LaConte Stephen, Strother Stephen, Cherkassky Vladimir, Anderson Jon, Hu Xiaoping
Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, 30322, USA.
Neuroimage. 2005 Jun;26(2):317-29. doi: 10.1016/j.neuroimage.2005.01.048. Epub 2005 Mar 24.
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, 10-27; 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.
本文探讨了支持向量机（SVM）分类在组块设计功能磁共振成像（fMRI）中的应用，扩展了我们之前使用线性判别分析的工作[拉康特，S.，安德森，J.，穆利，S.，阿什，J.，弗鲁蒂格，S.，雷姆，K.，汉森，L.K.，亚库布，E.，胡，X.，罗滕伯格，D.，斯特罗瑟，S.，2003a。使用NPAIRS性能指标评估单受试者BOLD fMRI中的预处理选择。《神经影像学》18卷，第10 - 27页；斯特罗瑟，S.C.，安德森，J.，汉森-拉森，L.K.，克耶姆斯，U.，库斯特拉，R.，西迪蒂斯，J.，弗鲁蒂格，S.，穆利，S.，拉康特，S.，罗滕伯格，D.，2002。功能神经成像实验的定量评估：NPAIRS数据分析框架。《神经影像学》15卷，第747 - 771页]。我们通过检验每种方法对由空间平滑、时间去趋势和运动校正组成的十种预处理选择组合的相对敏感性，将支持向量机与典型变量分析（CVA）进行比较。在功能磁共振成像的背景下，对分类性能、模型解释和验证等问题的讨论很重要。由于支持向量机具有许多独特的特性，我们研究了支持向量模型在神经成像数据方面的解释。我们提出了四种从支持向量机模型中提取激活图的方法，并详细研究了其中一种。对于典型变量分析和支持向量机，我们对全脑数据的单个时间样本进行了分类，时间分辨率约为4秒，有30个切片，近30000个脑体素，未对扫描进行平均或进行先验特征选择。
