Model sparsity and brain pattern interpretation of classification models in neuroimaging
Model sparsity and brain pattern interpretation of classification models in neuroimaging
复制标题
DOI：
10.1016/j.patcog.2011.09.011
复制
发表时间：
2012-06-01
影响因子：
8
通讯作者：
Strother, Stephen C.
中科院分区：
文献类型：
--
作者：
Rasmussen, Peter M.;Hansen, Lars K.;Strother, Stephen C.
将判别性多元分析技术应用于功能神经影像数据分析的兴趣日益浓厚。模型解释在神经影像学背景下非常重要，并且通常基于从分类模型导出的“脑图”。在本研究中，我们重点关注模型正则化参数选择对模型泛化、从分类模型中提取的空间模式的可靠性以及所得模型识别定义实验底层神经编码的相关大脑网络的能力的相对影响。对于支持向量机、逻辑回归和 Fisher 判别分析，我们证明模型正则化参数的选择对 l(2) 和 l(1) 正则化模型的泛化性、再现性和可解释稀疏性具有强烈但一致的影响。重要的是，我们说明了模型空间再现性和预测准确性之间的权衡。我们表明，在单独使用 l(2) 和/或 l(1) 正则化来追求分类精度最大化时，可以忽略大脑网络的已知部分。这支持了这样一种观点，即从模型中提取的空间模式的质量不能仅仅通过关注预测准确性来评估。相反，我们的结果表明必须仔细选择模型正则化参数，以便模型及其可视化增强我们解释大脑的能力。 (C) 2011 Elsevier Ltd. 保留所有权利。
Interest is increasing in applying discriminative multivariate analysis techniques to the analysis of functional neuroimaging data. Model interpretation is of great importance in the neuroimaging context, and is conventionally based on a 'brain map' derived from the classification model. In this study we focus on the relative influence of model regularization parameter choices on both the model generalization, the reliability of the spatial patterns extracted from the classification model, and the ability of the resulting model to identify relevant brain networks defining the underlying neural encoding of the experiment. For a support vector machine, logistic regression and Fisher's discriminant analysis we demonstrate that selection of model regularization parameters has a strong but consistent impact on the generalizability and both the reproducibility and interpretable sparsity of the models for both l(2) and l(1) regularization. Importantly, we illustrate a trade-off between model spatial reproducibility and prediction accuracy. We show that known parts of brain networks can be overlooked in pursuing maximization of classification accuracy alone with either l(2) and/or l(1) regularization. This supports the view that the quality of spatial patterns extracted from models cannot be assessed purely by focusing on prediction accuracy. Our results instead suggest that model regularization parameters must be carefully selected, so that the model and its visualization enhance our ability to interpret the brain. (C) 2011 Elsevier Ltd. All rights reserved.