Periodicity-based nonlocal-means denoising method for electrocardiography in low SNR non-white noisy conditions

Nonlocal means (NLM) denoising, originally developed for non-neighborhood image filtering, might be appropriate for denoising electrocardiography (ECG). It was applied to ECG signals and achieved results comparable to those of other state-of-the-art filters. This study proposed periodic NLM filtering (pNLM) for ECG and tested it in various noise environments. To increase the original NLM denoising performance for ECG, pNLM search windows were selected based on ECG periodicity, reducing dissimilar patch effects and leading to better denoising performance. The algorithm was evaluated using the MIT-BIH arrhythmia database and quantitative metrics, such as signal-to-noise ratio (SNR) improvement, mean squared error (MSE), and percent root mean square difference (PRD). Experimental results showed that this novel denoising method increased denoising performance compared to the NLM method by 23.8%, 28.8% and 97.9% for white, pink, and electromyogram (EMG) noise, respectively, especially for low SNR input. In summary, the pNLM algorithm is effective for denoising three types of ECG noise.