Detection of breath cycles in pediatric lung sounds via an object detection-based transfer learning method

•YOLOv1-based model for pediatric breath cycle detection via transfer learning.•Fine-tuned model achieves an F1 score of 0.824 on pediatric lung sounds dataset.•Utilized log Mel spectrogram for effective respiratory sound feature extraction.•Model outperforms baseline in precision, recall, and avera...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical signal processing and control Jg. 105; S. 107693
Hauptverfasser: Park, Sa-Yoon, Park, Ji Soo, Lee, Jisoo, Lee, Hyesu, Kim, Yelin, Suh, Dong In, Kim, Kwangsoo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.07.2025
Schlagworte:
ISSN:1746-8094
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •YOLOv1-based model for pediatric breath cycle detection via transfer learning.•Fine-tuned model achieves an F1 score of 0.824 on pediatric lung sounds dataset.•Utilized log Mel spectrogram for effective respiratory sound feature extraction.•Model outperforms baseline in precision, recall, and average precision metrics.•Facilitates large-scale annotated lung sound database creation for pediatric care. Auscultation is critical for assessing the respiratory system in children; however, the lack of pediatric lung sound databases impedes the development of automated analysis tools. This study introduces an object detection-based transfer learning method to accurately predict breath cycles in pediatric lung sounds. We utilized a model based on the YOLOv1 architecture, initially pre-trained on an adult lung sound dataset (HF_Lung_v1) and subsequently fine-tuned on a pediatric dataset (SNUCH_Lung). The input feature was the log Mel spectrogram, which effectively captured the relevant frequency and temporal information. The pre-trained model achieved an F1 score of 0.900 ± 0.003 on the HF_Lung_v1 dataset. After fine-tuning, it reached an F1 score of 0.824 ± 0.009 on the SNUCH_Lung dataset, confirming the efficacy of transfer learning. This model surpassed the performance of a baseline model trained solely on the SNUCH_Lung dataset without transfer learning. We also explored the impact of segment length, width, and various audio feature extraction techniques; the optimal results were obtained with 15 s segments, a 2-second width, and the log Mel spectrogram. The model is promising for clinical applications, such as generating large-scale annotated datasets, visualizing and labeling individual breath cycles, and performing correlation analysis with physiological indicators. Future research will focus on expanding the pediatric lung sound database through auto-labeling techniques and integrating the model into stethoscopes for real-time analysis. This study highlights the potential of object detection-based transfer learning in enhancing the accuracy of breath cycle prediction in pediatric lung sounds and advancing pediatric respiratory sound analysis tools.
AbstractList •YOLOv1-based model for pediatric breath cycle detection via transfer learning.•Fine-tuned model achieves an F1 score of 0.824 on pediatric lung sounds dataset.•Utilized log Mel spectrogram for effective respiratory sound feature extraction.•Model outperforms baseline in precision, recall, and average precision metrics.•Facilitates large-scale annotated lung sound database creation for pediatric care. Auscultation is critical for assessing the respiratory system in children; however, the lack of pediatric lung sound databases impedes the development of automated analysis tools. This study introduces an object detection-based transfer learning method to accurately predict breath cycles in pediatric lung sounds. We utilized a model based on the YOLOv1 architecture, initially pre-trained on an adult lung sound dataset (HF_Lung_v1) and subsequently fine-tuned on a pediatric dataset (SNUCH_Lung). The input feature was the log Mel spectrogram, which effectively captured the relevant frequency and temporal information. The pre-trained model achieved an F1 score of 0.900 ± 0.003 on the HF_Lung_v1 dataset. After fine-tuning, it reached an F1 score of 0.824 ± 0.009 on the SNUCH_Lung dataset, confirming the efficacy of transfer learning. This model surpassed the performance of a baseline model trained solely on the SNUCH_Lung dataset without transfer learning. We also explored the impact of segment length, width, and various audio feature extraction techniques; the optimal results were obtained with 15 s segments, a 2-second width, and the log Mel spectrogram. The model is promising for clinical applications, such as generating large-scale annotated datasets, visualizing and labeling individual breath cycles, and performing correlation analysis with physiological indicators. Future research will focus on expanding the pediatric lung sound database through auto-labeling techniques and integrating the model into stethoscopes for real-time analysis. This study highlights the potential of object detection-based transfer learning in enhancing the accuracy of breath cycle prediction in pediatric lung sounds and advancing pediatric respiratory sound analysis tools.
