Computers in Biology and Medicine ( IF 7.0 ) Pub Date : 2020-05-23 , DOI: 10.1016/j.compbiomed.2020.103831 Elmar Messner 1 , Melanie Fediuk 2 , Paul Swatek 2 , Stefan Scheidl 3 , Freyja-Maria Smolle-Jüttner 2 , Horst Olschewski 3 , Franz Pernkopf 1
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 . Together with our multi-channel lung sound recording device, we present a holistic approach to multi-channel lung sound analysis.
中文翻译:
卷积递归神经网络的多通道肺部声音分类。
在本文中,我们提出了一种利用频谱,时间和空间信息进行多通道肺部声音分类的方法。特别是,我们提出了一种逐帧分类框架,以利用卷积循环神经网络处理多通道肺部录音的完整呼吸周期。借助我们最近开发的16通道肺部录音设备,我们在一项临床试验中收集了来自肺部健康受试者和特发性肺纤维化(IPF)患者的肺部录音。从肺部录音中,我们提取了频谱图特征,并比较了不同的深层神经网络体系结构以进行二进制分类,即健康与病理学。我们提出的带有卷积递归神经网络的分类框架通过获得F分数来胜过其他网络。与我们的多通道肺部声音记录设备一起,我们提出了一种用于多通道肺部声音分析的整体方法。