通过多窗口对比学习,提升心电图自监督表征的效率与准确性。
Learning ECG Representations via Poly-Window Contrastive Learning
- 从单个心电图中提取多个时间窗构建正样本对,增强时序结构利用。
- 在PTB-XL数据集上实现更高准确率(AUROC 0.891)且训练耗时减少14.8%。
- 适合需要高效训练基础模型的医学时序数据分析场景。
心电图分析是心血管疾病诊断的基础,但深度学习模型性能常受限于标注数据稀缺。自监督对比学习已成为从无标签信号中学习鲁棒心电图表征的有效方法。然而,现有方法多仅生成成对增强视图,未能充分利用心电图记录中的丰富时序结构。本文提出一种多窗口对比学习框架:从每个心电图实例中提取多个时间窗,构造正样本对并通过统计方法最大化其一致性。受慢特征分析原理启发,该方法显式鼓励模型学习跨时间保持不变且具有生理意义的特征。在PTB-XL数据集上的大量实验和消融研究验证了该方法的有效性。结果表明,多窗口对比学习在多标签超类分类任务中持续优于传统双视图方法,实现更高的AUROC(0.891 vs. 0.888)和F1分数(0.680 vs. 0.679),同时预训练所需周期减少至四分之一(32 vs. 128),总训练时间减少14.8%。尽管每样本处理多个窗口,仍显著降低训练周期与计算开销,使其适用于基础模型训练。通过广泛消融分析,确定了最优设计选择,并证明其对多种超参数的鲁棒性。这些发现确立了多窗口对比学习在自动化心电图分析中的高效可扩展性,为生物医学时序数据的自监督表征学习提供通用框架。
原文摘要 · Abstract (English)
Electrocardiogram (ECG) analysis is foundational for cardiovascular disease diagnosis, yet the performance of deep learning models is often constrained by limited access to annotated data. Self-supervised contrastive learning has emerged as a powerful approach for learning robust ECG representations from unlabeled signals. However, most existing methods generate only pairwise augmented views and fail to leverage the rich temporal structure of ECG recordings. In this work, we present a poly-window contrastive learning framework. We extract multiple temporal windows from each ECG instance to construct positive pairs and maximize their agreement via statistics. Inspired by the principle of slow feature analysis, our approach explicitly encourages the model to learn temporally invariant and physiologically meaningful features that persist across time. We validate our approach through extensive experiments and ablation studies on the PTB-XL dataset. Our results demonstrate that poly-window contrastive learning consistently outperforms conventional two-view methods in multi-label superclass classification, achieving higher AUROC (0.891 vs. 0.888) and F1 scores (0.680 vs. 0.679) while requiring up to four times fewer pre-training epochs (32 vs. 128) and 14.8% in total wall clock pre-training time reduction. Despite processing multiple windows per sample, we achieve a significant reduction in the number of training epochs and total computation time, making our method practical for training foundational models. Through extensive ablations, we identify optimal design choices and demonstrate robustness across various hyperparameters. These findings establish poly-window contrastive learning as a highly efficient and scalable paradigm for automated ECG analysis and provide a promising general framework for self-supervised representation learning in biomedical time-series data.
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。