Application of semi-supervised deep learning to lung sound analysis

Abstract

The analysis of lung sounds, collected through auscultation, is a fundamental component of pulmonary disease diagnostics for primary care and general patient monitoring for telemedicine. Despite advances in computation and algorithms, the goal of automated lung sound identification and classification has remained elusive. Over the past 40 years, published work in this field has demonstrated only limited success in identifying lung sounds, with most published studies using only a small numbers of patients (typically N<;20) and usually limited to a single type of lung sound. Larger research studies have also been impeded by the challenge of labeling large volumes of data, which is extremely labor-intensive. In this paper, we present the development of a semi-supervised deep learning algorithm for automatically classify lung sounds from a relatively large number of patients (N=284). Focusing on the two most common lung sounds, wheeze and crackle, we present results from 11,627 sound files recorded from 11 different auscultation locations on these 284 patients with pulmonary disease. 890 of these sound files were labeled to evaluate the model, which is significantly larger than previously published studies. Data was collected with a custom mobile phone application and a low-cost (US$30) electronic stethoscope. On this data set, our algorithm achieves ROC curves with AUCs of 0.86 for wheeze and 0.74 for crackle. Most importantly, this study demonstrates how semi-supervised deep learning can be used with larger data sets without requiring extensive labeling of data.

The highs and lows of wheezing: A review of the most popular adventitious lung sound

“…Rapid advances in Artificial Intelligence such as “Deep Learning” that is already being successfully applied to speech processing have benefitted from the increasing sizes of data sets and computing power. Lung sound collection from hundreds or even thousands of adult subjects have created a wealth of data that should lead to more accurate detection and detailed automatic characterization of wheezing. To date, however, there are no comparably large collections of wheeze‐type lung sounds in infants and young children.…”

Survey on deep learning for pulmonary medical imaging

“…Cengil et al [153] used deep learning for the classification of cancer types. A semi-supervised deep learning algorithm was proposed to automatically classify patients' lung sounds [154,155] (for the two most common lung sounds, wheezing and bursting). The algorithm made some progress in automatic lung sound recognition and classification.…”

Semi-Supervised Approach Using Nearest Neighbors Clustering and Deep Learning

“…In Chamberlain et al (2016) it is presented the development of a semi-supervised deep learning algorithm for automatically classify lung sounds using a Convolutional Neural Network, this paper solver a specificy problem with Deep Semi-supervised.…”