Deep learning is advancing EEG processing for automated epileptic seizure detection and onset zone localization, yet its performance relies heavily on high-quality annotated training data. However, scalp EEG is susceptible to high noise levels, which in turn leads to imprecise annotations of the seizure timing and characteristics. This "label noise" presents a significant challenge in model training and generalization. In this paper, we introduce Bayesian UncertaiNty-aware Deep Learning (BUNDL), a novel algorithm that informs a deep learning model of label ambiguities, thereby enhancing the robustness of seizure detection systems. By integrating domain knowledge into an underlying Bayesian framework, we derive a novel KL-divergence-based loss function that capitalizes on uncertainty to better learn seizure characteristics from scalp EEG. Thus, BUNDL offers a straightforward and model-agnostic method for training deep neural networks with noisy training labels that does not add any parameters to existing architectures. Additionally, we explore the impact of improved detection system on the task of automated onset zone localization. We validate BUNDL using a comprehensive simulated EEG dataset and two publicly available datasets collected by Temple University Hospital (TUH) and Boston Children's Hospital (CHB-MIT). Results show that BUNDL consistently identifies noisy labels and improves the robustness of three base models under various label noise conditions. We also evaluate cross-site generalizability and quantify computational cost of all methods. Ultimately, BUNDL presents as a reliable method that can be seamlessly integrated with existing deep models used in clinical practice, enabling the training of trustworthy models for epilepsy evaluation.

翻译：深度学习正在推动脑电图（EEG）处理在自动癫痫发作检测与起始区定位方面的发展，但其性能在很大程度上依赖于高质量的标注训练数据。然而，头皮脑电图易受高水平噪声影响，进而导致对发作时间与特征的标注不精确。这种"标签噪声"对模型训练与泛化构成了重大挑战。本文提出贝叶斯不确定性感知深度学习（BUNDL），这是一种新颖的算法，旨在向深度学习模型传达标签的模糊性，从而增强癫痫检测系统的鲁棒性。通过将领域知识整合到基础的贝叶斯框架中，我们推导出一种基于KL散度的新型损失函数，该函数利用不确定性来更好地从头皮脑电图中学习癫痫特征。因此，BUNDL提供了一种简单且与模型无关的方法，用于在含有噪声训练标签的情况下训练深度神经网络，且无需为现有架构增加任何参数。此外，我们还探讨了改进的检测系统对自动起始区定位任务的影响。我们使用一个综合模拟脑电图数据集以及由天普大学医院（TUH）和波士顿儿童医院（CHB-MIT）收集的两个公开数据集对BUNDL进行了验证。结果表明，BUNDL能够持续识别噪声标签，并在多种标签噪声条件下提升三个基础模型的鲁棒性。我们还评估了跨站点泛化能力，并量化了所有方法的计算成本。最终，BUNDL展现为一种可靠的方法，能够无缝集成到临床实践中现有的深度模型中，从而为癫痫评估训练出可信赖的模型。