Interpretation of lung disease classification with light attention connected module

• Published in: Biomedical signal processing and control 2023-07, Vol.84, p.104695-104695, Article 104695
• Main Authors: Choi, Youngjin, Lee, Hongchul
• Format: Article
• Language: English
• Subjects: Attention; ECA-Net; eXplainable AI; Grad-CAM; Lung disease; Respiratory sound
• ISSN: 1746-8094; 1746-8108; 1746-8094
• DOI: 10.1016/j.bspc.2023.104695

•Novel lung disease classification model using attention module and deep learning.•Light attention connected module with improved VGGish model.•Depthwise separable convolution for weight reduction and parameter minimization.•High accuracy of 92.56%, precision of 92.81%, sensitivity of 92.22%, specificity of 98.50%, f1-score of 92.29%, and balanced accuracy of 95.4%.•Using XAI to analyze the cause of disease classification and check respiratory symptoms by clinicians. Lung diseases lead to complications from obstructive diseases, and the COVID-19 pandemic has increased lung disease-related deaths. Medical practitioners use stethoscopes to diagnose lung disease. However, an artificial intelligence model capable of objective judgment is required since the experience and diagnosis of respiratory sounds differ. Therefore, in this study, we propose a lung disease classification model that uses an attention module and deep learning. Respiratory sounds were extracted using log-Mel spectrogram MFCC. Normal and five types of adventitious sounds were effectively classified by improving VGGish and adding a light attention connected module to which the efficient channel attention module (ECA-Net) was applied. The performance of the model was evaluated for accuracy, precision, sensitivity, specificity, f1-score, and balanced accuracy, which were 92.56%, 92.81%, 92.22%, 98.50%, 92.29%, and 95.4%, respectively. We confirmed high performance according to the attention effect. The classification causes of lung diseases were analyzed using gradient-weighted class activation mapping (Grad-CAM), and the performances of their models were compared using open lung sounds measured using a Littmann 3200 stethoscope. The experts’ opinions were also included. Our results will contribute to the early diagnosis and interpretation of diseases in patients with lung disease by utilizing algorithms in smart medical stethoscopes.