A CBAM-enhanced ResNet-18 architecture achieved a test accuracy of 0.9674 for paper-based ECG classification, outperforming a custom CNN reference model (accuracy 0.9022).
Does a CBAM-enhanced ResNet-18 architecture improve classification accuracy of paper-based ECG images compared to a custom CNN reference model?
A CBAM-enhanced ResNet-18 architecture with tailored preprocessing effectively classifies paper-based ECG images, outperforming a custom CNN reference model.
Absolute Event Rate: 0.9674% vs 0.9022%
Abstract Cardiovascular diseases (CVDs) remain a major cause of mortality worldwide, and electrocardiograms (ECGs) are an important non-invasive tool for diagnosis. However, many ECG records are still stored as scanned paper images containing grid interference, noise, and variable image quality, which complicates automated analysis. This study presents a framework for four-class ECG image classification directly from paper-based records, covering Normal, Myocardial Infarction (MI), Abnormal Heartbeat (HB), and Post-Myocardial Infarction (PMI). The proposed method combines a targeted preprocessing pipeline with a CBAM-enhanced ResNet-18 architecture. The preprocessing stages are designed to suppress non-diagnostic background interference while preserving clinically relevant waveform morphology, and the attention mechanism refines feature learning in both channel and spatial dimensions. Under a unified training strategy, the proposed model achieved a test accuracy of 0.9674 and a macro-F1 score of 0.9702 on the independent test set. In direct comparison under the same evaluation protocol, the custom CNN reference model achieved 0.9022 test accuracy and 0.8950 macro-F1, indicating clear gains from the proposed architecture. These findings suggest that the combination of tailored preprocessing and attention-enhanced residual learning is effective for paper-based ECG image classification and may provide useful support for automated analysis of legacy ECG archives and resource-limited clinical settings.
Liu et al. (Fri,) conducted a other in Cardiovascular diseases. CBAM-enhanced ResNet-18 architecture vs. Custom CNN reference model was evaluated on Test accuracy for four-class ECG image classification. A CBAM-enhanced ResNet-18 architecture achieved a test accuracy of 0.9674 for paper-based ECG classification, outperforming a custom CNN reference model (accuracy 0.9022).