.doi:10.1016/j.jalz.2014.02.007.
    [10]EZZATI A,KATZ M J,ZAMMIT A R,et al.Differential association of left and right hippocampal volumes with verbal episodic and spatial memory in older adults[J].Neuropsychologia,2016,93(Pt B):380-385.doi:10.1016/j.neuropsychologia.2016.08.016.
    [11]BAI F,ZHANG Z,WASTON D R,et al.Abnormal functional connectivity of hippocampus during episodic memory retrieval processing network in amnestic mild cognitive impairment[J].Biol Psychiatry,2009,65(11):951-958.doi:10.1016/j.biopsych.2008.10.017.
    [12]GUO X,WANG Z,LI K,et al.Voxel-based assessment of gray and white matter volumes in Alzheimer's disease[J].Neuroscience Letters,2010,468(2):146-150.doi:10.1016/j.neulet.2009.10.086.
    [13]YE B S,SEO S W,KIM C H,et al.Hippocampal and cortical atrophy in amyloid-negative mild cognitive impairments:comparison with amyloid-positive mild cognitive impairment[J].Neurobiology of Aging,2014,35(2):291-300.doi:10.1016/j.neurobiolaging.2013.08.017.
    [14]SORENSEN L,LGEL C,LIV-HANSEN N,et al.Early detection of Alzheimer's disease using MRI hippocampal texture[J].Human Brain Mapping,2016,37(3):1148-1161.doi:10.1002/hbm.23091.
    [15]ORENSEN L,LGEL C,PAI A,et al.Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness,hippocampal shape,hippocampal texture,and volumetry[J].Neuroimage Clinical,2017,(13):470-482.doi:10.1016/j.nicl.2016.11.025.
    [16]AERTS H J,VELAZQUEZ E R,LEIJENAAR R T,et al.Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach[J].Nature Communications,2014,5(1):4006.doi:10.1038/ncomms5006.
    [17]FENG F,WANG P,ZHAO K,et al.Radiomic features of hippocampal subregions in Alzheimer’s disease and amnestic mild cognitive impairment[J].Frontiers in Aging Neuroscience,2018(10):290.doi:10.3389/fnagi.2018.00290.
    [18]HAO Y F,WANG T Y,ZHANG X Q,et al.Local Label Learning(LLL)for subcortical structure segmentation:application to hippocampus segmentation[J].Human Brain Mapping,2014,35(6):2674-2697.doi:10.1002/hbm.22359.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700