Ethiopian Artificial Intelligence Institute, P.O. Box 40782, Addis Ababa, Ethiopia.
Department of Computer Engineering, Addis Ababa Science and Technology University, P.O. Box 120611, Addis Ababa, Ethiopia.
Comput Intell Neurosci. 2022 Aug 8;2022:8413294. doi: 10.1155/2022/8413294. eCollection 2022.
The electrical activity produced during the heartbeat is measured and recorded by an ECG. Cardiologists can interpret the ECG machine's signals and determine the heart's health condition and related causes of ECG signal abnormalities. However, cardiologist shortage is a challenge in both developing and developed countries. Moreover, the experience of a cardiologist matters in the accurate interpretation of the ECG signal, as the interpretation of ECG is quite tricky even for experienced doctors. Therefore, developing computer-aided ECG interpretation is required for its wide-reaching effect. 12-lead ECG generates a 1D signal with 12 channels among the well-known time-series data. Classical machine learning can develop automatic detection, but deep learning is more effective in the classification task. 1D-CNN is being widely used for CVDS detection from ECG datasets. However, adopting a deep learning model designed for computer vision can be problematic because of its massive parameters and the need for many samples to train. In many detection tasks ranging from semantic segmentation of medical images to time-series data classification, multireceptive field CNN has improved performance. Notably, the nature of the ECG dataset made performance improvement possible by using a multireceptive field CNN (MRF-CNN). Using MRF-CNN, it is possible to design a model that considers semantic context information within ECG signals with different sizes. As a result, this study has designed a multireceptive field CNN architecture for ECG classification. The proposed multireceptive field CNN architecture can improve the performance of ECG signal classification. We have achieved a 0.72 score and 0.93 AUC for 5 superclasses, a 0.46 score and 0.92 AUC for 20 subclasses, and a 0.31 score and 0.92 AUC for all the diagnostic classes of the PTB-XL dataset.
心电图（ECG）测量并记录心脏跳动时产生的电活动。心脏病专家可以解读 ECG 机的信号，判断心脏的健康状况和 ECG 信号异常的相关原因。然而，心脏病专家的短缺是发展中国家和发达国家共同面临的挑战。此外，即使对于经验丰富的医生来说，ECG 信号的解读也颇具难度，因此需要借助计算机辅助 ECG 解读技术。12 导联心电图产生的一维信号包含 12 个通道，是广为人知的时间序列数据之一。经典的机器学习可以开发自动检测，但深度学习在分类任务中更为有效。一维卷积神经网络（1D-CNN）在从 ECG 数据集检测心血管疾病（CVDS）方面得到了广泛应用。然而，采用专为计算机视觉设计的深度学习模型可能会存在问题，因为它的参数众多，需要大量样本进行训练。在从医学图像语义分割到时间序列数据分类等多种检测任务中，多感受野卷积神经网络（MRF-CNN）提高了性能。值得注意的是，由于 ECG 数据集的性质，使用 MRF-CNN 可以提高性能。通过使用 MRF-CNN，可以设计一个模型，考虑到不同大小的 ECG 信号中的语义上下文信息。因此，本研究设计了一种用于 ECG 分类的多感受野卷积神经网络架构。所提出的多感受野卷积神经网络架构可以提高 ECG 信号分类的性能。我们在 PTB-XL 数据集的 5 个超级分类中达到了 0.72 的得分和 0.93 的 AUC，在 20 个子分类中达到了 0.46 的得分和 0.92 的 AUC，在所有诊断类别中达到了 0.31 的得分和 0.92 的 AUC。
