An Open-Source Python Framework and Synthetic ECG Image Datasets for Digitization, Lead and Lead Name Detection, and Overlapping Signal Segmentation

TL;DR

This paper presents an open-source Python framework that generates synthetic ECG image datasets for tasks like digitization, lead detection, and waveform segmentation, facilitating deep learning research.

Contribution

The authors introduce a novel framework that creates diverse synthetic ECG image datasets, including overlapping signals, to support various ECG analysis deep learning tasks.

Findings

Generated four open-access ECG datasets with annotations and segmentation masks.

Framework produces datasets with overlapping waveforms for complex segmentation tasks.

Datasets and code are publicly available for research use.

Abstract

We introduce an open-source Python framework for generating synthetic ECG image datasets to advance critical deep learning-based tasks in ECG analysis, including ECG digitization, lead region and lead name detection, and pixel-level waveform segmentation. Using the PTB-XL signal dataset, our proposed framework produces four open-access datasets: (1) ECG images in various lead configurations paired with time-series signals for ECG digitization, (2) ECG images annotated with YOLO-format bounding boxes for detection of lead region and lead name, (3)-(4) cropped single-lead images with segmentation masks compatible with U-Net-based models in normal and overlapping versions. In the overlapping case, waveforms from neighboring leads are superimposed onto the target lead image, while the segmentation masks remain clean. The open-source Python framework and datasets are publicly available at https://github.com/rezakarbasi/ecg-image-and-signal-dataset and https://doi.org/10.5281/zenodo.15484519, respectively.