Comparing Deep Neural Network for Multi-Label ECG Diagnosis From Scanned ECG

TL;DR

This paper evaluates various deep neural network architectures for multi-label ECG diagnosis from scanned images, assessing their accuracy, robustness, and potential for clinical application.

Contribution

It provides a comparative analysis of deep learning models on scanned ECGs, highlighting their strengths and limitations for automated diagnosis.

Findings

ResNet and Vision Transformer outperform others in accuracy.

Models show robustness to common image artifacts.

Extracted ECG signals retain diagnostic information.

Abstract

Automated ECG diagnosis has seen significant advancements with deep learning techniques, but real-world applications still face challenges when dealing with scanned paper ECGs. In this study, we explore multi-label classification of ECGs extracted from scanned images, moving beyond traditional binary classification (normal/abnormal). We evaluate the performance of multiple deep neural network architectures, including AlexNet, VGG, ResNet, and Vision Transformer, on scanned ECG datasets. Our comparative analysis examines model accuracy, robustness to image artifacts, and generalizability across different ECG conditions. Additionally, we investigate whether ECG signals extracted from scanned images retain sufficient diagnostic information for reliable automated classification. The findings highlight the strengths and limitations of each architecture, providing insights into the feasibility of image-based ECG diagnosis and its potential integration into clinical workflows.