Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data.
Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data.
复制标题
DOI：
10.1016/j.neuroimage.2011.09.085
复制
发表时间：
2012-02-01
期刊：
影响因子：
5.7
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
中科院分区：
文献类型：
--
作者：
Cho Y;Seong JK;Jeong Y;Shin SY;Alzheimer's Disease Neuroimaging Initiative
通过磁共振结构成像测量的大脑萎缩已被用作诊断阿尔茨海默氏病的重要生物标志物（AD）。由于大脑萎缩的复杂和可变模式，我们需要大量的结构数据。 ，采用多种谐波变换。基于增量学习的分类。通过反映其空间变化的同时，可以通过过滤皮质厚度的高频成分来实现噪声的稳健性。我们的方法将AD患者与健康对照组（HC）区分为82％的敏感性和93％的特异性。此外，具有63％的敏感性和76％的特异性。 ，它支持我们方法在AD诊断和AD预测中的歧视能力。
Patterns of brain atrophy measured by magnetic resonance structural imaging have been utilized as significant biomarkers for diagnosis of Alzheimer’s disease (AD). However, brain atrophy is variable across patients and is non-specific for AD in general. Thus, automatic methods for AD classification require a large number of structural data due to complex and variable patterns of brain atrophy. In this paper, we propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. In general, methods based on region-wise features poorly reflect the detailed spatial variation of cortical thickness, and those based on vertex-wise features are sensitive to noise. Adopting a vertex-wise cortical thickness representation, our method can still achieve robustness to noise by filtering out high frequency components of the cortical thickness data while reflecting their spatial variation. This compromise leads to high accuracy in AD classification. We utilized MR volumes provided by Alzheimer’s Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82% sensitivity and 93% specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18 month, from non-converted MCI subjects with 63% sensitivity and 76% specificity. Moreover, it showed that the entorhinal cortex was the most discriminative region for classification, which is consistent with previous pathological findings. In comparison with other classification methods, our method demonstrated high classification performance in the both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.
登录
查看更多内容
影响因子：
3.7
作者：
Dickerson, Bradford C.;Bakkour, Akram;Salat, David H.;Feczko, Eric;Pacheco, Jenni;Greve, Douglas N.;Grodstein, Fran;Wright, Christopher I.;Blacker, Deborah;Rosas, H. Diana;Sperling, Reisa A.;Atri, Alireza;Growdon, John H.;Hyman, Bradley T.;Morris, John C.;Fischl, Bruce;Buckner, Randy L.
通讯作者：
Buckner, Randy L.
DOI：
10.1093/brain/awp123
发表时间：
2009-08
期刊：
Brain : a journal of neurology
影响因子：
--
作者：
Desikan RS;Cabral HJ;Hess CP;Dillon WP;Glastonbury CM;Weiner MW;Schmansky NJ;Greve DN;Salat DH;Buckner RL;Fischl B;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
19.7
作者：
Colliot, Olivier;Chetelat, Gael;Lehericy, Stephane
通讯作者：
Lehericy, Stephane
影响因子：
4.7
作者：
Hall, P;Marshall, D;Martin, R
通讯作者：
Martin, R
影响因子：
14
作者：
Bain, Lisa J.;Jedrziewski, Kathy;Morrison-Bogorad, Marcelle;Albert, Marilyn;Cotman, Carl;Hendrie, Hugh;Trojanowski, John Q.
通讯作者：
Trojanowski, John Q.