ECG signal denoising based on multi-scale residual dense U-Net

The electrocardiogram (ECG) can provide detailed information about the rhythm and function of the heart, and provide guidance for doctors. However, the ECG signals are susceptible to be contaminated by noise, which affects the accuracy of the waveforms. In view of this, a denoising method for ECG signals based on multi-scale residual dense U-Net is proposed. A dual-branch residual dense block is proposed, which realizes the adaptive extraction of local multi-scale features of ECG signals. By integrating the block into the up-sampling and down-sampling of U-Net, the multi-scale features of ECG signals can be extracted. By reducing the size of the feature maps, the down-sampling can realize a better trade-off between efficiency and effectiveness in exploiting the hierarchical features. By skip connection, the restored features from up-sampling are fused with the down-sampling features, and are transferred to the dual-branch residual dense block. This operation avoids the information loss and captures more accurate contextual information. It has been verified that the waveforms obtained by this method are basically consistent with the waveforms of the clean signals and effectively retains the important waveform information of the ECG signals.