Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK; Wellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UK; Christ Church, OX1 1DP, Oxford, UK.
Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK; Wellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UK.
Neuroimage. 2023 Nov 15;282:120396. doi: 10.1016/j.neuroimage.2023.120396. Epub 2023 Oct 5.
Multivariate pattern analysis (MVPA) of Magnetoencephalography (MEG) and Electroencephalography (EEG) data is a valuable tool for understanding how the brain represents and discriminates between different stimuli. Identifying the spatial and temporal signatures of stimuli is typically a crucial output of these analyses. Such analyses are mainly performed using linear, pairwise, sliding window decoding models. These allow for relative ease of interpretation, e.g. by estimating a time-course of decoding accuracy, but have limited decoding performance. On the other hand, full epoch multiclass decoding models, commonly used for brain-computer interface (BCI) applications, can provide better decoding performance. However interpretation methods for such models have been designed with a low number of classes in mind. In this paper, we propose an approach that combines a multiclass, full epoch decoding model with supervised dimensionality reduction, while still being able to reveal the contributions of spatiotemporal and spectral features using permutation feature importance. Crucially, we introduce a way of doing supervised dimensionality reduction of input features within a neural network optimised for the classification task, improving performance substantially. We demonstrate the approach on 3 different many-class task-MEG datasets using image presentations. Our results demonstrate that this approach consistently achieves higher accuracy than the peak accuracy of a sliding window decoder while estimating the relevant spatiotemporal features in the MEG signal.
多变量模式分析（MVPA）的脑磁图（MEG）和脑电图（EEG）数据是理解大脑如何表示和区分不同刺激的有价值的工具。识别刺激的空间和时间特征通常是这些分析的关键输出。这些分析主要使用线性、成对、滑动窗口解码模型进行。这些模型允许相对容易解释，例如通过估计解码准确性的时间过程，但解码性能有限。另一方面，常用于脑机接口（BCI）应用的全时段多类解码模型可以提供更好的解码性能。然而，此类模型的解释方法是针对少数类别设计的。在本文中，我们提出了一种方法，将多类全时段解码模型与有监督降维相结合，同时仍然能够使用置换特征重要性来揭示时空和频谱特征的贡献。至关重要的是，我们引入了一种在针对分类任务优化的神经网络中对输入特征进行有监督降维的方法，从而大大提高了性能。我们在 3 个不同的多类任务-MEG 数据集上使用图像呈现来演示该方法。我们的结果表明，与滑动窗口解码器的峰值准确性相比，该方法始终能够实现更高的准确性，同时估计 MEG 信号中的相关时空特征。
