Learning ECG Image Representations via Dual Physiological-Aware Alignments
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 2 Apr 2026.
Builds on
25 of 49 references.
References · 25
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
- 2019Publicly Available Clinical BERT Embeddingscited by 995
- 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 182
- 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
- 2024ECG-FM: An Open Electrocardiogram Foundation Modelcited by 89
- 2024Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogramcited by 84
- 2024Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancementcited by 66
- 2023ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogramcited by 52
13 more
- 2024Gramian Multimodal Representation Learning and Alignmentcited by 52
- 2022Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformercited by 47
- 2025Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Modelcited by 36
- 2024ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Textcited by 25
- 2024Teach Multimodal LLMs to Comprehend Electrocardiographic Imagescited by 25
- 2023ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitizationcited by 20
- 2024Boosting Masked ECG-Text Auto-Encoders as Discriminative Learnerscited by 16
- 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretrainingcited by 15
- 2018Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discoverycited by 14
- 2025Q-Heart: ECG Question Answering via Knowledge-Informed Multimodal LLMscited by 11
- 2025anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understandingcited by 9
- 2024Combining Hough Transform and Deep Learning Approaches to Reconstruct ECG Signals From Printoutscited by 5
- 2025Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Researchcited by 3
Built on by
Not cited yet.