Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers
Open Access
Abstract
Early identification of respiratory irregularities is critical for improving lung health and reducing global mortality rates. The analysis of respiratory sounds plays a significant role in characterizing the respiratory system’s condition and identifying abnormalities. The main contribution of this study is to investigate the performance when the input data, represented by cochleogram, is used to feed the Vision Transformer (ViT) architecture, since this input–classifier combination is the first time it has been applied to adventitious sound classification to our knowledge. Although ViT has shown promising results in audio classification tasks by applying self-attention to spectrogram patches, we extend this approach by applying the cochleogram, which captures specific spectro-temporal features of adventitious sounds. The proposed methodology is evaluated on the ICBHI dataset. We compare the classification performance of ViT with other state-of-the-art CNN approaches using spectrogram, Mel frequency cepstral coefficients, constant-Q transform, and cochleogram as input data. Our results confirm the superior classification performance combining cochleogram and ViT, highlighting the potential of ViT for reliable respiratory sound classification. This study contributes to the ongoing efforts in developing automatic intelligent techniques with the aim to significantly augment the speed and effectiveness of respiratory disease detection, thereby addressing a critical need in the medical field.Keywords
All Related Versions
Funding Information
- MCIN/AEI/10.13039/501100011033 (PID2020-119082RB-{C21,C22}, P18-RT-1994)
- Ministry of Economy, Knowledge and University, Junta de Andalucía, Spain (PID2020-119082RB-{C21,C22}, P18-RT-1994)
This publication has 106 references indexed in Scilit:
- Pulmonary crackle detection using time–frequency and time–scale analysisDigital Signal Processing, 2013
- Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patientsComputers in Biology and Medicine, 2011
- Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classesComputers in Biology and Medicine, 2009
- An integrated automated system for crackles extraction and classificationBiomedical Signal Processing and Control, 2008
- Wheeze detection based on time-frequency analysis of breath soundsComputers in Biology and Medicine, 2007
- Wavelet-Based Enhancement of Lung and Bowel Sounds Using Fractal Dimension Thresholding —Part II: Application ResultsIEEE Transactions on Biomedical Engineering, 2005
- The Relationship between Normal Lung Sounds, Age, and GenderAmerican Journal of Respiratory and Critical Care Medicine, 2000
- Respiratory SoundsAmerican Journal of Respiratory and Critical Care Medicine, 1997
- Validated method for automatic detection of lung sound cracklesMedical & Biological Engineering & Computing, 1991
- On a Test of Whether one of Two Random Variables is Stochastically Larger than the OtherThe Annals of Mathematical Statistics, 1947