A Self-Attention-Driven Deep Denoiser Model for Real Time Lung Sound Denoising in Noisy Environments

TL;DR

This paper introduces Uformer, a deep learning model combining CNN and Transformer modules, designed for real-time lung sound denoising in noisy environments, significantly improving signal clarity and aiding respiratory monitoring.

Contribution

The study presents a novel Uformer model that effectively denoises lung sounds using a hybrid CNN-Transformer architecture, outperforming existing models in noisy conditions.

Findings

Achieved an average SNR improvement of 16.51 dB on synthetic noise.

Outperformed existing models with an average SNR improvement of 19.31 dB.

Demonstrated robustness and generalization in real-world noisy environments.

Abstract

Objective: Lung auscultation is a valuable tool in diagnosing and monitoring various respiratory diseases. However, lung sounds (LS) are significantly affected by numerous sources of contamination, especially when recorded in real-world clinical settings. Conventional denoising models prove impractical for LS denoising, primarily owing to spectral overlap complexities arising from diverse noise sources. To address this issue, we propose a specialized deep-learning model (Uformer) for lung sound denoising. Methods: The proposed Uformer model is constituted of three modules: a Convolutional Neural Network (CNN) encoder module, dedicated to extracting latent features; a Transformer encoder module, employed to further enhance the encoding of unique LS features and effectively capture intricate long-range dependencies; and a CNN decoder module, employed to generate the denoised signals. An ablation study was performed in order to find the most optimal architecture. Results: The performance of the proposed Uformer model was evaluated on lung sounds induced with different types of synthetic and real-world noises. Lung sound signals of -12 dB to 15 dB signal-to-noise ratio (SNR) were considered in testing experiments. The proposed model showed an average SNR improvement of 16.51 dB when evaluated with -12 dB LS signals. Our end-to-end model, with an average SNR improvement of 19.31 dB, outperforms the existing model when evaluated with ambient noise and fewer parameters. Conclusion: Based on the qualitative and quantitative findings in this study, it can be stated that Uformer is robust and generalized to be used in assisting the monitoring of respiratory conditions.