发表机构
Yokohama National University; Yokohama City University Medical Center; Fukuda Denshi Co.,Ltd（横滨国立大学; 横滨市立大学医学中心; 福田电子株式会社）
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12导联ECG分析方法难以捕捉导联间依赖与全局模式的问题，提出Graph-CMMC框架，通过将ECG波形转换为GADF图像构建伪多模态表征，结合图关系模块建模导联间依赖，在冠状动脉闭塞分类任务上取得了有竞争力的性能。
AI 中文摘要
12导联心电图（ECG）是一种标准的非侵入性检查，广泛用于诊断冠状动脉疾病，临床解读依赖于对多导联间波形模式的比较。然而，大多数现有的ECG分析方法聚焦于单导联信号，或独立处理每个导联，通常使用卷积神经网络（CNNs）或循环神经网络（RNNs）将ECG信号作为一维时间序列数据处理。这类方法在建模局部波形变化方面虽有效，但难以捕捉临床诊断必需的导联间依赖关系和全局波形模式。为解决这一局限，我们提出一种名为Graph-CMMC的基于图的伪多模态对比学习框架。ECG波形被转换为格拉姆角差场（GADF）图像，以构建同一心脏活动的互补表征，从而形成伪多模态学习场景。Graph-CMMC利用全部12个导联，以自监督方式对齐波形与GADF表征，同时采用基于图的关系模块在对比学习过程中建模导联间依赖关系并强制导联间的结构一致性。在多标签冠状动脉闭塞分类任务上的实验结果表明，该框架相较于监督学习方法取得了具有竞争力的性能。这些结果进一步表明，将GADF用作互补表征，并在学习鲁棒的12导联ECG表征时纳入显式的基于图的导联间依赖关系建模是有效的。
英文摘要
12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. However, most existing ECG analysis methods focus on single-lead signals or treat each lead independently, and typically process ECG signals as one-dimensional time-series data using CNNs or RNNs. While effective in modeling local waveform changes, such approaches have difficulty capturing inter-lead dependency and global waveform patterns essential for clinical diagnosis. To address this limitation, we propose a graph-based pseudo-multimodal contrastive learning framework called Graph-CMMC. ECG waveforms are transformed into Gramian Angular Difference Field (GADF) images to construct complementary representations of the same cardiac activity, enabling a pseudo-multimodal learning setting. Using all 12 leads, Graph-CMMC aligns waveform and GADF representations in a self-supervised manner, while a graph-based relational module is employed to model inter-lead dependency and enforce structural consistency across leads during contrastive learning. Experimental results on a multi-label coronary artery occlusion classification task demonstrate that the proposed framework achieves competitive performance compared to supervised learning methods. These results further suggest the effectiveness of using GADF as a complementary representation and incorporating explicit graph-based modeling of inter-lead dependency for learning robust 12-lead ECG representations.
Comments7 pages, 7 figures. Presented at the 48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2026)
