Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Ludwig Boltzmann Institute for Cardiovascular Research, Währinger Gürtel 18-20, A-1090 Vienna, Austria.
Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Ludwig Boltzmann Institute for Cardiovascular Research, Währinger Gürtel 18-20, A-1090 Vienna, Austria.
Artif Intell Med. 2023 Sep;143:102632. doi: 10.1016/j.artmed.2023.102632. Epub 2023 Aug 10.
Training deep neural network classifiers for electrocardiograms (ECGs) requires sufficient data. However, imbalanced datasets pose a major problem for the training process and hence data augmentation is commonly performed. Generative adversarial networks (GANs) can create synthetic ECG data to augment such imbalanced datasets. This review aims at identifying the present literature concerning synthetic ECG signal generation using GANs to provide a comprehensive overview of architectures, quality evaluation metrics, and classification performances. Thirty publications from the years 2019 to 2022 were selected from three separate databases. Nine publications used a quality evaluation metric neglecting classification, eleven performed a classification but omitted a quality evaluation metric, and ten publications performed both. Twenty different quality evaluation metrics were observed. Overall, the classification performance of databases augmented with synthetically created ECG signals increased by 7 % to 98 % in accuracy and 6 % to 97 % in sensitivity. In conclusion, synthetic ECG signal generation using GANs represents a promising tool for data augmentation of imbalanced datasets. Consistent quality evaluation of generated signals remains challenging. Hence, future work should focus on the establishment of a gold standard for quality evaluation metrics for GANs.
训练用于心电图 (ECG) 的深度神经网络分类器需要足够的数据。然而，不平衡数据集对训练过程构成了重大问题，因此通常会进行数据扩充。生成对抗网络 (GAN) 可以创建合成 ECG 数据来扩充此类不平衡数据集。本综述旨在确定目前使用 GAN 生成合成 ECG 信号的文献，以提供有关架构、质量评估指标和分类性能的全面概述。从三个独立的数据库中选择了 2019 年至 2022 年的 30 篇出版物。9 篇出版物使用了忽略分类的质量评估指标，11 篇进行了分类但忽略了质量评估指标，10 篇出版物同时进行了分类和质量评估指标。观察到了 20 种不同的质量评估指标。总体而言，用合成 ECG 信号扩充后的数据库的分类性能在准确性方面提高了 7% 到 98%，在灵敏度方面提高了 6% 到 97%。总之，使用 GAN 生成合成 ECG 信号是一种很有前途的数据扩充工具，可用于不平衡数据集。生成信号的一致质量评估仍然具有挑战性。因此，未来的工作应集中于为 GAN 的质量评估指标建立黄金标准。
