Abnormal Respiratory Sound Identification Using Audio-Spectrogram Vision Transformer
This work addresses respiratory disease diagnosis, a critical global health issue, by providing an AI tool to aid specialists, though it appears incremental as it builds on existing vision transformer and spectrogram techniques.
The study tackled the problem of identifying abnormal respiratory sounds from stethoscope recordings by developing an audio-spectrogram vision transformer (AS-ViT) method, which achieved up to 86.4% unweighted average recall and 69.3% overall score on the ICBHI 2017 database, surpassing previous state-of-the-art results.
Respiratory disease, the third leading cause of deaths globally, is considered a high-priority ailment requiring significant research on identification and treatment. Stethoscope-recorded lung sounds and artificial intelligence-powered devices have been used to identify lung disorders and aid specialists in making accurate diagnoses. In this study, audio-spectrogram vision transformer (AS-ViT), a new approach for identifying abnormal respiration sounds, was developed. The sounds of the lungs are converted into visual representations called spectrograms using a technique called short-time Fourier transform (STFT). These images are then analyzed using a model called vision transformer to identify different types of respiratory sounds. The classification was carried out using the ICBHI 2017 database, which includes various types of lung sounds with different frequencies, noise levels, and backgrounds. The proposed AS-ViT method was evaluated using three metrics and achieved 79.1% and 59.8% for 60:40 split ratio and 86.4% and 69.3% for 80:20 split ratio in terms of unweighted average recall and overall scores respectively for respiratory sound detection, surpassing previous state-of-the-art results.