ArticleNumber 107693
Author Lee, Jisoo
Park, Ji Soo
Park, Sa-Yoon
Lee, Hyesu
Kim, Kwangsoo
Kim, Yelin
Suh, Dong In
Author_xml – sequence: 1
  givenname: Sa-Yoon
  orcidid: 0000-0003-4058-9457
  surname: Park
  fullname: Park, Sa-Yoon
  organization: The Instiute of Convergence Medicine with Innovative Technology, Seoul National University Hospital, Seoul 03080, South Korea
– sequence: 2
  givenname: Ji Soo
  surname: Park
  fullname: Park, Ji Soo
  organization: Dept of Pediatrics, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, South Korea
– sequence: 3
  givenname: Jisoo
  surname: Lee
  fullname: Lee, Jisoo
  organization: Interdisciplinary Program in Bioengineering, Seoul National University, Seoul 08826, South Korea
– sequence: 4
  givenname: Hyesu
  orcidid: 0009-0004-5445-2878
  surname: Lee
  fullname: Lee, Hyesu
  organization: The Instiute of Convergence Medicine with Innovative Technology, Seoul National University Hospital, Seoul 03080, South Korea
– sequence: 5
  givenname: Yelin
  surname: Kim
  fullname: Kim, Yelin
  organization: Dept. of Computer Engineering, Hongik University, Seoul, South Korea
– sequence: 6
  givenname: Dong In
  surname: Suh
  fullname: Suh, Dong In
  email: dongins0@snu.ac.kr
  organization: Dept of Pediatrics, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, South Korea
– sequence: 7
  givenname: Kwangsoo
  surname: Kim
  fullname: Kim, Kwangsoo
  email: kwangsookim@snu.ac.kr
  organization: Dept. of Transdisciplinary Medicine, Institute of Convergence Medicine with Innovative Technology, Seoul National University Hospital, Seoul 03080, South Korea
BookMark eNp9kMtKAzEUhrOoYFt9AVd5ganJ3JIBN1KvUHCj65DLic0wzZQkLfTtzVDduOjqwA_fz3--BZr50QNCd5SsKKHtfb9Sca9XJSmbHLC2q2ZoTlndFpx09TVaxNgTUnNG6znqnyCBTm70eLRYBZBpi_VJDxCx83gPxskUnMbDwX_jOB68ifjoJJYZUH1GsflrKJSMYHAK0kcLAQ8gg3cZ20HajuYGXVk5RLj9vUv09fL8uX4rNh-v7-vHTaErQlLBuqpTWjXK5rWd1ISVtbUdL7mxpTaWMVZCzRSlFmTV2lq1ikrOLW9sBbSqloife3UYYwxghXZJTgPzMjcISsTkSfRi8iQmT-LsKaPlP3Qf3E6G02Xo4QxBfuroIIioHXid1YUsRpjRXcJ_APHjiDQ
CitedBy_id crossref_primary_10_1515_bmt_2025_0197
crossref_primary_10_1016_j_compbiomed_2025_110947
Cites_doi 10.1016/j.cmpb.2017.04.013
10.1186/s12879-023-08358-x
10.1016/j.procs.2020.03.209
10.1109/TBCAS.2022.3204910
10.1038/s41746-023-00838-3
10.1111/crj.12250
10.1016/j.neucom.2021.05.065
10.1038/s41598-023-27399-5
10.1371/journal.pone.0220606
10.1007/s00431-019-03363-2
10.21437/Interspeech.2021-698
10.1038/s41598-022-25953-1
10.1007/s00247-006-0191-5
10.1371/journal.pone.0254134
10.1088/1361-6579/ab03ea
10.1016/S0954-6111(97)90051-2
10.1164/ajrccm.162.3.9905104
ContentType Journal Article
Copyright 2025
Copyright_xml – notice: 2025
DBID AAYXX
CITATION
DOI 10.1016/j.bspc.2025.107693
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_bspc_2025_107693
S1746809425002046
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9DU
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
UNMZH
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c300t-7939bcb5bf0949ac0724ff9828df2cdf7772e47b11fea36f4b6b1a88f85f3e133
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001428337700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1746-8094
IngestDate Tue Nov 18 21:19:42 EST 2025
Thu Nov 27 00:57:48 EST 2025
Wed Dec 10 14:41:50 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords CWT
AST
Auscultation
Transfer learning
FN
STFT
FP
