Classification of lung sounds using convolutional neural networks

• Published in: EURASIP journal on image and video processing Vol. 2017; no. 1; pp. 1 - 9
• Main Authors: Aykanat, Murat, Kılıç, Özkan, Kurt, Bahar, Saryal, Sevgi
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 11.09.2017; Springer Nature B.V; SpringerOpen
• Subjects: Acoustics; Algorithms; Applications of Visual Analysis of Human Behaviour; Artificial intelligence; Artificial neural networks; Audio data; Biometrics; Classification; Convolutional neural networks; Deep learning; Diagnostic systems; Engineering; Image classification; Image Processing and Computer Vision; Lung sounds; Machine learning; Neural networks; Pattern Recognition; Signal,Image and Speech Processing; Sound; Support vector machines; Deep learning; Convolutional neural networks; Lung sounds; Machine learning
• ISSN: 1687-5281; 1687-5176; 1687-5281
• DOI: 10.1186/s13640-017-0213-2

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms. In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects. We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively. As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.