Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

In this paper, we present a method for event detection in single-channel lung sound recordings. This includes the detection of crackles and breathing phase events (inspiration/expiration). Therefore, we propose an event detection approach with spectral features and bidirectional gated recurrent neural networks (BiGRNNs). In our experiments, we use multichannel lung sound recordings from lung-healthy subjects and patients diagnosed with idiopathic pulmonary fibrosis, collected within a clinical trial. We achieve an event-based F-score of F1 ≈ 86% for breathing phase events and F1 ≈ 72% for crackles. The proposed method shows robustness regarding the contamination of the lung sound recordings with noise, bowel and heart sounds.

[1]  A. Bohadana,et al.  Fundamentals of lung auscultation. , 2014, The New England journal of medicine.

[2]  Mohammed Bahoura,et al.  An Automatic System for Crackles Detection and Classification , 2006, 2006 Canadian Conference on Electrical and Computer Engineering.

[3]  A. Vyshedskiy,et al.  Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis , 2010, Pulmonary medicine.

[4]  H. Pasterkamp,et al.  Computerised acoustical respiratory phase detection without airflow measurement , 2000, Medical and Biological Engineering and Computing.

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Cristina Jácome,et al.  Automatic Crackle Detection Algorithm Based on Fractal Dimension and Box Filtering , 2015, CENTERIS/ProjMAN/HCist.

[9]  V. Cottin,et al.  Velcro crackles: the key for early diagnosis of idiopathic pulmonary fibrosis? , 2012, European Respiratory Journal.

[10]  Surya Ganguli,et al.  Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , 2013, ICLR.

[11]  Yoshua Bengio,et al.  Gated Feedback Recurrent Neural Networks , 2015, ICML.

[12]  Franz Pernkopf,et al.  A Robust Multichannel Lung Sound Recording Device , 2016, BIODEVICES.

[13]  Zahra Moussavi,et al.  Automated detection of respiratory phases by acoustical means , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Annamaria Mesaros,et al.  Metrics for Polyphonic Sound Event Detection , 2016 .

[16]  Nizamettin Aydin,et al.  Pulmonary crackle detection using time-frequency and time-scale analysis , 2013, Digit. Signal Process..

[17]  Luca Richeldi,et al.  Neglected evidence in idiopathic pulmonary fibrosis and the importance of early diagnosis and treatment , 2014, European Respiratory Review.

[18]  Z. Moussavi,et al.  Automatic breath phase detection using only tracheal sounds , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[19]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[20]  Franz Pernkopf,et al.  Gated Recurrent Networks applied to Acoustic Scene Classification , 2016, DCASE.

[21]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.