Cargando…

Data augmentation using Variational Autoencoders for improvement of respiratory disease classification

Computerized auscultation of lung sounds is gaining importance today with the availability of lung sounds and its potential in overcoming the limitations of traditional diagnosis methods for respiratory diseases. The publicly available ICBHI respiratory sounds database is severely imbalanced, making...

Descripción completa

Detalles Bibliográficos
Autores principales: Saldanha, Jane, Chakraborty, Shaunak, Patil, Shruti, Kotecha, Ketan, Kumar, Satish, Nayyar, Anand
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9374267/
https://www.ncbi.nlm.nih.gov/pubmed/35960763
http://dx.doi.org/10.1371/journal.pone.0266467
_version_ 1784767753988603904
author Saldanha, Jane
Chakraborty, Shaunak
Patil, Shruti
Kotecha, Ketan
Kumar, Satish
Nayyar, Anand
author_facet Saldanha, Jane
Chakraborty, Shaunak
Patil, Shruti
Kotecha, Ketan
Kumar, Satish
Nayyar, Anand
author_sort Saldanha, Jane
collection PubMed
description Computerized auscultation of lung sounds is gaining importance today with the availability of lung sounds and its potential in overcoming the limitations of traditional diagnosis methods for respiratory diseases. The publicly available ICBHI respiratory sounds database is severely imbalanced, making it difficult for a deep learning model to generalize and provide reliable results. This work aims to synthesize respiratory sounds of various categories using variants of Variational Autoencoders like Multilayer Perceptron VAE (MLP-VAE), Convolutional VAE (CVAE) Conditional VAE and compare the influence of augmenting the imbalanced dataset on the performance of various lung sound classification models. We evaluated the quality of the synthetic respiratory sounds’ quality using metrics such as Fréchet Audio Distance (FAD), Cross-Correlation and Mel Cepstral Distortion. Our results showed that MLP-VAE achieved an average FAD of 12.42 over all classes, whereas Convolutional VAE and Conditional CVAE achieved an average FAD of 11.58 and 11.64 for all classes, respectively. A significant improvement in the classification performance metrics was observed upon augmenting the imbalanced dataset for certain minority classes and marginal improvement for the other classes. Hence, our work shows that deep learning-based lung sound classification models are not only a promising solution over traditional methods but can also achieve a significant performance boost upon augmenting an imbalanced training set.
format Online
Article
Text
id pubmed-9374267
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93742672022-08-13 Data augmentation using Variational Autoencoders for improvement of respiratory disease classification Saldanha, Jane Chakraborty, Shaunak Patil, Shruti Kotecha, Ketan Kumar, Satish Nayyar, Anand PLoS One Research Article Computerized auscultation of lung sounds is gaining importance today with the availability of lung sounds and its potential in overcoming the limitations of traditional diagnosis methods for respiratory diseases. The publicly available ICBHI respiratory sounds database is severely imbalanced, making it difficult for a deep learning model to generalize and provide reliable results. This work aims to synthesize respiratory sounds of various categories using variants of Variational Autoencoders like Multilayer Perceptron VAE (MLP-VAE), Convolutional VAE (CVAE) Conditional VAE and compare the influence of augmenting the imbalanced dataset on the performance of various lung sound classification models. We evaluated the quality of the synthetic respiratory sounds’ quality using metrics such as Fréchet Audio Distance (FAD), Cross-Correlation and Mel Cepstral Distortion. Our results showed that MLP-VAE achieved an average FAD of 12.42 over all classes, whereas Convolutional VAE and Conditional CVAE achieved an average FAD of 11.58 and 11.64 for all classes, respectively. A significant improvement in the classification performance metrics was observed upon augmenting the imbalanced dataset for certain minority classes and marginal improvement for the other classes. Hence, our work shows that deep learning-based lung sound classification models are not only a promising solution over traditional methods but can also achieve a significant performance boost upon augmenting an imbalanced training set. Public Library of Science 2022-08-12 /pmc/articles/PMC9374267/ /pubmed/35960763 http://dx.doi.org/10.1371/journal.pone.0266467 Text en © 2022 Saldanha et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Saldanha, Jane
Chakraborty, Shaunak
Patil, Shruti
Kotecha, Ketan
Kumar, Satish
Nayyar, Anand
Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title_full Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title_fullStr Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title_full_unstemmed Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title_short Data augmentation using Variational Autoencoders for improvement of respiratory disease classification
title_sort data augmentation using variational autoencoders for improvement of respiratory disease classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9374267/
https://www.ncbi.nlm.nih.gov/pubmed/35960763
http://dx.doi.org/10.1371/journal.pone.0266467
work_keys_str_mv AT saldanhajane dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification
AT chakrabortyshaunak dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification
AT patilshruti dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification
AT kotechaketan dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification
AT kumarsatish dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification
AT nayyaranand dataaugmentationusingvariationalautoencodersforimprovementofrespiratorydiseaseclassification