脑电年龄预测中的自动伪迹去除：系统比较

中文摘要 AI 辅助

自动脑电伪迹去除可能改善下游分析，但也可能改变预测信息。我们针对跨数据集脑电年龄预测，将九种自动伪迹去除方法与常见的无伪迹去除基线进行了基准比较。我们引入了信号质量指数（SQI）引导的GEDAI，该方法利用局部信号质量评估，将校正限制在需要干预的通道-epoch对上。在TUEG上训练了三种深度神经架构，并在不进行目标域适配的情况下，在ds005385、LEMON和TDBRAIN上进行了评估。在此设置下，GEDAI和SQI引导的GEDAI是唯一在所有数据集和架构上相对于基线在年龄预测性能上取得一致提升的方法（ΔMAE分别为-0.77/-0.64年，ΔR²分别为+0.083/+0.072）。其余方法平均而言是中性的或有害的（跨方法的ΔMAE=+0.22±0.16年，ΔR²=-0.023±0.016）。两种基于GEDAI的方法性能接近，而SQI引导将中位修改率从74.78%降至42.80%。这些发现表明，数据整理的收益依赖于方法，并确立了SQI引导作为一种更具选择性的操作点，保留了更多原始脑电信号不变，限制了神经活动潜在损失，同时保留了GEDAI的大部分预测优势。

英文摘要

Automated EEG artifact removal may improve downstream analysis but can also alter predictive information. We benchmarked nine automated artifact removal methods against a common no-artifact-removal baseline for cross-dataset EEG age prediction. We introduce Signal Quality Index (SQI)-guided GEDAI, which leverages local signal-quality assessment to restrict correction to the channel--epoch pairs requiring intervention. Three deep neural architectures were trained on TUEG and evaluated without target-domain fitting on ds005385, LEMON, and TDBRAIN. Across this setting, GEDAI and SQI-guided GEDAI were the only methods with consistent gains over baseline in age prediction performance across all datasets and architectures ($Δ$MAE $=-0.77/-0.64$ years, $ΔR^2=+0.083/+0.072$, respectively). The remaining methods were neutral or detrimental on average ($Δ$MAE $=+0.22\pm0.16$ years, $ΔR^2=-0.023\pm0.016$ across methods). The two GEDAI-based methods achieved closely matched performance, while SQI guidance reduced the median modification ratio from $74.78\%$ to $42.80\%$. These findings show that curation benefits are method-dependent and establish SQI guidance as a more selective operating point, leaving more of the original EEG unchanged and limiting the potential loss of neural activity while retaining most of GEDAI's predictive benefit.

发表机构

• Yneuro

机构由 AI 辅助整理，请以论文原文为准。