Department of Psychology, School of Arts and Sciences, University of Pennsylvania, Philadelphia, PA 19104, USA.
Marketing Department, Wharton School, University of Pennsylvania, PA 19104, USA.
Cell Rep Methods. 2022 Jun 6;2(6):100227. doi: 10.1016/j.crmeth.2022.100227. eCollection 2022 Jun 20.
Researchers often seek to decode mental states from brain activity measured with functional MRI. Rigorous decoding requires the use of formal neural prediction models, which are likely to be the most accurate if they use the whole brain. However, the computational burden and lack of interpretability of off-the-shelf statistical methods can make whole-brain decoding challenging. Here, we propose a method to build whole-brain neural decoders that are both interpretable and computationally efficient. We extend the partial least squares algorithm to build a regularized model with variable selection that offers a unique "fit once, tune later" approach: users need to fit the model only once and can choose the best tuning parameters post hoc. We show in real data that our method scales well with increasing data size and yields interpretable predictors. The algorithm is publicly available in multiple languages in the hope that interpretable whole-brain predictors can be implemented more widely in neuroimaging research.
研究人员通常试图从功能磁共振成像测量的大脑活动中解码心理状态。严格的解码需要使用正式的神经预测模型，如果这些模型使用整个大脑，那么它们很可能是最准确的。然而，现成的统计方法的计算负担和缺乏可解释性可能使全脑解码具有挑战性。在这里，我们提出了一种构建可解释且计算效率高的全脑神经解码器的方法。我们将偏最小二乘法扩展到建立具有变量选择的正则化模型，提供了一种独特的“一次拟合，后期调整”方法：用户只需拟合一次模型，然后可以事后选择最佳调整参数。我们在真实数据中表明，我们的方法可以很好地扩展到数据量的增加，并产生可解释的预测因子。该算法以多种语言提供，希望可解释的全脑预测因子可以在神经影像学研究中更广泛地实现。
