Convolutional Neural Networks for the Classification of Bronchopulmonary System Diseases with the Use of Lung Sounds

Abstract

This study suggests the use of convolutional neural networks for the classification of bronchopulmonary system diseases, by considering the lung sounds as an image that called spectrogram. Analyzing images and getting a set of parameters, there is the possibility of training and getting certain classifiers. Subsequently, the use of this method can help pulmonologist make a correct diagnosis.