Beyond Single-Channel: Multichannel Signal Imaging for PPG-to-ECG Reconstruction with Vision Transformers

Reconstructing ECG from PPG is a promising yet challenging task. While recent advancements in generative models have significantly improved ECG reconstruction, accurately capturing fine-grained waveform features remains a key challenge. To address this, we propose a novel PPG-to-ECG reconstruction method that leverages a Vision Transformer (ViT) as the core network. Unlike conventional approaches that rely on single-channel PPG, our method employs a four-channel signal image representation, incorporating the original PPG, its first-order di ff erence, second-order di fference, and area under the curve. This multi-channel design enriches feature extraction by preserving both temporal and physiological variations within the PPG. Experimental results demonstrate that our method consistently outperforms existing 1D convolution-based approaches, achieving up to 29% reduction in PRD and 15% reduction in RMSE. The proposed approach also produces improvements in other evaluation metrics, highlighting its robustness and e ff ectiveness in reconstructing ECG signals. Furthermore, to ensure a clinically relevant evaluation, we introduce new performance metrics, including QRS area error, PR interval error, RT interval error, and RT amplitude di fference error. Beyond demonstrating the potential of PPG as a viable alternative for heart activity monitoring, our approach opens new avenues for cyclic signal analysis and prediction. Introduction Electrocardiograms (ECGs) are essential tools for diagnosing and monitoring cardiovascular health, providing crucial insights into heart rate variability (HRV), heart rate, and key waveform features. These include the QRS complex, PR interval, ST segment, TP interval, and QT interval, which are vital for understanding the heart's electrical activity and diagnosing various cardiac conditions [1, 2]. Prolonged PR intervals may indicate first-degree atrioventricular (A V) block or delayed conduction through the A V node, suggesting potential cardiac conduction issues [3]. Conversely, shortened PR intervals might imply conditions such as Wol ff-Parkinson-White (WPW) syndrome or Lown-Ganong-Levine syndrome, where accessory pathways bypass the normal A V nodal delay [3].