# ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization

arXiv: https://arxiv.org/abs/2307.01946 · HTML: https://mlsanity.com/paper/2307.01946/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 79 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts](https://mlsanity.com/paper/1902.09476/) (2019)
- [Accelerating Deep Learning Inference via Freezing](https://mlsanity.com/paper/2002.02645/) (2020)
- [Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial network](https://mlsanity.com/paper/2106.03701/) (2021)
- [Generation of Synthetic Electronic Health Records Using a Federated GAN](https://mlsanity.com/paper/2109.02543/) (2021)
- [A Data-Driven Gaussian Process Filter for Electrocardiogram Denoising](https://mlsanity.com/paper/2301.02607/) (2023)

## Built on by (most cited first, 20 of 20)

- [GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images](https://mlsanity.com/paper/2503.06073/) (2025)
- [Teach Multimodal LLMs to Comprehend Electrocardiographic Images](https://mlsanity.com/paper/2410.19008/) (2024)
- [ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation](https://mlsanity.com/paper/2602.04279/) (2026)
- [Combining Hough Transform and Deep Learning Approaches to Reconstruct ECG Signals From Printouts](https://mlsanity.com/paper/2410.14185/) (2024)
- [ECG-Image-Database: A Dataset of ECG Images with Real-World Imaging and Scanning Artifacts; A Foundation for Computerized ECG Image Digitization and Analysis](https://mlsanity.com/paper/2409.16612/) (2024)
- [Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework](https://mlsanity.com/paper/2505.18847/) (2025)
- [Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research](https://mlsanity.com/paper/2510.19590/) (2025)
- [An Open-Source Python Framework and Synthetic ECG Image Datasets for Digitization, Lead and Lead Name Detection, and Overlapping Signal Segmentation](https://mlsanity.com/paper/2506.06315/) (2025)
- [Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach](https://mlsanity.com/paper/2603.26695/) (2026)
- [Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs](https://mlsanity.com/paper/2607.05013/) (2026)
- [Comparing Deep Neural Network for Multi-Label ECG Diagnosis From Scanned ECG](https://mlsanity.com/paper/2502.14909/) (2025)
- [Pic2Diagnosis: A Method for Diagnosis of Cardiovascular Diseases from the Printed ECG Pictures](https://mlsanity.com/paper/2507.19961/) (2025)
- [Knowledge Augmentation via Synthetic Data: A Framework for Real-World ECG Image Classification](https://mlsanity.com/paper/2507.21968/) (2025)
- [Privacy-Aware Federated nnU-Net for ECG Page Digitization](https://mlsanity.com/paper/2510.22387/) (2025)
- [BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis](https://mlsanity.com/paper/2601.07316/) (2026)
- [PTB-XL-Image-17K: A Large-Scale Synthetic ECG Image Dataset with Comprehensive Ground Truth for Deep Learning-Based Digitization](https://mlsanity.com/paper/2602.07446/) (2026)
- [VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines](https://mlsanity.com/paper/2604.00396/) (2026)
- [Learning ECG Image Representations via Dual Physiological-Aware Alignments](https://mlsanity.com/paper/2604.01526/) (2026)
- [ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening](https://mlsanity.com/paper/2607.07683/) (2026)
- [LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification](https://mlsanity.com/paper/2607.10784/) (2026)

## Abstract (arXiv)

Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are printed on paper. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis and to leverage the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution. We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background. As a case study, we used ECG-Image-Kit to create a dataset of 21,801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio (SNR) and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization. This toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.