Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Xiaoyu, Nadarajah, Ramesh, Zhang, Zhiqiang, Wong, David
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.21968
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909975100522496
author Wang, Xiaoyu
Nadarajah, Ramesh
Zhang, Zhiqiang
Wong, David
author_facet Wang, Xiaoyu
Nadarajah, Ramesh
Zhang, Zhiqiang
Wong, David
contents In real-world clinical practice, electrocardiograms (ECGs) are often captured and shared as photographs. However, publicly available ECG data, and thus most related research, relies on digital signals. This has led to a disconnect in which computer assisted interpretation of ECG cannot easily be applied to ECG images. The emergence of high-fidelity synthetic data generators has introduced practical alternatives by producing realistic, photo-like, ECG images derived from the digital signal that could help narrow this divide. To address this, we propose a novel knowledge augmentation framework that uses synthetic data generated from multiple sources to provide generalisable and accurate interpretation of ECG photographs. Our framework features two key contributions. First, we introduce a robust pre-processing pipeline designed to remove background artifacts and reduces visual differences between images. Second, we implement a two-stage training strategy: a Morphology Learning Stage, where the model captures broad morphological features from visually different, scan-like synthetic data, followed by a Task-Specific Adaptation Stage, where the model is fine-tuned on the photo-like target data. We tested the model on the British Heart Foundation Challenge dataset, to classify five common ECG findings: myocardial infarction (MI), atrial fibrillation, hypertrophy, conduction disturbance, and ST/T changes. Our approach, built upon the ConvNeXt backbone, outperforms a single-source training baseline and achieved \textbf{1st} place in the challenge with an macro-AUROC of \textbf{0.9677}. These results suggest that incorporating morphology learning from heterogeneous sources offers a more robust and generalizable paradigm than conventional single-source training.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge Augmentation via Synthetic Data: A Framework for Real-World ECG Image Classification
Wang, Xiaoyu
Nadarajah, Ramesh
Zhang, Zhiqiang
Wong, David
Computer Vision and Pattern Recognition
In real-world clinical practice, electrocardiograms (ECGs) are often captured and shared as photographs. However, publicly available ECG data, and thus most related research, relies on digital signals. This has led to a disconnect in which computer assisted interpretation of ECG cannot easily be applied to ECG images. The emergence of high-fidelity synthetic data generators has introduced practical alternatives by producing realistic, photo-like, ECG images derived from the digital signal that could help narrow this divide. To address this, we propose a novel knowledge augmentation framework that uses synthetic data generated from multiple sources to provide generalisable and accurate interpretation of ECG photographs. Our framework features two key contributions. First, we introduce a robust pre-processing pipeline designed to remove background artifacts and reduces visual differences between images. Second, we implement a two-stage training strategy: a Morphology Learning Stage, where the model captures broad morphological features from visually different, scan-like synthetic data, followed by a Task-Specific Adaptation Stage, where the model is fine-tuned on the photo-like target data. We tested the model on the British Heart Foundation Challenge dataset, to classify five common ECG findings: myocardial infarction (MI), atrial fibrillation, hypertrophy, conduction disturbance, and ST/T changes. Our approach, built upon the ConvNeXt backbone, outperforms a single-source training baseline and achieved \textbf{1st} place in the challenge with an macro-AUROC of \textbf{0.9677}. These results suggest that incorporating morphology learning from heterogeneous sources offers a more robust and generalizable paradigm than conventional single-source training.
title Knowledge Augmentation via Synthetic Data: A Framework for Real-World ECG Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.21968