HPS
IoU
AP
Pediatric lung sounds
Object detection
Leaky ReLU
TN
TP
EMD
Breath cycle detection
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-7939bcb5bf0949ac0724ff9828df2cdf7772e47b11fea36f4b6b1a88f85f3e133
ORCID 0009-0004-5445-2878
0000-0003-4058-9457
ParticipantIDs crossref_citationtrail_10_1016_j_bspc_2025_107693
crossref_primary_10_1016_j_bspc_2025_107693
elsevier_sciencedirect_doi_10_1016_j_bspc_2025_107693
PublicationCentury 2000
PublicationDate July 2025
2025-07-00
PublicationDateYYYYMMDD 2025-07-01
PublicationDate_xml – month: 07
  year: 2025
  text: July 2025
PublicationDecade 2020
PublicationTitle Biomedical signal processing and control
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Park, Kim, Kim, Choi, Kim, Suh (b0040) 2023; 13
Du, Bayasi, Hamarneh, Garbi (b0105) 2023
Bentur, Livnat, Husein, Pollack, Rotschild (b0080) 2007; 14
Martinón-Torres, Carmo, Platero, Drago, López-Belmonte, Bangert (b0010) 2023; 23
Gross, Dittmar, Penzel, Schuttler, Von Wichert (b0090) 2000; 162
Gallardo-Antolín, Montero (b0110) 2021; 456
Hsu, Huang, Huang, Huang, Cheng, Chen (b0035) 2021; 16
Chaurasiya (b0050) 2020; 167
Redmon, Divvala, Girshick, Farhadi (b0045) 2016
Palaniappan, Sundaraj, Sundaraj, Huliraj, Revadi (b0095) 2016; 10
Kleinerman (b0015) 2006; 36
Zhang, Zhang, Yuan, Huang, Zhang, Zhang (b0025) 2022; 16
Heitmann, Glangetas, Doenz, Dervaux, Shama, Garcia (b0060) 2023; 6
Grzywalski, Piecuch, Szajek, Bręborowicz, Hafke-Dys, Kociński (b0070) 2019; 178
Hafke-Dys, Bręborowicz, Kleka, Kociński, Biniakowski (b0020) 2019; 14
Kim, Kim, Mun, Lim, Kim (b0065) 2022; 12
De L'Auscultation Mediate; ou Traite du Diagnostic des Maladies des Poumons et du Coeur, Edinb Med Surg J. 18 (1822) 447–474.
Y. Gong, Y.-A. Chung, J. Glass, AST: Audio spectrogram transformer, arXiv preprint arXiv:210401778. (2021).
Purohit, Bohadana, Kopferschmitt-Kubler, Mahr, Linder, Pauli (b0085) 1997; 91
Palaniappan, Sundaraj, Sundaraj (b0100) 2017; 145
Rocha, Filos, Mendes, Serbes, Ulukaya, Kahya (b0030) 2019; 40
Desmond, Muller, Ashktorab, Dugan, Duesterwald, Brimijoin (b0075) 2021
10.1016/j.bspc.2025.107693_b0005
Palaniappan (10.1016/j.bspc.2025.107693_b0095) 2016; 10
Kleinerman (10.1016/j.bspc.2025.107693_b0015) 2006; 36
Chaurasiya (10.1016/j.bspc.2025.107693_b0050) 2020; 167
Martinón-Torres (10.1016/j.bspc.2025.107693_b0010) 2023; 23
Rocha (10.1016/j.bspc.2025.107693_b0030) 2019; 40
Grzywalski (10.1016/j.bspc.2025.107693_b0070) 2019; 178
Gallardo-Antolín (10.1016/j.bspc.2025.107693_b0110) 2021; 456
Heitmann (10.1016/j.bspc.2025.107693_b0060) 2023; 6
Zhang (10.1016/j.bspc.2025.107693_b0025) 2022; 16
Palaniappan (10.1016/j.bspc.2025.107693_b0100) 2017; 145
Kim (10.1016/j.bspc.2025.107693_b0065) 2022; 12
Hafke-Dys (10.1016/j.bspc.2025.107693_b0020) 2019; 14
Redmon (10.1016/j.bspc.2025.107693_b0045) 2016
Park (10.1016/j.bspc.2025.107693_b0040) 2023; 13
Hsu (10.1016/j.bspc.2025.107693_b0035) 2021; 16
Du (10.1016/j.bspc.2025.107693_b0105) 2023
10.1016/j.bspc.2025.107693_b0055
Purohit (10.1016/j.bspc.2025.107693_b0085) 1997; 91
Bentur (10.1016/j.bspc.2025.107693_b0080) 2007; 14
Desmond (10.1016/j.bspc.2025.107693_b0075) 2021
Gross (10.1016/j.bspc.2025.107693_b0090) 2000; 162
References_xml – volume: 91
  start-page: 151
  year: 1997
  end-page: 157
  ident: b0085
  article-title: Lung auscultation in airway challenge testing
  publication-title: Respir. Med.
