Messner Elmar, Fediuk Melanie, Swatek Paul, Scheidl Stefan, Smolle-Jüttner Freyja-Maria, Olschewski Horst, Pernkopf Franz
Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria.
Division of Thoracic and Hyperbaric Surgery, Medical University of Graz, Graz, Austria.
Comput Biol Med. 2020 Jul;122:103831. doi: 10.1016/j.compbiomed.2020.103831. Epub 2020 May 23.
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≈92%. Together with our multi-channel lung sound recording device, we present a holistic approach to multi-channel lung sound analysis.
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音分类的方法。具体而言，我们提出了一个逐帧分类框架，用于使用卷积循环神经网络处理多通道肺音记录的完整呼吸周期。通过我们最近开发的16通道肺音记录设备，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）患者的肺音记录。从肺音记录中，我们提取频谱图特征，并比较不同的深度神经网络架构进行二元分类，即健康与病理分类。我们提出的带有卷积循环神经网络的分类框架以F≈92%的F分数优于其他网络。连同我们的多通道肺音记录设备，我们提出了一种多通道肺音分析的整体方法。
