Key result
FG-DPUNet outperforms 2D-CEDNet in ECG denoising, improving average SNRimp by ~6 dB.
Why the study?
Motion artifacts in wearable ambulatory ECG frequently distort faint P and T waves, and existing denoising networks struggle to balance noise suppression with morphological waveform integrity needed for clinical diagnosis.
Does the FG-DPUNet deep learning framework improve ECG motion artifact suppression and P-QRS-T waveform morphological integrity compared to state-of-the-art denoising models and static fusion architectures in wearable and ambulatory ECG recordings?
Does the FG-DPUNet deep learning framework improve ECG motion artifact suppression and P-QRS-T waveform morphological integrity compared to state-of-the-art denoising models and static fusion architectures in wearable and ambulatory ECG recordings?
Answers are grounded in this paper and cite their sources.
FG-DPUNet substantially reduces motion artifacts while preserving diagnostically critical P- and T-wave morphologies in wearable ECG recordings with low computational latency suitable for real-time ambulatory monitoring.
Wearable electrocardiography (ECG) has significant clinical value in ambulatory monitoring. However, motion artifacts during daily activities frequently distort faint P/T waves, compromising diagnostic interpretation. Meanwhile, single-branch or static fusion U-Net-based networks struggle to balance effective noise suppression with waveform integrity. Existing denoising methods primarily optimize global metrics such as signal-to-noise ratio improvement ( S N R i m p ), percentage root-mean-square difference (PRD), and root mean square error (RMSE), overlooking that denoising distorts P-QRS-T waveform and thus affects clinical diagnosis. This paper presents FG-DPUNet (Feature-aware Gating Dual-Path U-Net), a framework tailored to address P/T diagnostic waveform distortion induced by motion artifacts in wearable ambulatory ECG monitoring. The framework employs heterogeneous dual branches with kernel sizes of k = 7 and k = 21 to extract multi-scale ECG features in parallel, and adaptively adjusts fusion weights via a dynamic gating mechanism that operates on shared shallow features to produce temporal weights. To quantitatively assess waveform recovery quality, we introduce the P-QRS-T weighted correlation degradation index ( D w ) and P/T wave peak deviation metrics ( Δ PR , Δ R T ), providing a waveform-aware quantitative evaluation approach. On the MIT-BIH dataset under standard additive noise testing, FG-DPUNet improves the average S N R i m p by 5.94 dB and reduces the average PRD from 63.87% to 10.07% compared with state-of-the-art (SOTA) methods. On the BUT real-world motion artifact dataset, cross-subject experiments demonstrate that our model improves D w by approximately 16% over static dual-branch structures, demonstrating improved morphological preservation under motion artifacts.
No takes yet. Share an insight, caveat, or question.
Lv et al. (2026) studied ECG motion artifact in wearable ambulatory cardiac monitoring (n=41). FG-DPUNet (Feature-aware Gating Dual-Path U-Net) vs. State-of-the-art ECG denoising methods (2D-CEDNet, 2D-SCEDNet, MrSeNet, TCDAE) and dual/single-branch U-Net ablation variants was evaluated on Average percentage root-mean-square difference (PRD) and signal-to-noise ratio improvement (SNRimp) on MIT-BIH dataset (MD -53.80% for PRD (SNRimp +5.94 dB: 12.69 dB vs 6.75 dB)). FG-DPUNet improved average SNRimp by 5.94 dB (12.69 vs 6.75 dB) and reduced average PRD from 63.87% to 10.07% compared with 2D-CEDNet on the MIT-BIH dataset.
Synapse has enriched 10 related papers. Consider them for comparative context: