用图神经网络和多尺度注意力提取高保真胎儿心电图，提升早筛准确率。
Graph-Based Spatio-temporal Attention and Multi-Scale Fusion for Clinically Interpretable, High-Fidelity Fetal ECG Extraction
- 融合图神经网络与多尺度Transformer，动态建模电极间时空关联
- 在低信噪比下仍达R2>0.99，RMSE=0.015，优于主流模型
- 可解释性强，结果符合生理规律，适合临床医生信任使用
先天性心脏病（CHD）是最常见的新生儿异常，亟需早期检测以改善预后。然而，腹部心电图（aECG）中的胎儿心电图（fECG）常被母体心电图和噪声掩盖，在低信噪比（SNR）条件下传统方法难以应对。本文提出FetalHealthNet（FHNet），一种结合图神经网络与多尺度增强型Transformer的深度学习框架，动态建模多导联间的时空相关性，实现高质量fECG提取。在基准aECG数据集上，FHNet持续优于长短期记忆（LSTM）、标准Transformer及当前最优模型，即使在严重噪声下仍保持R2>0.99，RMSE=0.015。可解释性分析揭示了具有生理意义的时间与导联贡献，增强了模型透明度与临床可信度。结果表明，该方法有望推动胎儿监测技术革新，实现早期CHD筛查，凸显下一代生物信号处理的变革潜力。
原文摘要 · Abstract (English)
Congenital Heart Disease (CHD) is the most common neonatal anomaly, highlighting the urgent need for early detection to improve outcomes. Yet, fetal ECG (fECG) signals in abdominal ECG (aECG) are often masked by maternal ECG and noise, challenging conventional methods under low signal-to-noise ratio (SNR) conditions. We propose FetalHealthNet (FHNet), a deep learning framework that integrates Graph Neural Networks with a multi-scale enhanced transformer to dynamically model spatiotemporal inter-lead correlations and extract clean fECG signals. On benchmark aECG datasets, FHNet consistently outperforms long short-term memory (LSTM) models, standard transformers, and state-of-the-art models, achieving R2>0.99 and RMSE = 0.015 even under severe noise. Interpretability analyses highlight physiologically meaningful temporal and lead contributions, supporting model transparency and clinical trust. FHNet illustrates the potential of AI-driven modeling to advance fetal monitoring and enable early CHD screening, underscoring the transformative impact of next-generation biomedical signal processing.
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。