用深度学习去除脑电图中的磁共振伪影，提升信号质量。
Deep Learning for Gradient and BCG Artifacts Removal in EEG During Simultaneous fMRI
- 用1D卷积自编码器直接学习噪声到干净信号的映射。
- 相比传统方法，信噪比提升14.63 dB，RMSE降低至0.0218。
- 模型可解释性强，适合实时脑电伪影处理应用。
同步脑电-磁共振成像结合了高时间与空间分辨率，用于追踪神经活动。然而，其应用受限于磁共振引起的伪影，尤其是梯度伪影（GA）和搏动性心脏伪影（BCG）。为此，本文提出一种去噪自编码器（DAR），基于CWL EEG-fMRI数据集中的含伪影与校正后脑电信号配对数据，采用1D卷积自编码器学习从噪声信号到清晰信号的直接映射。相较于主成分分析（PCA）、独立成分分析（ICA）、平均伪影减除（AAS）和小波阈值法，DAR表现更优：均方根误差（RMSE）为0.0218 ± 0.0152，结构相似性指数（SSIM）达0.8885 ± 0.0913，信噪比增益14.63 dB。配对t检验显示差异显著（p<0.001；Cohen's d>1.2）。留一被试交叉验证表明模型泛化良好，未见被试的平均RMSE为0.0635 ± 0.0110，SSIM为0.6658 ± 0.0880。此外，基于显著性的可视化揭示了伪影密集区域，增强了决策可解释性。结果表明，DAR是同步脑电-磁共振中实时伪影去除的可行且可解释的解决方案。
原文摘要 · Abstract (English)
Simultaneous EEG-fMRI recording combines high temporal and spatial resolution for tracking neural activity. However, its usefulness is greatly limited by artifacts from magnetic resonance (MR), especially gradient artifacts (GA) and ballistocardiogram (BCG) artifacts, which interfere with the EEG signal. To address this issue, we used a denoising autoencoder (DAR), a deep learning framework designed to reduce MR-related artifacts in EEG recordings. Using paired data that includes both artifact-contaminated and MR-corrected EEG from the CWL EEG-fMRI dataset, DAR uses a 1D convolutional autoencoder to learn a direct mapping from noisy to clear signal segments. Compared to traditional artifact removal methods like principal component analysis (PCA), independent component analysis (ICA), average artifact subtraction (AAS), and wavelet thresholding, DAR shows better performance. It achieves a root-mean-squared error (RMSE) of 0.0218 $\pm$ 0.0152, a structural similarity index (SSIM) of 0.8885 $\pm$ 0.0913, and a signal-to-noise ratio (SNR) gain of 14.63 dB. Statistical analysis with paired t-tests confirms that these improvements are significant (p<0.001; Cohen's d>1.2). A leave-one-subject-out (LOSO) cross-validation protocol shows that the model generalizes well, yielding an average RMSE of 0.0635 $\pm$ 0.0110 and an SSIM of 0.6658 $\pm$ 0.0880 across unseen subjects. Additionally, saliency-based visualizations demonstrate that DAR highlights areas with dense artifacts, which makes its decisions easier to interpret. Overall, these results position DAR as a potential and understandable solution for real-time EEG artifact removal in simultaneous EEG-fMRI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。