IntroductionA challenge when applying an artificial intelligence (AI) deep learning (DL) approach to novel electroencephalography (EEG) data, is the DL architecture's lack of adaptability to changing numbers of EEG channels. That is, the number of channels cannot vary neither in the training data, nor upon deployment. Such highly specific hardware constraints put major limitations on the clinical usability and scalability of the DL models.MethodsIn this work, we propose a technique for handling such varied numbers of EEG channels by splitting the EEG montages into distinct regions and merge the channels within the same region to a region representation. The solution is termed Region Based Pooling (RBP). The procedure of splitting the montage into regions is performed repeatedly with different region configurations, to minimize potential loss of information. As RBP maps a varied number of EEG channels to a fixed number of region representations, both current and future DL architectures may apply RBP with ease. To demonstrate and evaluate the adequacy of RBP to handle a varied number of EEG channels, sex classification based solely on EEG was used as a test example. The DL models were trained on 129 channels, and tested on 32, 65, and 129-channels versions of the data using the same channel positions scheme. The baselines for comparison were zero-filling the missing channels and applying spherical spline interpolation. The performances were estimated using 5-fold cross validation.ResultsFor the 32-channel system version, the mean AUC values across the folds were: RBP (93.34%), spherical spline interpolation (93.36%), and zero-filling (76.82%). Similarly, on the 65-channel system version, the performances were: RBP (93.66%), spherical spline interpolation (93.50%), and zero-filling (85.58%). Finally, the 129-channel system version produced the following results: RBP (94.68%), spherical spline interpolation (93.86%), and zero-filling (91.92%).ConclusionIn conclusion, RBP obtained similar results to spherical spline interpolation, and superior results to zero-filling. We encourage further research and development of DL models in the cross-dataset setting, including the use of methods such as RBP and spherical spline interpolation to handle a varied number of EEG channels.

中文翻译：

---

引入基于区域的池化来处理深度学习模型的各种 EEG 通道

简介将人工智能 (AI) 深度学习 (DL) 方法应用于新型脑电图 (EEG) 数据时面临的挑战是 DL 架构缺乏对不断变化的 EEG 通道数量的适应性。也就是说，通道的数量既不能在训练数据中变化，也不能在部署时变化。这种高度特定的硬件限制对 DL 模型的临床可用性和可扩展性造成了重大限制。方法在这项工作中，我们提出了一种通过将 EEG 蒙太奇分成不同区域并将通道合并到同一区域中来处理如此不同数量的 EEG 通道的技术。区域到区域表示。该解决方案被称为基于区域的池化（RBP）。使用不同的区域配置重复执行将蒙太奇分割成区域的过程，以最大程度地减少潜在的信息丢失。由于 RBP 将不同数量的 EEG 通道映射到固定数量的区域表示，因此当前和未来的 DL 架构都可以轻松应用 RBP。为了证明和评估 RBP 处理不同数量 EEG 通道的充分性，仅基于 EEG 的性别分类被用作测试示例。深度学习模型在 129 个通道上进行训练，并使用相同的通道位置方案在 32、65 和 129 通道版本的数据上进行测试。用于比较的基线是对缺失通道进行零填充并应用球面样条插值。使用 5 倍交叉验证来估计性能。结果对于 32 通道系统版本，跨倍数的平均 AUC 值为：RBP (93.34%)、球面样条插值 (93.36%) 和零填充 (76.82%) 。同样，在65通道系统版本上，性能分别为：RBP（93.66%）、球面样条插值（93.50%）和零填充（85.58%）。最终，129通道系统版本产生了以下结果：RBP（94.68％）、球面样条插值（93.86％）和零填充（91.92％）。结论综上所述，RBP获得了与球面样条插值相似的结果，并且优于球面样条插值。结果为零填充。我们鼓励在跨数据集设置中进一步研究和开发深度学习模型，包括使用 RBP 和球面样条插值等方法来处理不同数量的 EEG 通道。