Laboratory of Brain and Cognition, National Institute of Mental Health, National Institutes of Health, Bethesda, MD, USA.
Neuroimage. 2010 Oct 15;53(1):103-18. doi: 10.1016/j.neuroimage.2010.05.051. Epub 2010 May 23.
A popular method for investigating whether stimulus information is present in fMRI response patterns is to attempt to "decode" the stimuli from the response patterns with a multivariate classifier. The sensitivity for detecting the information depends on the particular classifier used. However, little is known about the relative performance of different classifiers on fMRI data. Here we compared six multivariate classifiers and investigated how the response-amplitude estimate used (beta- or t-value) and different pattern normalizations affect classification performance. The compared classifiers were a pattern-correlation classifier, a k-nearest-neighbors classifier, Fisher's linear discriminant, Gaussian naïve Bayes, and linear and nonlinear (radial-basis-function kernel) support vector machines. We compared these classifiers' accuracy at decoding the category of visual objects from response patterns in human early visual and inferior temporal cortex acquired in an event-related design with BOLD fMRI at 3T using SENSE and isotropic voxels of about 2-mm width. Overall, Fisher's linear discriminant (with an optimal-shrinkage covariance estimator) and the linear support vector machine performed best. The pattern-correlation classifier often performed similarly as those two classifiers. The nonlinear classifiers never performed better and sometimes significantly worse than the linear classifiers, suggesting overfitting. Defining response patterns by t-values (or in error-standard-deviation units) rather than by beta estimates (in % signal change) to define the patterns appeared advantageous. Cross-validation by a leave-one-stimulus-pair-out method gave higher accuracies than a leave-one-run-out method, suggesting that generalization to independent runs (which more safely ensures independence of the test set) is more challenging than generalization to novel stimuli within the same category. Independent selection of fewer more visually responsive voxels tended to yield better decoding performance for all classifiers. Normalizing mean and standard deviation of the response patterns either across stimuli or across voxels had no significant effect on decoding performance. Overall our results suggest that linear decoders based on t-value patterns may perform best in the present scenario of visual object representations measured for about 60min per subject with 3T fMRI.
一种研究刺激信息是否存在于 fMRI 反应模式中的常用方法是尝试使用多元分类器“解码”反应模式中的刺激。检测信息的敏感性取决于所使用的特定分类器。然而，关于不同分类器在 fMRI 数据上的相对性能知之甚少。在这里，我们比较了六种多元分类器，并研究了所使用的响应幅度估计（β 或 t 值）和不同的模式归一化如何影响分类性能。比较的分类器是模式相关分类器、k 最近邻分类器、Fisher 的线性判别、高斯朴素贝叶斯、线性和非线性（径向基函数核）支持向量机。我们比较了这些分类器在解码来自人类早期视觉和下颞叶皮质的与 BOLD fMRI 相关的反应模式中视觉对象类别的准确性，该研究使用 3T 上的 SENSE 和各向同性体素（宽度约为 2 毫米）进行了事件相关设计。总体而言，Fisher 的线性判别（具有最优收缩协方差估计）和线性支持向量机表现最好。模式相关分类器的表现通常与这两个分类器相似。非线性分类器的表现从未优于线性分类器，有时甚至明显差于线性分类器，这表明存在过拟合。与通过定义模式的 t 值（或以误差标准差单位）而不是通过定义模式的β估计（以信号变化的百分比）相比，通过定义模式的 t 值似乎更有利。通过一种留下一对刺激的方法进行交叉验证比留下一次运行的方法给出更高的准确性，这表明对独立运行的泛化（更安全地确保测试集的独立性）比在同一类别中对新刺激的泛化更具挑战性。独立选择较少的更具视觉响应的体素往往会提高所有分类器的解码性能。无论在刺激之间还是体素之间对响应模式的均值和标准差进行归一化对解码性能都没有显著影响。总体而言，我们的结果表明，基于 t 值模式的线性解码器在当前的视觉对象表示场景中可能表现最佳，该场景是使用 3T fMRI 为每个受试者测量约 60 分钟的结果。
