让心电图重建更懂病灶，提升跨患者泛化能力
Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction
- 引入病理先验约束潜在空间，学习病理性特征
- 在PTB-XL上相比最优模型RMSE降低76%
- 适合需要高精度、通用性强的心电图重建场景
从有限导联重构12导联心电图是因解剖差异导致的病态逆问题。传统深度学习方法常忽略心脏病变，丢失胸导联关键形态。本文提出病理感知多视角对比学习框架，通过病理流形正则化潜在空间。架构融合高保真时域波形与基于监督对比对齐学习的病理嵌入，通过最大化潜在表示与临床标签间的互信息，实现对解剖“干扰”变量的过滤。在PTB-XL数据集上，该方法在无患者依赖设置下相较现有最优模型，RMSE降低约76%。跨数据集评估在PTB诊断数据库上验证了优越泛化能力，弥合了硬件便携性与诊断级重建之间的差距。
原文摘要 · Abstract (English)
Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction.
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。