利用心脏周期对称性，实现高效无监督心电图表示学习
Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning
- 设计相位等变自监督目标，通过解剖几何构建固定传输算子
- 在PTB-XL上仅用100万参数即达顶尖方法诊断精度
- 适合关注心电图分析与生理可解释表征的研究者
生理过程的周期性结构为自监督表征学习提供了天然先验，而心脏周期则是一个定义明确的利用场景。本文推导出一种相位等变的自监督目标，并提出Winder——一种联合嵌入架构，将表征组织为相位不变坐标和相位旋转的谐波子空间。其传输算子为固定闭式解，基于周期几何而非学习得到，不引入额外参数。在冻结线性探测协议下评估PTB-XL数据集，Winder在约100万参数规模下达到当前最优自监督方法的诊断准确率，同时展现出相位等变的潜在几何结构。结果表明，显式编码心脏相位对称性可在保留诊断有用信息的同时，获得可读性强、参数高效且直接关联可测量生理量的潜在空间。
原文摘要 · Abstract (English)
The cyclic structure of physiological processes offers a natural prior for self-supervised representation learning, and the cardiac cycle provides a particularly well-defined setting in which to exploit it. We derive a phase-equivariant self-supervised objective and introduce Winder, a joint-embedding architecture that organises representations into phase-invariant coordinates and phase-rotating harmonic subspaces. Its transport operator is fixed and closed-form, derived from the cycle's geometry rather than learned, and adds no parameters. Evaluated on PTB-XL under a frozen linear-probe protocol, Winder attains diagnostic accuracy within the range reported by state-of-the-art self-supervised methods at a ~1 M parameter footprint, while exhibiting phase-equivariant latent geometry. These findings demonstrate that explicitly encoding cardiac-phase symmetry can preserve diagnostically useful information while yielding a latent geometry that is legible, parameter-efficient, and directly tied to a measurable physiological quantity.
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。