AI 中文总结
针对EEG疾病诊断中实例标签可靠性不均、受试者稀缺的问题，提出两阶段BridgeMIL框架，解耦实例表示学习与受试者级监督，在15种数据集-骨干网络设置中14种获最高准确率，总体较基线高4.28个百分点。
AI 中文摘要
基于EEG的疾病诊断要求每个受试者对应一次预测，而常规流程会将记录分割为短实例，为每个实例继承受试者标签并训练实例级分类器，该方法假设所有实例提供同等可靠的诊断证据。多实例学习（MIL）通过将每个受试者视为一个包来避免继承标签，但EEG数据集中的受试者数量远少于实例数量，可能会限制端到端MIL学习到的表示质量。我们提出BridgeMIL，这是一种将实例表示学习与受试者级监督解耦的两阶段框架。第一阶段，编码器在无继承实例标签的情况下进行预训练，通过对齐时间邻近窗口和独立采样的受试者内子包实现；方差和协方差正则化可防止崩溃并减少冗余，且无需负样本。第二阶段，将编码器迁移至基于注意力的MIL聚合器，仅对受试者预测应用监督，并通过特征保留限制表示漂移。在三个EEG疾病数据集和五个代表性骨干网络上，BridgeMIL在15种数据集-骨干网络设置中的14种达到最高平均准确率，总体平均准确率为76.57%，比最强基线高4.28个百分点。进一步分析显示，各实例的继承标签可靠性存在显著差异，模型性能对受试者稀缺性的敏感度高于对实例稀缺性的敏感度，且表示空间更具结构性，存在不同受试者簇，诊断类别间的分离度也有所提升。这些发现共同强调，在从大量EEG实例中学习时，需将监督与受试者级预测目标对齐，而非为单个实例分配疾病标签。
英文摘要
EEG-based disease diagnosis requires one prediction per subject, yet common pipelines segment recordings into short instances, inherit the subject label for every instance, and train instance-level classifiers. This assumes that all instances provide equally reliable diagnostic evidence. Multiple instance learning (MIL) avoids inherited labels by treating each subject as a bag. However, EEG datasets contain far fewer subjects than instances, which can limit the quality of the representations learned by end-to-end MIL. We propose BridgeMIL, a two-stage framework that decouples instance representation learning from subject-level supervision. Stage 1 pretrains the encoder without inherited instance labels by aligning temporally nearby windows and independently sampled within-subject sub-bags. Variance and covariance regularization prevent collapse and reduce redundancy without negative pairs. Stage 2 transfers the encoder to an attention-based MIL aggregator, applies supervision only to subject predictions, and limits representation drift through feature retention. Across three EEG disease datasets and five representative backbones, BridgeMIL attains the highest mean accuracy in 14 of 15 dataset-backbone settings and an overall mean accuracy of 76.57%, 4.28 percentage points higher than the strongest baseline. Further analyses reveal substantial variation in inherited-label reliability across instances, greater performance sensitivity to subject scarcity than to instance scarcity, and a more structured representation space with distinct subject-wise clusters and improved separation between diagnostic classes. Together, these findings underscore the importance of aligning supervision with the subject-level prediction objective while learning from abundant EEG instances without assigning disease labels to individual instances.
