Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

Elmar Messner; Melanie Fediuk; Paul Swatek; Stefan Scheidl; Freyja Maria Smolle-Juttner; Horst Olschewski; Franz Pernkopf

doi:10.1109/EMBC.2018.8512237

Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

Elmar Messner
, Melanie Fediuk
, Paul Swatek
, Stefan Scheidl
, Freyja Maria Smolle-Juttner
, Horst Olschewski
, Franz Pernkopf

Institute of Signal Processing and Speech Communication (4420)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

In this paper, we present a method for event detection in single-channel lung sound recordings. This includes the detection of crackles and breathing phase events (inspiration/expiration). Therefore, we propose an event detection approach with spectral features and bidirectional gated recurrent neural networks (BiGRNNs). In our experiments, we use multichannel lung sound recordings from lung-healthy subjects and patients diagnosed with idiopathic pulmonary fibrosis, collected within a clinical trial. We achieve an event-based F-score of F₁ ≈ 86% for breathing phase events and F₁ ≈ 72% for crackles. The proposed method shows robustness regarding the contamination of the lung sound recordings with noise, bowel and heart sounds.

Original language	English
Title of host publication	40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
Publisher	IEEE
Pages	356-359
Number of pages	4
Volume	2018-July
ISBN (Electronic)	9781538636466
DOIs	https://doi.org/10.1109/EMBC.2018.8512237
Publication status	Published - 26 Oct 2018
Event	40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: EMBC 2018 - Honolulu, United States Duration: 18 Jul 2018 → 21 Jul 2018

Conference

Conference	40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Country/Territory	United States
City	Honolulu
Period	18/07/18 → 21/07/18

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/EMBC.2018.8512237

Cite this

Messner, E., Fediuk, M., Swatek, P., Scheidl, S., Smolle-Juttner, F. M., Olschewski, H., & Pernkopf, F. (2018). Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (Vol. 2018-July, pp. 356-359). Article 8512237 IEEE. https://doi.org/10.1109/EMBC.2018.8512237

Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks. / Messner, Elmar; Fediuk, Melanie; Swatek, Paul et al.
40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July IEEE, 2018. p. 356-359 8512237.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Messner, E, Fediuk, M, Swatek, P, Scheidl, S, Smolle-Juttner, FM, Olschewski, H & Pernkopf, F 2018, Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. vol. 2018-July, 8512237, IEEE, pp. 356-359, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, United States, 18/07/18. https://doi.org/10.1109/EMBC.2018.8512237

Messner E, Fediuk M, Swatek P, Scheidl S, Smolle-Juttner FM, Olschewski H et al. Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July. IEEE. 2018. p. 356-359. 8512237 doi: 10.1109/EMBC.2018.8512237

@inproceedings{4a5d91d8aede42fcbaffc06f87c52afe,

title = "Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks",

abstract = "In this paper, we present a method for event detection in single-channel lung sound recordings. This includes the detection of crackles and breathing phase events (inspiration/expiration). Therefore, we propose an event detection approach with spectral features and bidirectional gated recurrent neural networks (BiGRNNs). In our experiments, we use multichannel lung sound recordings from lung-healthy subjects and patients diagnosed with idiopathic pulmonary fibrosis, collected within a clinical trial. We achieve an event-based F-score of F1 ≈ 86\% for breathing phase events and F1 ≈ 72\% for crackles. The proposed method shows robustness regarding the contamination of the lung sound recordings with noise, bowel and heart sounds.",

author = "Elmar Messner and Melanie Fediuk and Paul Swatek and Stefan Scheidl and Smolle-Juttner, \{Freyja Maria\} and Horst Olschewski and Franz Pernkopf",

year = "2018",

month = oct,

day = "26",

doi = "10.1109/EMBC.2018.8512237",

language = "English",

volume = "2018-July",

pages = "356--359",

booktitle = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018",

publisher = "IEEE",

address = "United States",

note = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : EMBC 2018 ; Conference date: 18-07-2018 Through 21-07-2018",

}

TY - GEN

T1 - Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

AU - Messner, Elmar

AU - Fediuk, Melanie

AU - Swatek, Paul

AU - Scheidl, Stefan

AU - Smolle-Juttner, Freyja Maria

AU - Olschewski, Horst

AU - Pernkopf, Franz

PY - 2018/10/26

Y1 - 2018/10/26

N2 - In this paper, we present a method for event detection in single-channel lung sound recordings. This includes the detection of crackles and breathing phase events (inspiration/expiration). Therefore, we propose an event detection approach with spectral features and bidirectional gated recurrent neural networks (BiGRNNs). In our experiments, we use multichannel lung sound recordings from lung-healthy subjects and patients diagnosed with idiopathic pulmonary fibrosis, collected within a clinical trial. We achieve an event-based F-score of F1 ≈ 86% for breathing phase events and F1 ≈ 72% for crackles. The proposed method shows robustness regarding the contamination of the lung sound recordings with noise, bowel and heart sounds.

AB - In this paper, we present a method for event detection in single-channel lung sound recordings. This includes the detection of crackles and breathing phase events (inspiration/expiration). Therefore, we propose an event detection approach with spectral features and bidirectional gated recurrent neural networks (BiGRNNs). In our experiments, we use multichannel lung sound recordings from lung-healthy subjects and patients diagnosed with idiopathic pulmonary fibrosis, collected within a clinical trial. We achieve an event-based F-score of F1 ≈ 86% for breathing phase events and F1 ≈ 72% for crackles. The proposed method shows robustness regarding the contamination of the lung sound recordings with noise, bowel and heart sounds.

UR - https://www.scopus.com/pages/publications/85052711640

U2 - 10.1109/EMBC.2018.8512237

DO - 10.1109/EMBC.2018.8512237

M3 - Conference paper

C2 - 30440410

AN - SCOPUS:85052711640

VL - 2018-July

SP - 356

EP - 359

BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018

PB - IEEE

T2 - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 18 July 2018 through 21 July 2018

ER -

Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

CULA - Computerized Lung Sound Analysis

Cite this

Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Projects

CULA - Computerized Lung Sound Analysis

Cite this