– year: 2021
  ident: b0075
  article-title: Increasing the speed and accuracy of data labeling through an AI-assisted interface
  publication-title: Int. Conf. Intell. User Interf.
– volume: 10
  start-page: 486
  year: 2016
  end-page: 494
  ident: b0095
  article-title: A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system
  publication-title: Clin. Respir. J.
– volume: 12
  start-page: 22465
  year: 2022
  ident: b0065
  article-title: An accurate deep learning model for wheezing in children using real-world data
  publication-title: Sci. Rep.
– volume: 145
  start-page: 67
  year: 2017
  end-page: 72
  ident: b0100
  article-title: Adaptive neuro-fuzzy inference system for breath phase detection and breath cycle segmentation
  publication-title: Comput. Methods Programs Biomed.
– volume: 14
  start-page: 156
  year: 2007
  end-page: 161
  ident: b0080
  article-title: Dynamic visualization of breath sound distribution in suspected foreign body aspiration: a pediatric case series
  publication-title: J. Bronchol. Interv. Pulmonol.
– volume: 456
  start-page: 49
  year: 2021
  end-page: 60
  ident: b0110
  article-title: On combining acoustic and modulation spectrograms in an attention LSTM-based system for speech intelligibility level classification
  publication-title: Neurocomputing
– volume: 16
  year: 2021
  ident: b0035
  article-title: Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1
  publication-title: PLoS One
– reference: De L'Auscultation Mediate; ou Traite du Diagnostic des Maladies des Poumons et du Coeur, Edinb Med Surg J. 18 (1822) 447–474.
– volume: 23
  start-page: 385
  year: 2023
  ident: b0010
  article-title: Clinical and economic hospital burden of acute respiratory infection (BARI) due to respiratory syncytial virus in Spanish children, 2015–2018
  publication-title: BMC Infect Dis.
– year: 2016
  ident: b0045
  article-title: You only look once: Unified, real-time object detection
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 14
  year: 2019
  ident: b0020
  article-title: The accuracy of lung auscultation in the practice of physicians and medical students
  publication-title: PLoS One
– volume: 13
  start-page: 1289
  year: 2023
  ident: b0040
  article-title: A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model
  publication-title: Sci. Rep.
– volume: 162
  start-page: 905
  year: 2000
  end-page: 909
  ident: b0090
  article-title: The relationship between normal lung sounds, age, and gender
  publication-title: Am. J. Respir. Crit. Care Med.
– volume: 36
  start-page: 121
  year: 2006
  end-page: 125
  ident: b0015
  article-title: Cancer risks following diagnostic and therapeutic radiation exposure in children
  publication-title: Pediatr. Radiol.
– year: 2023
  ident: b0105
  article-title: MDViT: Multi-domain vision transformer for small medical image segmentation datasets
– volume: 167
  start-page: 1901
  year: 2020
  end-page: 1910
  ident: b0050
  article-title: Time-frequency representations: spectrogram, cochleogram and correlogram
  publication-title: Procedia Comput. Sci.
