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

2025/05/26 by Rahimi, Masoud, Karbasi, Reza, Vahabie, Abdol-Hossein · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2506.06315

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.

Citations

• ECG-Image-Database: A Dataset of ECG Images with Real-World Imaging and Scanning Artifacts; A Foundation for Computerized ECG Image Digitization and Analysis
• ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet
• Comparing Deep Neural Network for Multi-Label ECG Diagnosis From Scanned ECG

Cited by

• Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code

Related

• Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code
• ECG-Image-Database: A Dataset of ECG Images with Real-World Imaging and Scanning Artifacts; A Foundation for Computerized ECG Image Digitization and Analysis
• ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization
• Auto Lead Extraction and Digitization of ECG Paper Records using cGAN
• ECGXtract: Deep Learning-based ECG Feature Extraction for Automated CVD Diagnosis