发表机构
Westlake University; Hokkaido University; RIKEN（西湖大学; 北海道大学; 理化学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有测试时适应（TTA）方法在ECG分类任务中忽略节拍-节律结构、易受伪影影响的问题，提出BeatRhythm-TTA框架，通过SQI门控方案与双层次一致性提升性能，在多域ECG诊断中获2.70%的Macro-F1相对提升。
AI 中文摘要
用于心电图（ECG）分类的深度学习模型在部署到未知域时，由于采集设备和患者群体的变化，往往会出现显著的性能下降。测试时适应（TTA）通过仅使用推理时的无标签数据来适应模型，提供了一种实用的解决方案。然而，现有的TTA方法在ECG任务上常常表现不佳，因为简单的在线更新忽略了心动周期的分层节拍-节律结构，且容易受到信号伪影的影响，这会导致适应过程不稳定和模型漂移。我们提出了BeatRhythm-TTA，一种针对ECG定制的TTA框架，该框架在域偏移下明确考虑了ECG的噪声观测和结构化的节拍-节律语义。首先，为了处理普遍存在的ECG伪影，我们引入了信号质量指数（SQI）门控适应方案，该方案会选择性地过滤掉低质量信号，以防止有害的更新。其次，为了利用ECG的节拍-节律语义，我们强制实施双层次一致性，使模型在适应偏移的采集条件时保留节拍形态和节律动态。在三种适应协议下，使用PTB-XL作为源域、CPSC2018和Georgia作为两个目标域的多标签ECG诊断上进行的大量实验，证明了我们方法的有效性，与最佳的对比方法相比，在Macro-F1上平均实现了2.70%的相对提升。
英文摘要
Deep learning models for electrocardiogram (ECG) classification often suffer from significant performance degradation when deployed in unseen domains due to shifts in acquisition devices and patient populations. Test-time adaptation (TTA) offers a practical solution by adapting models using only unlabeled data at inference time. However, existing TTA methods often underperform on ECG tasks, since naive online updates ignore the hierarchical beat-rhythm structure of cardiac cycles and are vulnerable to signal artifacts, which leads to unstable adaptation and model drift. We propose BeatRhythm-TTA, an ECG-tailored TTA framework that explicitly accounts for ECG's noisy observations and structured beat-rhythm semantics under domain shift. First, to handle pervasive ECG artifacts, we introduce a Signal Quality Index (SQI)-gated adaptation scheme that selectively filters out low-quality signals to prevent harmful updates. Second, to leverage ECG's beat-rhythm semantics, we enforce dual-level consistency so the model preserves beat morphology and rhythm dynamics while adapting to shifted acquisition conditions. Extensive experiments on multi-label ECG diagnosis across three adaptation protocols, using PTB-XL as the source domain and CPSC2018/Georgia as two target domains, demonstrate the effectiveness of our method, yielding an average +2.70% relative improvement in Macro-F1 over the best competing method.
CommentsAccepted at MICCAI 2026
