Deep learning for digitizing highly noisy paper-based ECG records. (December 2020)

• Record Type: Journal Article
• Authors: Li, Yao; Qu, Qixun; Wang, Meng; Yu, Liheng; Wang, Jun; Shen, Linghao; He, Kunlun
• Is Part Of: Computers in biology and medicine. Volume 127(2020)
• Publication Date: 2020-12
• Subjects: Electrocardiogram -- Digitization -- Deep learning -- Image segmentation -- Signal processing; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104077
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: 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. Highlights: Proposing an end-to-end ECG digitization method to handle the various types of low-quality ECG scans. Formulating the ECG digitization as image segmentation and proposing deep learning framework for solving it. Achieving good performance in both waveform extraction and common ECG parameter measurements.