Support vector machines for temporal classification of block design fMRI data
Support vector machines for temporal classification of block design fMRI data
复制标题
DOI：
10.1016/j.neuroimage.2005.01.048
复制
发表时间：
2005-06-01
期刊：
影响因子：
5.7
通讯作者：
Hu, XP
中科院分区：
文献类型：
--
作者：
LaConte, S;Strother, S;Hu, XP
本文将支持向量机（SVM）分类应用于块设计fMRI，扩展了我们以前的工作与线性判别分析[LaConte，S.，安德森，J.，Muley，S.，Ashe，J.，Frutiger，S.，雷姆，K.，汉森，L.K.，Yacoub，E.，Hu，X.，Rottenberg，D.，Strother，S.，2003年a。使用NPAIRS性能指标评价单受试者BOLD fMRI的预处理选择。NeuroImage 18，1027; Strother，S.C.，安德森，J.，汉森，L.K.，Kjems，U.，库斯特拉河，Siditis，J.，Frutiger，S.，Muley，S.，LaConte，S.，Rottenberg，D.，2002.功能神经影像学实验的定量评价：NPAIRS数据分析框架。NeuroImage 15，747-771]。我们比较SVM的典型变量分析（CVA），通过检查每种方法的相对灵敏度，包括空间平滑，时间去趋势和运动校正的预处理选择的10个组合。重要的讨论是分类性能的问题，模型的解释，并在功能磁共振成像的背景下进行验证。由于支持向量机有许多独特的属性，我们研究支持向量模型的解释与神经影像学数据。我们提出了四种从SVM模型中提取激活图的方法，并详细研究了其中一种方法。对于CVA和SVM，我们对全脑数据的单个时间样本进行了分类，TR大约为4秒，30个切片，近30，000个脑体素，没有平均扫描或先验特征选择。(c)2005年爱思唯尔公司All rights reserved.
This paper treats support vector machine (SVM) classification applied to block design fMRI, extending our previous work with linear discriminant analysis [LaConte, S., Anderson, J., Muley, S., Ashe, J., Frutiger, S., Rehm, K., Hansen, L.K., Yacoub, E., Hu, X., Rottenberg, D., Strother, S., 2003a. The evaluation of preprocessing choices in single-subject BOLD fMRI using NPAIRS performance metrics. NeuroImage 18, 1027; Strother, S.C., Anderson, J., Hansen, L.K., Kjems, U., Kustra, R., Siditis, J., Frutiger, S., Muley, S., LaConte, S., Rottenberg, D., 2002. The quantitative evaluation of functional neuroimaging experiments: the NPAIRS data analysis framework. NeuroImage 15, 747-771]. We compare SVM to canonical variates analysis (CVA) by examining the relative sensitivity of each method to ten combinations of preprocessing choices consisting of spatial smoothing, temporal detrending, and motion correction. Important to the discussion are the issues of classification performance, model interpretation, and validation in the context of fMRI. As the SVM has many unique properties, we examine the interpretation of support vector models with respect to neuroimaging data. We propose four methods for extracting activation maps from SVM models, and we examine one of these in detail. For both CVA and SVM, we have classified individual time samples of whole brain data, with TRs of roughly 4 s, thirty slices, and nearly 30,000 brain voxels, with no averaging of scans or prior feature selection. (c) 2005 Elsevier Inc. All rights reserved.