What is the clinical evidence from this study?

Study design: Other. Population: Lung diseases (lung sound classification) (n=920). Intervention: Deep feature extraction (VGG-16 CNN) and SVM classifier vs. Transfer learning (VGG-16) and softmax classifier. Primary outcome: Classification accuracy.

December 23, 2019Open Access

Convolutional neural networks based efficient approach for classification of lung diseases

Key Result

A deep feature extraction approach using a pre-trained VGG-16 convolutional neural network model and SVM classifier achieved 65.5% accuracy in classifying lung sounds.

Structured PICO

Population

Lung sound signals from the ICBHI 2017 database (including different sample frequencies, noise, and background sounds)

Intervention

Deep learning based approaches: pre-trained deep CNN model for feature extraction with SVM classifier, and fine-tuned pre-trained deep CNN model (transfer learning) via spectrogram images

Comparator

Existing classification methods

Outcome

Classification accuracy of lung sounds

A deep learning approach using CNNs and spectrogram images achieved up to 65.5% accuracy in classifying lung sounds from the ICBHI 2017 database.

Main Result

Absolute Event Rate: 65.5% vs 63.09%

Abstract

Treatment of lung diseases, which are the third most common cause of death in the world, is of great importance in the medical field. Many studies using lung sounds recorded with stethoscope have been conducted in the literature in order to diagnose the lung diseases with artificial intelligence-compatible devices and to assist the experts in their diagnosis. In this paper, ICBHI 2017 database which includes different sample frequencies, noise and background sounds was used for the classification of lung sounds. The lung sound signals were initially converted to spectrogram images by using time-frequency method. The short time Fourier transform (STFT) method was considered as time-frequency transformation. Two deep learning based approaches were used for lung sound classification. In the first approach, a pre-trained deep convolutional neural networks (CNN) model was used for feature extraction and a support vector machine (SVM) classifier was used in classification of the lung sounds. In the second approach, the pre-trained deep CNN model was fine-tuned (transfer learning) via spectrogram images for lung sound classification. The accuracies of the proposed methods were tested by using the ten-fold cross validation. The accuracies for the first and second proposed methods were 65.5% and 63.09%, respectively. The obtained accuracies were then compared with some of the existing results and it was seen that obtained scores were better than the other results.

Mark Helpful

Bookmark

Relay

View Full Paper