ProEGAN-MS: A Progressive Growing Generative Adversarial Networks for Electrocardiogram Generation

Abstract

Electrocardiogram (ECG) is a physiological signal widely used in monitoring heart health, which is of great significance to the detection and diagnosis of heart diseases. Because abnormal heart rhythms are very rare, most ECG datasets have data imbalance problems. At present, many algorithms for ECG anomaly automatic recognition are affected by data imbalance. Conventional data augmentation methods are not suitable for the augmentation of the ECG signal, because the ECG signal is one-dimensional and their morphology has physiological significances. In this paper, we propose a ProGAN based ECG sample generation model, called ProEGAN-MS, to solve the problem of data imbalance. The model can stably generate realistic ECG samples. We evaluate the fidelity and diversity of the data generated by the model and compare the data distribution of the original and generated data. In addition, in order to show the diversity of the generated ECG data more intuitively, we manually checked the diversity and calculate the statistics of the data. The results show that compared with other ECG augmentation methods based on GANs, the ECG data generated by our model has higher fidelity and diversity, and the distribution of generated samples is closer to the distribution of original data. Finally, we established neural network models for arrhythmia classification, and used them to evaluate the improvement of the classification model performance by ProEGAN-MS. The results show that augmented data by ProEGAN-MS can effectively improve the insufficient sensitivity and precision of the classification model.

Research Progress of ECG Monitoring Equipment and Algorithms Based on Polymer Materials

“…Some studies have begun to apply GAN to the generation of ECG signals [64,74,75]. They use one-dimensional ECG signals as training sets to train GAN to produce new data similar to real collected signals.…”

“…On this basis, due to the change of random parameters during generation, the generated signals of the same type are not exactly the same, which is very similar to the difference between the real data. The expanded dataset generated by GAN solves the problem of class imbalance, and the performance of the deep learning model trained by it is further improved; also, the SEN of discriminating heart rhythm categories with a small number is significantly improved [74,75].…”

“…In the field of computer vision, they have been applied in generation [69], restoration [70][71][72], style transfer, and natural language processing in text generation [73]. Some studies have begun to apply GAN to the generation of ECG signals [64,74,75]. They use one-dimensional ECG signals as training sets to train GAN to produce new data similar to real collected signals.…”

A novel weighted approach for automated cardiac arrhythmia beat classification using convolutional neural networks

“…Even though deep learning models produced promising outcomes in arrhythmia classification, they were seriously influenced by imbalanced data. When a dataset contains extremely imbalance data, especially in deep learning, training models become more biased towards majority class samples [11]. In case of arrhythmia datasets, most of the abnormal heart beats are very rare, which restricts the development of automated models.…”

A Generative Adversarial Network (GAN) Technique for Internet of Medical Things Data

“…Data augmentation techniques are often used to generate new data by transforming existing datasets or by generating new synthetic data, always starting from real and existing data [ 8 ]. In healthcare, data augmentation has been applied, for example, to signals and images to improve disease detection and prediction [ 9 , 10 , 11 , 12 ]. In order to achieve this purpose, in recent years, a new concept called Generative Adversarial Networks (GAN) has emerged that offers an innovative method for data augmentation [ 13 ].…”