Department of Electronic Science and TechnologyUniversity of Science and Technology of ChinaHefei230027China.
Department of ElectrocardiogramThe First Affiliated Hospital of USTC, Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei230001China.
IEEE J Transl Eng Health Med. 2021 Mar 9;9:1900211. doi: 10.1109/JTEHM.2021.3064675. eCollection 2021.
Automatic arrhythmia detection using 12-lead electrocardiogram (ECG) signal plays a critical role in early prevention and diagnosis of cardiovascular diseases. In the previous studies on automatic arrhythmia detection, most methods concatenated 12 leads of ECG into a matrix, and then input the matrix to a variety of feature extractors or deep neural networks for extracting useful information. Under such frameworks, these methods had the ability to extract comprehensive features (known as integrity) of 12-lead ECG since the information of each lead interacts with each other during training. However, the diverse lead-specific features (known as diversity) among 12 leads were neglected, causing inadequate information learning for 12-lead ECG. To maximize the information learning of multi-lead ECG, the information fusion of comprehensive features with integrity and lead-specific features with diversity should be taken into account. In this paper, we propose a novel Multi-Lead-Branch Fusion Network (MLBF-Net) architecture for arrhythmia classification by integrating multi-loss optimization to jointly learning diversity and integrity of multi-lead ECG. MLBF-Net is composed of three components: 1) multiple lead-specific branches for learning the diversity of multi-lead ECG; 2) cross-lead features fusion by concatenating the output feature maps of all branches for learning the integrity of multi-lead ECG; 3) multi-loss co-optimization for all the individual branches and the concatenated network. We demonstrate our MLBF-Net on China Physiological Signal Challenge 2018 which is an open 12-lead ECG dataset. The experimental results show that MLBF-Net obtains an average [Formula: see text] score of 0.855, reaching the highest arrhythmia classification performance. The proposed method provides a promising solution for multi-lead ECG analysis from an information fusion perspective.
使用 12 导联心电图（ECG）信号进行自动心律失常检测在心血管疾病的早期预防和诊断中起着关键作用。在以前的自动心律失常检测研究中，大多数方法将 12 导联 ECG 串联成一个矩阵，然后将矩阵输入到各种特征提取器或深度神经网络中，以提取有用信息。在这种框架下，这些方法具有提取 12 导联 ECG 综合特征（称为完整性）的能力，因为在训练过程中每个导联的信息相互作用。然而，12 导联之间多样化的导联特异性特征（称为多样性）被忽略了，导致对 12 导联 ECG 的信息学习不足。为了最大限度地提高多导联 ECG 的信息学习能力，应考虑综合特征的完整性和导联特异性特征的多样性的信息融合。在本文中，我们提出了一种新的多导联分支融合网络（MLBF-Net）架构，通过集成多损失优化来联合学习多导联 ECG 的多样性和完整性，用于心律失常分类。MLBF-Net 由三个部分组成：1）多个导联特定分支，用于学习多导联 ECG 的多样性；2）通过串联所有分支的输出特征图进行跨导联特征融合，用于学习多导联 ECG 的完整性；3）多损失共同优化所有个体分支和串联网络。我们在中国生理信号挑战赛 2018 上展示了我们的 MLBF-Net，这是一个开放的 12 导联 ECG 数据集。实验结果表明，MLBF-Net 获得了 0.855 的平均[Formula: see text]分数，达到了最高的心律失常分类性能。该方法从信息融合的角度为多导联 ECG 分析提供了一种有前途的解决方案。
