Kernel regression for fMRI pattern prediction.
Kernel regression for fMRI pattern prediction.
复制标题
DOI：
10.1016/j.neuroimage.2010.03.058
复制
发表时间：
2011-05-15
期刊：
影响因子：
5.7
通讯作者：
Ashburner, John
中科院分区：
文献类型：
--
作者：
Chu, Carlton;Ni, Yizhao;Tan, Geoffrey;Saunders, Craig J.;Ashburner, John
关键词：
本文介绍了两种基于核的回归方案，用于解码或预测大脑功能扫描的大脑状态，作为2007年匹兹堡大脑活动解释竞赛（PBAIC）的一部分，我们的团队在该竞赛中获得了第一名。我们的程序涉及图像重新排列，空间平滑，低频漂移的去趋势化，以及多元线性和非线性核回归方法的应用：即核脊回归（KRR）和相关向量回归（RVR）。RVR基于贝叶斯框架，通过边际似然最大化自动确定稀疏解。KRR是脊回归的双重形式，它以一种计算效率高的方式解决了高维数据的回归问题。基于人类大脑功能先验知识的特征选择也被使用。采用约束反卷积和约束再卷积后处理进行预测。本文还详细描述了如何使用先验知识来微调特定“特征评级”的预测，我们认为这是我们预测准确性的关键因素之一。对预处理的影响也进行了评估，表明不同的预处理可能导致显著不同的精度。虽然最初的工作是针对PBAIC，但本文中描述的许多技术可以普遍应用于任何fMRI解码工作，以提高预测精度。
This paper introduces two kernel-based regression schemes to decode or predict brain states from functional brain scans as part of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) 2007, in which our team was awarded first place. Our procedure involved image realignment, spatial smoothing, detrending of low-frequency drifts, and application of multivariate linear and non-linear kernel regression methods: namely kernel ridge regression (KRR) and relevance vector regression (RVR). RVR is based on a Bayesian framework, which automatically determines a sparse solution through maximization of marginal likelihood. KRR is the dual-form formulation of ridge regression, which solves regression problems with high dimensional data in a computationally efficient way. Feature selection based on prior knowledge about human brain function was also used. Post-processing by constrained deconvolution and re-convolution was used to furnish the prediction. This paper also contains a detailed description of how prior knowledge was used to fine tune predictions of specific “feature ratings,” which we believe is one of the key factors in our prediction accuracy. The impact of pre-processing was also evaluated, demonstrating that different pre-processing may lead to significantly different accuracies. Although the original work was aimed at the PBAIC, many techniques described in this paper can be generally applied to any fMRI decoding works to increase the prediction accuracy.
登录
查看更多内容
影响因子：
3.7
作者：
Shinkareva SV;Mason RA;Malave VL;Wang W;Mitchell TM;Just MA
通讯作者：
Just MA
影响因子：
5.7
作者：
LaConte, S;Anderson, J;Strother, S
通讯作者：
Strother, S
影响因子：
5.7
作者：
Mouao-Miranda, Janaina;Friston, Karl J.;Brammer, Michael
通讯作者：
Brammer, Michael
影响因子：
5.7
作者：
LaConte, S;Strother, S;Hu, XP
通讯作者：
Hu, XP
影响因子：
5.7
作者：
Mourao-Miranda, Janaina;Reynaud, Emanuelle;Brammer, Michael
通讯作者：
Brammer, Michael