Angular Gaussian Supervised Contrastive Learning for Long-Tailed Electrocardiogram Arrhythmia Diagnosis
作者: Jin Dai, Qiuzhen Zhang, Chenyun Dai, Danmei Lan, Can Han
分类: cs.LG, cs.AI
发布日期: 2026-07-16
🔗 代码/项目: GITHUB
💡 一句话要点
提出Angular Gaussian监督对比学习以解决长尾心电图心律失常诊断问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 长尾学习 心电图 心律失常 监督对比学习 深度学习 自适应逻辑调整 形态增强
📋 核心要点
- 现有方法在处理长尾标签分布时,主要关注类别频率,未能有效应对ECG类别间的形态变异性。
- 论文提出的AG-SCL方法通过Angular Gaussian对比学习、Adaptive Logit Adjustment和尾部感知增强,提升了对罕见心律失常的诊断能力。
- 在PTB-XL和Noc-ECG数据集上,AG-SCL分别取得了0.838和0.918的平衡准确率,显著提高了对罕见心律失常的敏感性。
📝 摘要(中文)
长尾标签分布降低了深度学习在心电图(ECG)心律失常诊断中的可靠性,尤其是对于临床重要但罕见的异常。现有的重平衡和逻辑调整方法主要关注类别频率,而忽视了ECG类别间方向依赖的形态变异性。本研究提出了Angular Gaussian监督对比学习(AG-SCL),用于长尾多标签ECG诊断。AG-SCL将三个组件整合为一个统一框架:一个建模全协方差类别不确定性的Angular Gaussian对比分支、自适应逻辑调整以及生成形态保持视图的尾部感知增强。该方法在公共PTB-XL基准和包含141名受试者1317小时录音的夜间ECG数据集上进行了评估,AG-SCL在两个数据集上均取得了最佳的宏观性能。
🔬 方法详解
问题定义:本研究旨在解决长尾标签分布对心电图(ECG)心律失常诊断的影响,现有方法主要关注类别频率,未能有效处理不同类别间的形态变异性。
核心思路:AG-SCL通过整合Angular Gaussian对比学习、Adaptive Logit Adjustment和尾部感知增强,旨在提高对罕见心律失常的诊断能力,同时保持临床相关的特异性。
技术框架:AG-SCL的整体架构包括三个主要模块:Angular Gaussian对比分支用于建模类别不确定性,自适应逻辑调整用于学习标签状态特定的先验修正,尾部感知增强用于生成形态保持的视图。
关键创新:AG-SCL的关键创新在于结合了全协方差建模与自适应逻辑调整,显著提升了对罕见心律失常的敏感性,与传统方法相比,能够更好地处理形态变异性。
关键设计:在设计中,AG-SCL采用了单位归一化嵌入的全协方差模型,使用自适应逻辑调整来替代固定频率的边际,并通过尾部感知增强保护7-25 Hz的QRS主导带。
🖼️ 关键图片
📊 实验亮点
AG-SCL在PTB-XL数据集上实现了0.838的平衡准确率、0.709的敏感性和0.968的特异性,在Noc-ECG数据集上分别达到了0.918、0.889和0.947,尤其在罕见或形态不稳定的心律类别中表现出显著提升。
🎯 应用场景
该研究的潜在应用领域包括临床心电图分析、自动化心律失常检测和个性化医疗。AG-SCL方法能够提高对罕见心律失常的诊断准确性,具有重要的临床价值,未来可在智能医疗设备中得到广泛应用。
📄 摘要(原文)
Long-tailed label distributions reduce the reliability of deep learning for electrocardiogram (ECG) arrhythmia diagnosis, particularly for clinically important but rare abnormalities. Existing rebalancing and logit adjustment methods mainly address class frequency while overlooking direction-dependent morphological variability across ECG classes. This study proposes Angular Gaussian Supervised Contrastive Learning (AG-SCL) for long-tailed multi-label ECG diagnosis. AG-SCL integrates three components into a unified framework: an Angular Gaussian contrastive branch that models full-covariance class uncertainty on unit-normalized embeddings, Adaptive Logit Adjustment that learns bounded label-state-specific prior corrections instead of fixed frequency-based margins, and tail-aware augmentation that generates morphology-preserving views while protecting the 7-25 Hz QRS-dominant band. The method was evaluated on the public PTB-XL benchmark and a nocturnal ECG dataset comprising 1317 hours of recordings from 141 subjects. AG-SCL achieved the best macro-level performance on both datasets. On PTB-XL, it obtained a balanced accuracy of 0.838, sensitivity of 0.709, specificity of 0.968, mean average precision of 0.495, and TPR at 5% FPR of 0.778. On Noc-ECG, the corresponding values were 0.918, 0.889, 0.947, 0.488, and 0.900. The largest gains occurred in rare or morphologically unstable rhythm classes, while ablation studies confirmed the contributions of full-covariance modelling, Adaptive Logit Adjustment, and tail-aware augmentation. AG-SCL improves long-tailed ECG diagnosis by combining prior calibration with anisotropic representation learning, enhancing sensitivity to rare arrhythmias while maintaining clinically relevant specificity. Our code is available at: https://github.com/Open-EXG/AG-SCL-for-Long-Tailed-ECG.