Demolder Anthony, Kresnakova Viera, Hojcka Michal, Boza Vladimir, Iring Andrej, Rafajdus Adam, Rovder Simon, Palus Timotej, Herman Martin, Bauer Felix, Jurasek Viktor, Hatala Robert, Bartunek Jozef, Vavrik Boris, Herman Robert
Powerful Medical, Bratislava, Slovakia; Cardiovascular Centre Aalst, Aalst, Belgium.
Powerful Medical, Bratislava, Slovakia; Department of Cybernetics and Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Kosice, Slovakia.
J Electrocardiol. 2025 May-Jun;90:153900. doi: 10.1016/j.jelectrocard.2025.153900. Epub 2025 Feb 19.
Digitization of paper-based electrocardiograms (ECGs) enables long-term preservation, fast transmission, and advanced analysis. Traditional methods for digitizing ECGs face significant challenges, particularly in real-world scenarios with varying image quality. State-of-the-art solutions often require manual input and are limited by their dependence on high-quality scans and standardized layouts.
This study introduces a fully automated, deep learning-based approach for high precision ECG digitization. In the normalization phase, a standardized grid structure is detected, and image distortions are corrected. Next, the reconstruction phase uses deep learning techniques to extract and digitize the leads, followed by post-processing to refine the signal. This approach was evaluated using the publicly available PMcardio ECG Image Database (PM-ECG-ID), comprising 6000 ECG images reflecting diverse real-world scenarios and smartphone-based image acquisitions. Performance was assessed using Pearson's correlation coefficient (PCC), root mean squared error (RMSE), and signal-to-noise ratio (SNR).
The ECG digitization solution demonstrated an average PCC consistently exceeding 0.91 across all leads, SNR above 12.5 dB and RMSE below 0.10 mV. The time to ECG digitization was consistently less than 7 s. The average failure rate was 6.62 % across leads, with most failures occurring under extreme conditions such as severe blurring or significant image degradation. The solution maintained robust performance even under challenging scenarios, such as low-resolution images, distorted grids, and overlapping signals.
Our deep learning-based approach for ECG digitization delivers high-precision signals, effectively addressing real-world challenges. This fully automated method enhances the accessibility and utility of ECG data by enabling convenient digitization via smartphones, unlocking advanced AI-driven analysis.
纸质心电图（ECG）的数字化能够实现长期保存、快速传输和高级分析。传统的心电图数字化方法面临重大挑战，尤其是在图像质量各异的现实场景中。最先进的解决方案通常需要人工输入，并且受限于对高质量扫描和标准化布局的依赖。
本研究引入了一种基于深度学习的全自动高精度心电图数字化方法。在归一化阶段，检测标准化网格结构并校正图像失真。接下来，重建阶段使用深度学习技术提取导联并进行数字化，随后进行后处理以优化信号。使用公开可用的PMcardio心电图图像数据库（PM-ECG-ID）对该方法进行评估，该数据库包含6000张反映各种现实场景和基于智能手机图像采集的心电图图像。使用皮尔逊相关系数（PCC）、均方根误差（RMSE）和信噪比（SNR）评估性能。
心电图数字化解决方案在所有导联上的平均PCC始终超过0.91，SNR高于12.5 dB，RMSE低于0.10 mV。心电图数字化的时间始终少于7秒。各导联的平均故障率为6.62%，大多数故障发生在极端条件下，如严重模糊或图像严重退化。即使在具有挑战性的场景下，如低分辨率图像、扭曲的网格和重叠信号，该解决方案也能保持稳健的性能。
我们基于深度学习的心电图数字化方法可提供高精度信号，有效应对现实世界的挑战。这种全自动方法通过实现通过智能手机进行便捷数字化，增强了心电图数据的可及性和实用性，开启了先进的人工智能驱动分析。
