School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Science), Jinan, 250353, Shandong Province, China.
School of Electronic and Information Engineering (Department of Physics), Qilu University of Technology (Shandong Academy of Science), Jinan, 250353, Shandong Province, China.
Sci Rep. 2022 Aug 25;12(1):14485. doi: 10.1038/s41598-022-18664-0.
Electrocardiogram (ECG) is mostly used for the clinical diagnosis of cardiac arrhythmia due to its simplicity, non-invasiveness, and reliability. Recently, many models based on the deep neural networks have been applied to the automatic classification of cardiac arrhythmia with great success. However, most models independently extract the internal features of each lead in the 12-lead ECG during the training phase, resulting in a lack of inter-lead features. Here, we propose a general model based on the two-dimensional ECG and ResNet with detached squeeze-and-excitation modules (DSE-ResNet) to realize the automatic classification of normal rhythm and 8 cardiac arrhythmias. The original 12-lead ECG is spliced into a two-dimensional plane like a grayscale picture. DSE-ResNet is used to simultaneously extract the internal and inter-lead features of the two-dimensional ECG. Furthermore, an orthogonal experiment method is used to optimize the hyper-parameters of DSE-ResNet and a multi-model voting strategy is used to improve classification performance. Experimental results based on the test set of China Physiological Signal Challenge 2018 (CPSC2018) show that our model has average [Formula: see text] for classifying normal rhythm and 8 cardiac arrhythmias. Meanwhile, compared with the state-of-art model in CPSC2018, our model achieved the best [Formula: see text] in 2 sub-abnormal types. This shows that the model based on the two-dimensional ECG and DSE-ResNet has advantage in detecting some cardiac arrhythmias and has the potential to be used as an auxiliary tool to help doctors perform cardiac arrhythmias analysis.
心电图（ECG）因其简单、无创和可靠而主要用于临床心律失常的诊断。最近，许多基于深度学习神经网络的模型已被应用于心律失常的自动分类，并取得了巨大的成功。然而，大多数模型在训练阶段独立地从 12 导联心电图中提取每个导联的内部特征，导致缺乏导联间特征。在这里，我们提出了一种基于二维心电图和带有分离挤压激励模块（DSE-ResNet）的 ResNet 的通用模型，以实现正常节律和 8 种心律失常的自动分类。原始的 12 导联心电图被拼接成一个二维平面，就像灰度图像一样。DSE-ResNet 用于同时提取二维心电图的内部和导联间特征。此外，采用正交实验方法优化 DSE-ResNet 的超参数，并采用多模型投票策略提高分类性能。基于中国生理信号挑战赛 2018 （CPSC2018）测试集的实验结果表明，我们的模型在分类正常节律和 8 种心律失常方面的平均准确率为[Formula: see text]。同时，与 CPSC2018 中的最先进模型相比，我们的模型在 2 种亚异常类型中取得了最佳的[Formula: see text]。这表明基于二维心电图和 DSE-ResNet 的模型在检测某些心律失常方面具有优势，并有可能作为辅助工具帮助医生进行心律失常分析。
