Santiago-Fuentes Laura M, Charleston-Villalobos Sonia, Gonzalez-Camarena Ramon, Mejia-Avila Mayra, Mateos-Toledo Heidegger, Buendia-Roldan Ivette, Aljama-Corrales Tomas
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:2757-2760. doi: 10.1109/EMBC.2017.8037428.
Interstitial lung diseases (ILDs) have been increasing their relevance in loss of lives according to a recent world wide medical information. Idiopathic pulmonary fibrosis (IPF) and combined pulmonary fibrosis and emphysema syndrome (CPFES) belong to ILD class with the latter having a limited survival prognosis. In clinical environment high resolution computed tomography (HRCT) is used to detect CPFE; however, there is still controversy about the amount of emphysema observed in HRCT to declare CPFES. Consequently, to help in the diagnosis of CPFES to develop an alternative technique seems to be attractive. In this study, we propose a multichannel acoustic approach to discriminate between IPF and CPFES parameterizing the multichannel lung sounds information linearly and classifying it by neural networks (NN). The NN performance using different features provided values above 90% in the validation phase. Furthermore, to test the trained NN, the proposed approach was applied on new data from five patients 3 diagnosed by experts as CPFES and 2 with IPF. The univariate autoregressive model obtained the best classification followed by the feature vector formed by the percentile frequencies augmented by the total power of the acoustic information. Results indicate that multichannel acoustic analysis is promising to discern between these two ILDs.
根据最近的全球医学信息，间质性肺疾病（ILDs）在致死率方面的相关性一直在增加。特发性肺纤维化（IPF）和合并性肺纤维化和肺气肿综合征（CPFES）属于ILD类别，后者的生存预后有限。在临床环境中，高分辨率计算机断层扫描（HRCT）用于检测CPFE；然而，对于在HRCT中观察到的用于诊断CPFES的肺气肿量仍存在争议。因此，开发一种替代技术以帮助诊断CPFES似乎很有吸引力。在本研究中，我们提出了一种多通道声学方法，通过对多通道肺音信息进行线性参数化并利用神经网络（NN）对其进行分类，来区分IPF和CPFES。在验证阶段，使用不同特征的NN性能提供了高于90%的值。此外，为了测试训练好的NN，将所提出的方法应用于来自五名患者的新数据，其中3名被专家诊断为CPFES，2名被诊断为IPF。单变量自回归模型获得了最佳分类，其次是由声学信息总功率增强的百分位数频率形成的特征向量。结果表明，多通道声学分析有望区分这两种ILD。
