FReM - Scalable and stable decoding with fast regularized ensemble of models
FReM - Scalable and stable decoding with fast regularized ensemble of models
复制标题
DOI：
10.1016/j.neuroimage.2017.10.005
复制
发表时间：
2018-10-15
期刊：
影响因子：
5.7
通讯作者：
Thirion, Bertrand
中科院分区：
文献类型：
--
作者：
Hoyos-Idrobo, Andres;Varoquaux, Gael;Thirion, Bertrand
大脑解码通过预测模型将行为与大脑活动联系起来。这些也被用来识别与观察到的行为相关的认知操作所涉及的大脑区域。训练这样的多变量模型是一个高维统计问题，需要合适的先验知识。最先进的先验-例如小的总变化-在地图上强制执行空间结构，以稳定它们并改善预测。然而，它们带来了巨大的计算成本。我们基于空间结构和模型集成的快速降维，以实现在大型数据集上快速的解码器，并提高预测和地图的稳定性。我们的方法，快速正则化模型集成（FReM），包括一个隐式的空间正则化，通过使用一个快速聚类算法的体素分组。此外，它还聚合了交叉验证循环的各个部分获得的不同估计量，每次都保持最佳模型。在大量脑成像数据集上的实验表明，体素聚类和模型集成的结合提高了解码图的稳定性，降低了预测精度的方差。重要的是，我们的方法需要比最先进的方法更少的样本来实现给定的预测精度。最后，FreM比其他空间正则化方法快得多，此外，它可以更好地利用并行计算资源。
Brain decoding relates behavior to brain activity through predictive models. These are also used to identify brain regions involved in the cognitive operations related to the observed behavior. Training such multivariate models is a high-dimensional statistical problem that calls for suitable priors. State of the art priors -eg small total-variation- enforce spatial structure on the maps to stabilize them and improve prediction. However, they come with a hefty computational cost. We build upon very fast dimension reduction with spatial structure and model ensembling to achieve decoders that are fast on large datasets and increase the stability of the predictions and the maps. Our approach, fast regularized ensemble of models (FReM), includes an implicit spatial regularization by using a voxel grouping with a fast clustering algorithm. In addition, it aggregates different estimators obtained across splits of a cross-validation loop, each time keeping the best possible model. Experiments on a large number of brain imaging datasets show that our combination of voxel clustering and model ensembling improves decoding maps stability and reduces the variance of prediction accuracy. Importantly, our method requires less samples than state-of-the-art methods to achieve a given level of prediction accuracy. Finally, FreM is much faster than other spatially-regularized methods and, in addition, it can better exploit parallel computing resources.