Chen Xu, Pereira Francisco, Lee Wayne, Strother Stephen, Mitchell Tom
Rotman Research Institute, Baycrest, Toronto, Ontario, Canada.
Hum Brain Mapp. 2006 May;27(5):452-61. doi: 10.1002/hbm.20243.
Predictive modeling of functional magnetic resonance imaging (fMRI) has the potential to expand the amount of information extracted and to enhance our understanding of brain systems by predicting brain states, rather than emphasizing the standard spatial mapping. Based on the block datasets of Functional Imaging Analysis Contest (FIAC) Subject 3, we demonstrate the potential and pitfalls of predictive modeling in fMRI analysis by investigating the performance of five models (linear discriminant analysis, logistic regression, linear support vector machine, Gaussian naive Bayes, and a variant) as a function of preprocessing steps and feature selection methods. We found that: (1) independent of the model, temporal detrending and feature selection assisted in building a more accurate predictive model; (2) the linear support vector machine and logistic regression often performed better than either of the Gaussian naive Bayes models in terms of the optimal prediction accuracy; and (3) the optimal prediction accuracy obtained in a feature space using principal components was typically lower than that obtained in a voxel space, given the same model and same preprocessing. We show that due to the existence of artifacts from different sources, high prediction accuracy alone does not guarantee that a classifier is learning a pattern of brain activity that might be usefully visualized, although cross-validation methods do provide fairly unbiased estimates of true prediction accuracy. The trade-off between the prediction accuracy and the reproducibility of the spatial pattern should be carefully considered in predictive modeling of fMRI. We suggest that unless the experimental goal is brain-state classification of new scans on well-defined spatial features, prediction alone should not be used as an optimization procedure in fMRI data analysis.
功能磁共振成像（fMRI）的预测建模有潜力通过预测脑状态来扩展提取的信息量，并增强我们对脑系统的理解，而不是强调标准的空间映射。基于功能成像分析竞赛（FIAC）受试者3的块数据集，我们通过研究五种模型（线性判别分析、逻辑回归、线性支持向量机、高斯朴素贝叶斯和一种变体）的性能作为预处理步骤和特征选择方法的函数，展示了fMRI分析中预测建模的潜力和陷阱。我们发现：（1）与模型无关，时间去趋势和特征选择有助于构建更准确的预测模型；（2）线性支持向量机和逻辑回归在最佳预测准确性方面通常比高斯朴素贝叶斯模型中的任何一个表现更好；（3）在相同模型和相同预处理的情况下，使用主成分在特征空间中获得的最佳预测准确性通常低于在体素空间中获得的准确性。我们表明，由于存在来自不同来源的伪影，仅高预测准确性并不能保证分类器正在学习一种可能有用可视化的脑活动模式，尽管交叉验证方法确实提供了对真实预测准确性的相当无偏估计。在fMRI的预测建模中，应仔细考虑预测准确性和空间模式可重复性之间的权衡。我们建议，除非实验目标是对具有明确空间特征的新扫描进行脑状态分类，否则仅预测不应用作fMRI数据分析中的优化程序。
