Medicine School of Chinese PLA, Beijing, 100853, China; Core Laboratory of Translational Medicine, Chinese PLA General Hospital, Beijing, 100853, China; Beijing Key Laboratory of Chronic Heart Failure Precision Medicine, Chinese PLA General Hospital, Beijing, 100853, China.
Shenzhen Digital Life Institute, Shenzhen, Guangdong, 518000, China.
Comput Biol Med. 2020 Dec;127:104077. doi: 10.1016/j.compbiomed.2020.104077. Epub 2020 Oct 28.
Electrocardiography (ECG) is essential in many heart diseases. However, some ECGs are recorded by paper, which can be highly noisy. Digitizing the paper-based ECG records into a high-quality signal is critical for further analysis. We formulated the digitization problem as a segmentation problem and proposed a deep learning method to digitize highly noisy ECG scans. Our method extracts the ECG signal in an end-to-end manner and can handle different paper record layouts. In the experiment, our model clearly extracted the ECG waveform with a Dice coefficient of 0.85 and accurately measured the common ECG parameters with more than 0.90 Pearson's correlation. We showed that the end-to-end approach with deep learning can be powerful in ECG digitization. To the best of our knowledge, we provide the first approach to digitize the least informative noisy binary ECG scans and potentially be generalized to digitize various ECG records.
心电图（ECG）在许多心脏疾病中至关重要。然而，一些心电图是用纸记录的，这可能会产生很大的噪声。将基于纸张的心电图记录数字化为高质量的信号对于进一步分析至关重要。我们将数字化问题表述为一个分割问题，并提出了一种深度学习方法来数字化高度嘈杂的心电图扫描。我们的方法以端到端的方式提取心电图信号，可以处理不同的纸张记录布局。在实验中，我们的模型清晰地提取了心电图波形，Dice 系数为 0.85，并且能够准确地测量常见的心电图参数，Pearson 相关系数超过 0.90。我们表明，基于深度学习的端到端方法在心电图数字化方面非常有效。据我们所知，我们首次提出了一种方法来数字化信息量最少的嘈杂二进制心电图扫描，并有可能推广到各种心电图记录的数字化。
