1. Deep learning for digitizing highly noisy paper-based ECG records
- Author
-
Yao Li, Liheng Yu, Linghao Shen, Meng Wang, Jun Wang, Kunlun He, and Qixun Qu
- Subjects
0301 basic medicine ,Computer science ,Health Informatics ,Data_CODINGANDINFORMATIONTHEORY ,Signal ,03 medical and health sciences ,Electrocardiography ,0302 clinical medicine ,Deep Learning ,Sørensen–Dice coefficient ,Waveform ,ComputerSystemsOrganization_SPECIAL-PURPOSEANDAPPLICATION-BASEDSYSTEMS ,Segmentation ,Digitization ,Signal processing ,business.industry ,Deep learning ,Pattern recognition ,Signal Processing, Computer-Assisted ,Image segmentation ,Computer Science Applications ,ComputingMethodologies_PATTERNRECOGNITION ,030104 developmental biology ,Artificial intelligence ,business ,030217 neurology & neurosurgery ,Algorithms - 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.
- Published
- 2020