ACL-ECG: Anatomy-Aware Contrastive Learning for Multi-Lead Electrocardiograms
Open Access
Abstract
Deep learning has achieved impressive progress in automated electrocardiogram (ECG) analysis, yet its performance still relies heavily on large-scale labeled datasets. As ECG annotation requires cardiologists, this process is costly and time-consuming, limiting its scalability in clinical practice. Contrastive learning offers a promising alternative by enabling the extraction of generalizable representations from unlabeled ECG data. In this study, we propose Anatomy-Aware Contrastive Learning for ECG (ACL-ECG), a self-supervised method that incorporates cardiac anatomical relationships into contrastive learning. ACL-ECG employs a physiology-aware augmentation strategy to generate rhythm-preserving augmented views, including random scale cropping, cardiac-cycle masking, and temporal shifting. Furthermore, ECG leads are grouped into four anatomically meaningful regions—anterior, inferior, septal, and lateral—and region-level contrastive objectives are introduced to promote intra-region consistency while enhancing inter-region discriminability. Extensive evaluations of downstream tasks demonstrate that ACL-ECG consistently outperforms state-of-the-art contrastive baselines under linear probing, achieving improvements of up to 1.29% in the area under the receiver operating characteristic curve (AUROC) and 3.57% in the area under the precision–recall curve (AUPRC). Moreover, when fine-tuned using only 10% of labeled data, ACL-ECG attains a performance comparable to fully supervised training, effectively reducing annotation requirements by approximately 5∼8×. Ablation studies further confirm the contributions of both the physiology-aware augmentation strategy and the anatomy-aware contrastive objective. Overall, ACL-ECG enhances representation quality without increasing annotation burden, and provides a promising and anatomy-informed foundation for self-supervised ECG analysis in label-scarce settings.Keywords
Funding Information
- Natural Science Foundation of Jiangxi Province (20252BAC200017;20252BAC200021)
- Early-Career Young Scientists and Technologists Project of Jiangxi Province (20244BCE52162;20252BEJ730162)
- National Natural Science Foundation of China (62463009;62062034;62172160;81971702)
- National Key Research and Development Program of China (2022YFB2602200)
- Double Thousand Plan of Jiangxi Province (JXSQ2023201010)
- Jiangxi Province Key Laboratory of Advanced Network (2024SSY03071)
This publication has 30 references indexed in Scilit:
- Self-supervised learning for Electrocardiogram classification using Lead Correlation and DecorrelationApplied Soft Computing, 2025
- Dense lead contrast for self-supervised representation learning of multilead electrocardiogramsInformation Sciences, 2023
- Self-supervised representation learning from 12-lead ECG dataComputers in Biology and Medicine, 2022
- Cardiology2021
- ML–ResNet: A novel network to detect and locate myocardial infarction using 12 leads ECGComputer Methods and Programs in Biomedicine, 2020
- Computer Vision – ECCV 20202020
- Multiple-feature-branch convolutional neural network for myocardial infarction diagnosis using electrocardiogramBiomedical Signal Processing and Control, 2018
- ECG-based heartbeat classification for arrhythmia detection: A surveyComputer Methods and Programs in Biomedicine, 2016
- Myocardial infarction classification with multi-lead ECG using hidden Markov models and Gaussian mixture modelsApplied Soft Computing, 2012
- The Global Burden of Cardiovascular DiseaseEuropean Journal of Cardiovascular Nursing, 2011