PTB-Image: A Scanned Paper ECG Dataset for Digitization and Image-based Diagnosis

2025-02-19

AI Summary

To address the clinical challenge of automated analysis and digital archiving of paper-based electrocardiogram (ECG) recordings, this work introduces PTB-Image—the first publicly available dataset featuring strictly paired scanned paper-ECG images and their corresponding high-fidelity digital ECG signals. Methodologically, we propose VinDigitizer, an end-to-end framework integrating precise signal-line localization, adaptive waveform extraction, geometric distortion correction, and pixel-intensity-to-voltage mapping to achieve holistic image-to-time-series digitization. Evaluated on 549 real-world scanned ECGs, VinDigitizer achieves a mean signal-to-noise ratio of 0.01 dB, demonstrating high-fidelity signal reconstruction. This work establishes the first rigorously paired benchmark for paper-based ECGs and provides a systematic digitization methodology, enabling large-scale reuse of legacy ECG data, telecardiology applications, and automated cardiac diagnostics.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Humans and AI: Voting
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Privacy-enhancing technologies
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Electrocardiograms (ECGs) recorded on paper remain prevalent in clinical practice, yet their use presents challenges for automated analysis and digital storage. To address this issue, we introduce PTB-Image, a dataset comprising scanned paper ECGs with corresponding digital signals, enabling research on ECG digitization. We also provide VinDigitizer, a digitization baseline to convert paper-based ECGs into digital time-series signals. The method involves detecting signal rows, extracting waveforms from the background, and reconstructing numerical values from the digitized traces. We applied VinDigitizer to 549 scanned ECGs and evaluated its performance against the original PTB dataset (modified to match the printed signals). The results achieved a mean signal-to-noise ratio (SNR) of 0.01 dB, highlighting both the feasibility and challenges of ECG digitization, particularly in mitigating distortions from printing and scanning processes. By providing PTB-Image and baseline digitization methods, this work aims to facilitate advancements in ECG digitization, enhancing access to historical ECG data and supporting applications in telemedicine and automated cardiac diagnostics.

Problem

• Digitize paper-based ECGs for digital analysis.
• Mitigate distortions from printing and scanning.
• Enhance access to historical ECG data.

Innovation

• Introduces PTB-Image dataset
• Provides VinDigitizer for digitization
• Detects and reconstructs ECG signals