Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Learning ECG Image Representations via Dual Physiological-Aware Alignments

About

Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data worldwide appears only in image form. However, most existing automated ECG analysis methods rely on access to raw signal recordings, limiting their applicability in real-world and resource-constrained settings. In this paper, we present ECG-Scan, a self-supervised framework for learning clinically generalized representations from ECG images through dual physiological-aware alignments: 1) Our approach optimizes image representation learning using multimodal contrastive alignment between image and gold-standard signal-text modalities. 2) We further integrate domain knowledge via soft-lead constraints, regularizing the reconstruction process and improving signal lead inter-consistency. Extensive benchmarking across multiple datasets and downstream tasks demonstrates that our image-based model achieves superior performance compared to existing image baselines and notably narrows the gap between ECG image and signal analysis. These results highlight the potential of self-supervised image modeling to unlock large-scale legacy ECG data and broaden access to automated cardiovascular diagnostics.

Hung Manh Pham, Jialu Tang, Aaqib Saeed, Dong Ma, Bin Zhu, Pan Zhou• 2026

Related benchmarks

TaskDatasetResultRank
ECG ClassificationPTBXL Super
Macro AUC90.9
84
ECG ClassificationCPSC 2018
AUC94.6
23
ECG ClassificationPTBXL Sub
Macro AUC0.853
18
ECG ClassificationPTBXL Form
Macro AUC84.1
18
ECG ClassificationPTBXL Rhythm
Macro AUC93.3
18
ECG ClassificationCSN
Macro AUC94.2
18
ECG ClassificationPTB-XL, CPSC2018, CSN Cross-domain (test)
AUC (PTBXL-Super -> CPSC2018)84.27
14
ECG InterpretationCODE (test)
AUC94.78
9
Showing 8 of 8 rows

Other info

Follow for update