Lung Sound Classification Using Co-Tuning and Stochastic Normalization

Computational methods for lung sound analysis are beneficial for computer-aided diagnosis support, storage and monitoring in critical care. In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases. The learned representation of the pre-trained model is transferred by using vanilla fine-tuning, co-tuning, stochastic normalization and the combination of the co-tuning and stochastic normalization techniques. Furthermore, data augmentation in both time domain and time-frequency domain is used to account for the class imbalance of the ICBHI and our multi-channel lung sound dataset. Additionally, we introduce spectrum correction to account for the variations of the recording device properties on the ICBHI dataset. Empirically, our proposed systems mostly outperform all state-of-the-art lung sound classification systems for the adventitious lung sounds and respiratory diseases of both datasets.

Automated summary

Computational methods for lung sound analysis are used for computer-aided diagnosis support, storage, and monitoring in critical care. This paper proposes a method that uses pre-trained ResNet models for the classification of adventitious lung sounds and respiratory diseases. The method incorporates techniques such as fine-tuning, co-tuning, stochastic normalization, and data augmentation to improve performance. The experimental results show that the proposed systems outperform state-of-the-art lung sound classification systems.