A fully-automated paper ECG digitisation algorithm using deep learning

Abstract

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60–70% and the average correlation of 3-by-1 ECGs achieved 80–90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.

Machine learning discriminates P2X7-mediated intracellular calcium sparks in human-induced pluripotent stem cell-derived neural stem cells

“…Adenosine triphosphate (ATP) treatment results in mixed responses of random calcium-sparks and waves with various dynamic ranges. Previous studies have applied the ML method to analyze waveforms as digitized images 31 or as one-dimensional time-series data 32 . We hypothesized that ML using raw waveform images could be more effective for handling the high-variety waveform data of calcium sparks.…”

GenECG: A synthetic image-based ECG dataset to augment artificial intelligence-enhanced algorithm development

“…Several groups have attempted to develop ECG digitisation tools to address the issue. [20][21][22] Such tools have been designed to derive signal data from paper-based ECGs. Unfortunately, these tools are limited by the requirements for manual intervention to ensure correct ECG lead identification by the user, are unable to process large volumes of paper-based ECGs and often require users to individually input single ECGs one at a time.…”

Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets

“…The reason for using this tool was because of its high correlation of 0.977 and accurate mapping of signals from images. Since the region is selected manually, it performs better than other open-source tools that produce undesirable noise and wrong signals while working end-to-end [ 46 ]. For every image, one CSV file was saved for the digitized heartbeat of lead II, and this yielded 928 CSV files at the end of the digitization process.…”