arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01995eess.SPcs.LG
收藏

卷积神经网络对生理ECG噪声的鲁棒性

Robustness of convolutional neural networks to physiological ECG noise

National Physical Laboratory(英国国家物理实验室);University of Surrey(萨里大学)

J. Venton, P. M. Harris, A. Sundar, N. A. S. Smith, P. J. Aston

摘要:

心电图(ECG)是医疗保健中最广泛的诊断工具之一,支持心血管疾病的诊断。深度学习方法是一种成功且流行的技术,可以从ECG信号中检测疾病的迹象。然而,这些方法对各种因素(包括生理ECG噪声)的鲁棒性存在公开问题。在这项研究中,我们生成清洁和嘈杂的版本的ECG数据集之前,应用对称投影吸引子重建(SPAR)和尺度图图像变换。使用迁移学习来训练预训练的卷积神经网络,以分类这些图像变换。对于干净的ECG数据集,SPAR吸引子和尺度图变换的F1分数分别为0.70和0.79,对于有噪声的ECG数据集,分数下降小于0.05。值得注意的是,当使用干净数据训练的网络来分类嘈杂的数据集时,F1分数的性能下降高达0.18。然而,当使用在噪声数据上训练的网络来分类干净数据集时,性能下降小于0.05。我们的结论是,生理ECG噪声会影响使用深度学习方法的分类,在开发用于ECG分类的监督网络时,应仔细考虑在训练数据中包含噪声ECG信号。

英文摘要:

The electrocardiogram (ECG) is one of the most widespread diagnostic tools in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study we generate clean and noisy versions of an ECG dataset before applying Symmetric Projection Attractor Reconstruction (SPAR) and scalogram image transformations. A pretrained convolutional neural network is trained using transfer learning to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively, and the scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the performance decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