在隐私约束下用于癫痫发作检测的联邦少样本学习
Federated Few-Shot Learning for Epileptic Seizure Detection Under Privacy Constraints
AI总结：
本文提出了一种联邦少样本学习框架，用于在隐私约束下实现个性化EEG癫痫发作检测，通过两阶段方法提升模型性能。
摘要：
许多深度学习方法已开发用于基于EEG的发作检测；然而，大多数方法依赖于访问大型集中化标注数据集。在临床实践中，EEG数据通常稀缺，患者数据分布于不同机构，并受严格隐私法规约束，禁止数据汇总。因此，在现实医疗环境中创建可用的AI基于发作检测模型仍具有挑战性。为了解决这些限制，我们提出了一种两阶段联邦少样本学习（FFSL）框架，用于个性化EEG基于发作检测。该方法在TUH事件语料库上进行训练和评估，该语料库包含六个EEG事件类别。在第一阶段，通过联邦学习对预训练的生物信号转换器（BIOT）进行微调，跨非独立同分布的模拟医院站点进行训练，从而实现共享表示学习，而无需集中EEG记录。在第二阶段，联邦少样本个性化将分类器适应到每个患者，仅使用五个标注的EEG段，保留发作特定信息，同时仍能受益于跨站点知识。联邦微调实现了平衡准确率为0.43（集中化：0.52），Cohen's kappa为0.42（0.49），加权F1为0.69（0.74）。在FFSL阶段，客户端特定模型在四个具有异质事件分布的站点上实现了平均平衡准确率为0.77，Cohen's kappa为0.62，加权F1为0.73。这些结果表明，FFSL可以在现实的数据可用性和隐私约束下支持有效的患者自适应发作检测。
英文摘要：
Many deep learning approaches have been developed for EEG-based seizure detection; however, most rely on access to large centralized annotated datasets. In clinical practice, EEG data are often scarce, patient-specific distributed across institutions, and governed by strict privacy regulations that prohibit data pooling. As a result, creating usable AI-based seizure detection models remains challenging in real-world medical settings. To address these constraints, we propose a two-stage federated few-shot learning (FFSL) framework for personalized EEG-based seizure detection. The method is trained and evaluated on the TUH Event Corpus, which includes six EEG event classes. In Stage 1, a pretrained biosignal transformer (BIOT) is fine-tuned across non-IID simulated hospital sites using federated learning, enabling shared representation learning without centralizing EEG recordings. In Stage 2, federated few-shot personalization adapts the classifier to each patient using only five labeled EEG segments, retaining seizure-specific information while still benefiting from cross-site knowledge. Federated fine-tuning achieved a balanced accuracy of 0.43 (centralized: 0.52), Cohen's kappa of 0.42 (0.49), and weighted F1 of 0.69 (0.74). In the FFSL stage, client-specific models reached an average balanced accuracy of 0.77, Cohen's kappa of 0.62, and weighted F1 of 0.73 across four sites with heterogeneous event distributions. These results suggest that FFSL can support effective patient-adaptive seizure detection under realistic data-availability and privacy constraints.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
