TY - JOUR
T1 - Multi-channel Lung Sound Classification with Convolutional Recurrent Neural Networks
AU - Messner, Elmar
AU - Fediuk, Melanie
AU - Swatek, Paul
AU - Scheidl, Stefan
AU - Smolle-Jüttner, Maria
AU - Olschewski, Horst
AU - Pernkopf, Franz
PY - 2020
Y1 - 2020
N2 - In this paper, we present an approach for multi-channel lung sound classification, exploiting spectral, temporal and spatial information. In particular, we propose a frame-wise classification framework to process full breathing cycles of multi-channel lung sound recordings with a convolutional recurrent neural network. With our recently developed 16-channel lung sound recording device, we collect lung sound recordings from lung-healthy subjects and patients with idiopathic pulmonary fibrosis (IPF), within a clinical trial. From the lung sound recordings, we extract spectrogram features and compare different deep neural network architectures for binary classification, i.e. healthy vs. pathological. Our proposed classification framework with the convolutional recurrent neural network outperforms the other networks by achieving an F-score of F
1≈92%. Together with our multi-channel lung sound recording device, we present a holistic approach to multi-channel lung sound analysis.
AB - In this paper, we present an approach for multi-channel lung sound classification, exploiting spectral, temporal and spatial information. In particular, we propose a frame-wise classification framework to process full breathing cycles of multi-channel lung sound recordings with a convolutional recurrent neural network. With our recently developed 16-channel lung sound recording device, we collect lung sound recordings from lung-healthy subjects and patients with idiopathic pulmonary fibrosis (IPF), within a clinical trial. From the lung sound recordings, we extract spectrogram features and compare different deep neural network architectures for binary classification, i.e. healthy vs. pathological. Our proposed classification framework with the convolutional recurrent neural network outperforms the other networks by achieving an F-score of F
1≈92%. Together with our multi-channel lung sound recording device, we present a holistic approach to multi-channel lung sound analysis.
KW - Auscultation
KW - Convolutional recurrent neural networks
KW - Deep learning
KW - Multi-channel lung sound classification
KW - Pulmonary fibrosis
UR - http://www.scopus.com/inward/record.url?scp=85085690037&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2020.103831
DO - 10.1016/j.compbiomed.2020.103831
M3 - Article
SN - 0010-4825
VL - 122
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 103831
ER -