2 files

Automatic wheeze segmentation using harmonic-percussive source separation and empirical mode decomposition

Download all (2.8 MB)
posted on 2022-05-17, 02:34 authored by Bruno RochaBruno Rocha, Diogo Pessoa, Alda Marques, Paulo Carvalho, Rui Pedro Paiva
Wheezes are adventitious respiratory sounds commonly present in patients with respiratory conditions. The presence of wheezes and their time location are relevant for clinical reasons, such as understanding the degree of bronchial obstruction. Conventional auscultation is usually employed to analyze wheezes, but remote monitoring has become a pressing need during recent years. Automatic respiratory sound analysis is required to reliably perform remote auscultation. In this work we propose a method for wheeze segmentation. Our method starts by decomposing a given audio excerpt into intrinsic mode frequencies using empirical mode decomposition. Then, we apply harmonic-percussive source separation to the resulting audio tracks and get harmonic-enhanced spectrograms, which are processed to obtain harmonic masks. Subsequently, a series of empirically derived rules are applied to find wheeze candidates. Finally, the candidates stemming from the different audio tracks are merged and median filtered. In the evaluation stage, we compare our method to three baselines on the ICBHI 2017 Respiratory Sound Database, a challenging dataset containing various noise sources and background sounds. Using the full dataset, our method outperforms the baselines, achieving an F1 of 41.9%. Our method's performance is also better than the baselines across several stratified results focusing on five variables: recording equipment, age, sex, body-mass index, and diagnosis. We conclude that, contrary to what has been reported in the literature, wheeze segmentation has not been solved for real life scenario applications. Adaptation of existing systems to demographic characteristics might be a promising step in the direction of algorithm personalization, which would make automatic wheeze segmentation methods clinically viable.


Wearable Electronics for Effective Lung Monitoring

European Commission

Find out more...


Aveiro Institute of Biomedicine

Fundação para a Ciência e Tecnologia

Find out more...

Automatic Analysis of Cough and Adventitious Respiratory Sounds

Fundação para a Ciência e Tecnologia

Find out more...


Ferramentas avançadas para diagnóstico e prognóstico em pneumologia @ Cuidados intensivos

Fundação para a Ciência e Tecnologia

Find out more...


Email Address of Submitting Author

ORCID of Submitting Author


Submitting Author's Institution

University of Coimbra, Centre for Informatics and Systems, Department of Informatics Engineering

Submitting Author's Country