Classification of Abnormal Lung Sounds Using Deep Learning

Fan Wang, Xiaochen Yuan, Bowen Meng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Lung sound is an important reference factor in determining respiratory diseases. In particular, automatic lung sound classification systems could be of great help in situations where medical professionals are unavailable. In this work, we preprocess the original lung sound signal to remove noise interference from the signal. The processed sound signal is generated as a spectrogram by a short-time Fourier transform. The spectrogram is classified by a deep learning network based on ResNet, thus identifying the respiratory cycle into four types: normal, crackle, wheeze, and both. To address the issue of varying time scales in spectrograms, we extend the respiratory cycles to a uniform fixed time. The official benchmark standards of the ICBHI 2017 challenge and the dataset partitioning scheme have been used to validate the proposed method. Experiments and comparisons show that the proposed method achieves promising results in the classification of the respiratory cycle.

Original languageEnglish
Title of host publication2023 8th International Conference on Signal and Image Processing, ICSIP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages506-510
Number of pages5
ISBN (Electronic)9798350397932
DOIs
Publication statusPublished - 2023
Event8th International Conference on Signal and Image Processing, ICSIP 2023 - Wuxi, China
Duration: 8 Jul 202310 Jul 2023

Publication series

Name2023 8th International Conference on Signal and Image Processing, ICSIP 2023

Conference

Conference8th International Conference on Signal and Image Processing, ICSIP 2023
Country/TerritoryChina
CityWuxi
Period8/07/2310/07/23

Keywords

  • classification
  • deep learning
  • health care
  • lung sound

Fingerprint

Dive into the research topics of 'Classification of Abnormal Lung Sounds Using Deep Learning'. Together they form a unique fingerprint.

Cite this