Multi-channel lung sound classification with convolutional recurrent neural networks. (July 2020)

• Record Type: Journal Article
• Authors: Messner, Elmar; Fediuk, Melanie; Swatek, Paul; Scheidl, Stefan; Smolle-Jüttner, Freyja-Maria; Olschewski, Horst; Pernkopf, Franz
• Is Part Of: Computers in biology and medicine. Volume 122(2020)
• Publication Date: 2020-07
• Subjects: Auscultation -- Multi-channel lung sound classification -- Deep learning -- Convolutional recurrent neural networks -- Pulmonary fibrosis; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.103831
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: 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. Highlights: Multi-channel lung sound classification with Convolutional Recurrent Neural Networks. Multi-channel lung sound database. Comparison of different neural network architectures.