IEEE J Biomed Health Inform. 2023 Jun;27(6):2818-2828. doi: 10.1109/JBHI.2023.3246241. Epub 2023 Jun 5.
The automatic classification of electrocardiogram (ECG) signals has played an important role in cardiovascular diseases diagnosis and prediction. With recent advancements in deep neural networks (DNNs), particularly Convolutional Neural Networks (CNNs), learning deep features automatically from the original data is becoming an effective and widespread approach in a variety of intelligent tasks including biomedical and health informatics. However, most of the existing approaches are trained on either 1D CNNs or 2D CNNs, and they suffer from the limitations of random phenomena (i.e. random initial weights). Furthermore, the ability to train such DNNs in a supervised manner in healthcare is often limited due to the scarcity of labeled training data. To address the problems of weight initialization and limited annotated data, in this work, we leverage recent self-supervised learning technique, namely, contrastive learning, and present supervised contrastive learning (sCL). Different from existing self-supervised contrastive learning approaches, which often generate false negatives because of random selection of negative anchors, our contrastive learning makes use of labeled data to pull the same class closer together and push different classes far apart to avoid potential false negatives. Furthermore, unlike other kinds of signals (e.g. speech, image, video), ECG signal is sensitive to changes, and inappropriate transformation could directly affect diagnosis results. To deal with this issue, we present two semantic transformations, i.e. semantic split-join and semantic weighted peaks noise smoothing. The proposed deep neural network sCL-ST with supervised contrastive learning and semantic transformations is trained as an end-to-end framework for the multi-label classification of 12-lead ECGs. Our sCL-ST network contains two sub-networks i.e. pre-text task and down-stream task. Our experimental results have been evaluated on 12-lead PhysioNet 2020 dataset and shown that our proposed network outperforms the state-of-the-art existing approaches.
心电图（ECG）信号的自动分类在心血管疾病的诊断和预测中发挥了重要作用。随着深度学习网络（DNN），特别是卷积神经网络（CNN）的最新进展，从原始数据中自动学习深度特征在各种智能任务中变得越来越有效和广泛，包括生物医学和健康信息学。然而，现有的大多数方法都是基于一维 CNN 或二维 CNN 进行训练的，它们受到随机现象（即随机初始权重）的限制。此外，由于标记训练数据的稀缺，在医疗保健中以监督方式训练这些 DNN 的能力通常受到限制。为了解决权重初始化和有限标记数据的问题，在这项工作中，我们利用了最近的自监督学习技术，即对比学习，并提出了监督对比学习（sCL）。与现有的自监督对比学习方法不同，后者由于随机选择负锚而经常产生假阴性，我们的对比学习利用标记数据使相同类别的数据更加接近，使不同类别的数据更加远离，从而避免潜在的假阴性。此外，与其他类型的信号（如语音、图像、视频）不同，心电图信号对变化很敏感，不合适的变换会直接影响诊断结果。为了解决这个问题，我们提出了两种语义变换，即语义分割-合并和语义加权峰噪声平滑。所提出的具有监督对比学习和语义变换的深度神经网络 sCL-ST 被训练为用于 12 导联心电图的多标签分类的端到端框架。我们的 sCL-ST 网络包含两个子网络，即预训练任务和下游任务。我们的实验结果已经在 12 导联 PhysioNet 2020 数据集上进行了评估，结果表明我们提出的网络优于现有的最先进方法。
