[论文解读] Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks

Moncef Gabbouj, Serkan Kıranyaz+6 more|arXiv (Cornell University)|Sep 30, 2021

ECG Monitoring and Analysis参考文献 49被引用 14

一句话总结

本文提出了一种一维自组织操作神经网络（Self-ONNs），并引入生成神经元，以实现低质量Holter ECG信号中R波峰的鲁棒检测。通过在训练过程中使每个神经元能够自组织生成最优操作符，该方法在CPSC-2020数据集上实现了最先进性能——F1分数达到99.10%，敏感度为99.79%，阳性预测值为98.42%，且计算复杂度显著低于深度一维卷积神经网络（1-D CNNs）。

ABSTRACT

Although numerous R-peak detectors have been proposed in the literature, their robustness and performance levels may significantly deteriorate in low-quality and noisy signals acquired from mobile electrocardiogram (ECG) sensors, such as Holter monitors. Recently, this issue has been addressed by deep 1-D convolutional neural networks (CNNs) that have achieved state-of-the-art performance levels in Holter monitors; however, they pose a high complexity level that requires special parallelized hardware setup for real-time processing. On the other hand, their performance deteriorates when a compact network configuration is used instead. This is an expected outcome as recent studies have demonstrated that the learning performance of CNNs is limited due to their strictly homogenous configuration with the sole linear neuron model. In this study, to further boost the peak detection performance along with an elegant computational efficiency, we propose 1-D Self-Organized ONNs (Self-ONNs) with generative neurons. The most crucial advantage of 1-D Self-ONNs over the ONNs is their self-organization capability that voids the need to search for the best operator set per neuron since each generative neuron has the ability to create the optimal operator during training. The experimental results over the China Physiological Signal Challenge-2020 (CPSC) dataset with more than one million ECG beats show that the proposed 1-D Self-ONNs can significantly surpass the state-of-the-art deep CNN with less computational complexity. Results demonstrate that the proposed solution achieves a 99.10% F1-score, 99.79% sensitivity, and 98.42% positive predictivity in the CPSC dataset, which is the best R-peak detection performance ever achieved.

研究动机与目标

• 解决现有R波峰检测器在噪声大、质量差的Holter ECG信号中鲁棒性差的问题。
• 克服当前用于ECG波峰检测的最先进深度一维卷积神经网络（1-D CNNs）带来的高计算复杂度问题。
• 通过引入异构、自组织的神经元，超越同质一维卷积神经网络的学习性能。
• 开发一种紧凑、高效且高度准确的神经网络架构，用于实时ECG分析。
• 在模型复杂度极低的前提下，实现在CPSC-2020数据集上的卓越检测性能。

提出的方法

• 所提出的方法采用一维自组织操作神经网络（Self-ONNs），并引入生成神经元，使其在训练过程中能够自主生成最优操作符。
• 每个生成神经元动态选择并组合操作（例如卷积、池化类操作），以最佳匹配输入信号，从而无需手动搜索操作符。
• 网络通过反向传播进行端到端训练，自组织机制使神经元能够实现自适应、非同质的行为。
• 该架构设计注重计算效率，避免了深度一维卷积神经网络对并行硬件的依赖。
• 模型在包含超过一百万次ECG波搏动的中国生理信号挑战赛-2020（CPSC）数据集上进行评估。
• 性能通过标准指标进行衡量：F1分数、敏感度和阳性预测值。

实验结果

研究问题

• RQ1 自组织神经网络架构是否能在噪声较大的Holter ECG信号中，优于深度一维卷积神经网络（1-D CNNs）进行R波峰检测？
• RQ2 使用能够自主选择最优操作符的生成神经元，是否能提升检测的鲁棒性与准确性？
• RQ3 紧凑型神经网络是否能在无需专用并行硬件的情况下实现最先进性能？
• RQ4 与现有深度学习模型相比，所提出的Self-ONN方法在F1分数、敏感度和阳性预测值方面表现如何？
• RQ5 自组织机制在多大程度上减少了对神经网络中操作符集合超参数调优的需求？

主要发现

• 所提出的1-D Self-ONNs在CPSC-2020数据集上实现了99.10%的F1分数，创下R波峰检测的新最先进水平。
• 该方法达到99.79%的敏感度，表明在ECG信号中对真实R波峰的检测近乎完美。
• 阳性预测值达到98.42%，证明了在波峰定位上的高精度。
• 该模型在显著低于深度一维卷积神经网络的计算复杂度下，实现了卓越的性能。
• 自组织机制消除了对每个神经元操作符集合进行手动调优的需求，提升了模型的适应性与鲁棒性。
• 结果证实，异构的生成神经元在ECG波峰检测任务中优于同质、固定结构的网络。