arXiv:2411.00755cs.LG2024-11被引 5

用分层Transformer提升心电图诊断准确率

Hierarchical Transformer for Electrocardiogram Diagnosis

  • 分层结构融合深度卷积与多尺度特征
  • 通过CLS token实现跨导联关系建模
  • 轻量设计且增强模型可解释性

我们提出一种用于心电图分析的分层Transformer,结合深度卷积、基于CLS token的多尺度特征聚合以及注意力门控模块,以学习导联间的相互关系并提升可解释性。该模型轻量、灵活,无需复杂的注意力机制或下采样策略,有效提升心电图诊断性能。

原文摘要 · Abstract (English)

We propose a hierarchical Transformer for ECG analysis that combines depth-wise convolutions, multi-scale feature aggregation via a CLS token, and an attention-gated module to learn inter-lead relationships and enhance interpretability. The model is lightweight, flexible, and eliminates the need for complex attention or downsampling strategies.

心电图分析Transformer医疗AI

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。