通过心跳级对比学习捕捉心电图局部形态特征
Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets
- 在心跳和节律两级进行软目标对比学习，更贴合心电信号连续特性
- 在多标签心律分类任务中达到基线模型93%性能，在分割任务上领先4%
- 适合需要精细心电图表征的医疗诊断与模型迁移场景
获取用于训练监督模型的标注心电图数据颇具挑战。对比学习（CL）已成为一种有前景的预训练方法，可在标注数据有限的情况下实现有效迁移学习。然而，现有对比学习框架或仅关注全局上下文，或未能利用心电图特有的属性。此外，这些方法依赖硬对比目标，难以充分捕捉心电信号特征相似性的连续性。本文提出Beat-SSL，一种在节奏级和心跳级均进行对比学习并使用软目标的框架。我们在两个下游任务上评估了预训练模型：1）全局心律评估的多标签分类；2）心电图分割，以检验其跨上下文学习表征的能力。通过消融实验与三种方法（包括一个心电图基础模型）比较，尽管该基础模型具备更广泛的预训练，Beat-SSL在多标签分类任务中达到其93%的性能，并在分割任务中超出所有其他方法4%。
原文摘要 · Abstract (English)
Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL frameworks either focus solely on global context or fail to exploit ECG-specific characteristics. Furthermore, these methods rely on hard contrastive targets, which may not adequately capture the continuous nature of feature similarity in ECG signals. In this paper, we propose Beat-SSL, a contrastive learning framework that performs dual-context learning through both rhythm-level and heartbeat-level contrasting with soft targets. We evaluated our pretrained model on two downstream tasks: 1) multilabel classification for global rhythm assessment, and 2) ECG segmentation to assess its capacity to learn representations across both contexts. We conducted an ablation study and compared the best configuration with three other methods, including one ECG foundation model. Despite the foundation model's broader pretraining, Beat-SSL reached 93% of its performance in multilabel classification task and surpassed all other methods in the segmentation task by 4%.
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。