School of Electrical Engineering, Zhengzhou University, NO. 100 Kexue Road, Zhengzhou, Henan 450000, China.
School of Electrical Engineering, Zhengzhou University, NO. 100 Kexue Road, Zhengzhou, Henan 450000, China; Department of Automation, Tsinghua University, Beijing, Beijing, China; Beijing National Research Center for Information Science and Technology, Beijing, Beijing, China.
Comput Methods Programs Biomed. 2020 Mar;185:105138. doi: 10.1016/j.cmpb.2019.105138. Epub 2019 Oct 17.
Myocardial infarction (MI) is one of the most threatening cardiovascular diseases for human beings, which can be diagnosed by electrocardiogram (ECG). Automated detection methods based on ECG focus on extracting handcrafted features. However, limited by the performance of traditional methods and individual differences between patients, it's difficult for predesigned features to detect MI with high performance.
The paper presents a novel method to detect and locate MI combining a multi-lead residual neural network (ML-ResNet) structure with three residual blocks and feature fusion via 12 leads ECG records. Specifically, single lead feature branch network is trained to automatically learn the representative features of different levels between different layers, which exploits local characteristics of ECG to characterize the spatial information representation. Then all the lead features are fused together as global features. To evaluate the generalization of proposed method and clinical utility, two schemes including the intra-patient scheme and inter-patient scheme are all employed.
Experimental results based on PTB (Physikalisch-Technische Bundesanstalt) database shows that our model achieves superior results with the accuracy of 95.49%, the sensitivity of 94.85%, the specificity of 97.37%, and the F1 score of 96.92% for MI detection under the inter-patient scheme compared to the state-of-the-art. By contrast, the accuracy is 99.92% and the F1 score is 99.94% based on 5-fold cross validation under the intra-patient scheme. As for five types of MI location, the proposed method also yields an average accuracy of 99.72% and F1 of 99.67% in the intra-patient scheme.
The proposed method for MI detection and location has achieved superior results compared to other detection methods. However, further promotion of the performance based on MI location for the inter-patient scheme still depends significantly on the mass data and the novel model which reflects spatial location information of different leads subtly.
心肌梗死（MI）是对人类最具威胁的心血管疾病之一，可通过心电图（ECG）进行诊断。基于 ECG 的自动检测方法侧重于提取手工制作的特征。然而，受限于传统方法的性能和患者之间的个体差异，预先设计的特征难以实现高性能的 MI 检测。
本文提出了一种新的方法，通过 12 导联 ECG 记录，结合具有三个残差块和特征融合的多导联残差神经网络（ML-ResNet）结构，用于 MI 的检测和定位。具体来说，训练单导联特征分支网络，自动学习不同层之间不同级别之间的代表性特征，利用 ECG 的局部特征来描述空间信息表示。然后，将所有导联特征融合在一起作为全局特征。为了评估所提出方法的泛化能力和临床实用性，采用了包括患者内方案和患者间方案在内的两种方案。
基于 PTB（Physikalisch-Technische Bundesanstalt）数据库的实验结果表明，与最先进的方法相比，我们的模型在患者间方案下，MI 检测的准确率为 95.49%、灵敏度为 94.85%、特异性为 97.37%和 F1 得分为 96.92%，具有优异的结果。相比之下，在患者内方案下，基于 5 折交叉验证的准确率为 99.92%，F1 得分为 99.94%。对于 MI 的五种定位类型，该方法在患者内方案下的平均准确率为 99.72%，F1 得分为 99.67%。
与其他检测方法相比，用于 MI 检测和定位的方法取得了优异的结果。然而，要进一步提高患者间方案下 MI 定位的性能，仍然需要大量的数据和能够微妙地反映不同导联空间位置信息的新型模型。
