Abnormal Respiratory Sound Identification Using Audio-Spectrogram Vision Transformer

TL;DR

This paper introduces a novel audio-spectrogram vision transformer approach for identifying abnormal respiratory sounds, leveraging spectrogram analysis and deep learning to improve diagnostic accuracy in lung disorder detection.

Contribution

The study develops and evaluates a new vision transformer-based model (AS-ViT) for respiratory sound classification using spectrograms, achieving superior results over existing methods.

Findings

Achieved 79.1% unweighted average recall with 60:40 split.

Achieved 86.4% unweighted average recall with 80:20 split.

Surpassed previous state-of-the-art in respiratory sound detection.

Abstract

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.