– volume: 178
  start-page: 883
  year: 2019
  end-page: 890
  ident: b0070
  article-title: Practical implementation of artificial intelligence algorithms in pulmonary auscultation examination
  publication-title: Eur. J. Pediatr.
– volume: 16
  start-page: 867
  year: 2022
  end-page: 881
  ident: b0025
  article-title: SPRSound: open-source SJTU paediatric respiratory sound database
  publication-title: IEEE Trans Biomed Circuits Syst.
– volume: 40
  year: 2019
  ident: b0030
  article-title: An open access database for the evaluation of respiratory sound classification algorithms
  publication-title: Physiol. Meas.
– reference: Y. Gong, Y.-A. Chung, J. Glass, AST: Audio spectrogram transformer, arXiv preprint arXiv:210401778. (2021).
– volume: 6
  start-page: 104
  year: 2023
  ident: b0060
  article-title: DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries
  publication-title: NPJ Digit Med.
– volume: 145
  start-page: 67
  year: 2017
  ident: 10.1016/j.bspc.2025.107693_b0100
  article-title: Adaptive neuro-fuzzy inference system for breath phase detection and breath cycle segmentation
  publication-title: Comput. Methods Programs Biomed.
  doi: 10.1016/j.cmpb.2017.04.013
– volume: 23
  start-page: 385
  year: 2023
  ident: 10.1016/j.bspc.2025.107693_b0010
  article-title: Clinical and economic hospital burden of acute respiratory infection (BARI) due to respiratory syncytial virus in Spanish children, 2015–2018
  publication-title: BMC Infect Dis.
  doi: 10.1186/s12879-023-08358-x
– volume: 167
  start-page: 1901
  year: 2020
  ident: 10.1016/j.bspc.2025.107693_b0050
  article-title: Time-frequency representations: spectrogram, cochleogram and correlogram
  publication-title: Procedia Comput. Sci.
  doi: 10.1016/j.procs.2020.03.209
– volume: 16
  start-page: 867
  issue: 5
  year: 2022
  ident: 10.1016/j.bspc.2025.107693_b0025
  article-title: SPRSound: open-source SJTU paediatric respiratory sound database
  publication-title: IEEE Trans Biomed Circuits Syst.
  doi: 10.1109/TBCAS.2022.3204910
– volume: 6
  start-page: 104
  issue: 1
  year: 2023
  ident: 10.1016/j.bspc.2025.107693_b0060
  article-title: DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries
  publication-title: NPJ Digit Med.
  doi: 10.1038/s41746-023-00838-3
– volume: 10
  start-page: 486
  issue: 4
  year: 2016
  ident: 10.1016/j.bspc.2025.107693_b0095
  article-title: A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system
  publication-title: Clin. Respir. J.
  doi: 10.1111/crj.12250
– volume: 456
  start-page: 49
  year: 2021
  ident: 10.1016/j.bspc.2025.107693_b0110
  article-title: On combining acoustic and modulation spectrograms in an attention LSTM-based system for speech intelligibility level classification
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.05.065
– volume: 13
  start-page: 1289
  issue: 1
  year: 2023
  ident: 10.1016/j.bspc.2025.107693_b0040
  article-title: A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-023-27399-5
– year: 2021
  ident: 10.1016/j.bspc.2025.107693_b0075
  article-title: Increasing the speed and accuracy of data labeling through an AI-assisted interface
  publication-title: Int. Conf. Intell. User Interf.
– volume: 14
  issue: 8
  year: 2019
  ident: 10.1016/j.bspc.2025.107693_b0020
  article-title: The accuracy of lung auscultation in the practice of physicians and medical students
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0220606
– volume: 178
  start-page: 883
  issue: 6
  year: 2019
  ident: 10.1016/j.bspc.2025.107693_b0070
  article-title: Practical implementation of artificial intelligence algorithms in pulmonary auscultation examination
  publication-title: Eur. J. Pediatr.
  doi: 10.1007/s00431-019-03363-2
– ident: 10.1016/j.bspc.2025.107693_b0055
  doi: 10.21437/Interspeech.2021-698
– volume: 12
  start-page: 22465
  issue: 1
  year: 2022
  ident: 10.1016/j.bspc.2025.107693_b0065
  article-title: An accurate deep learning model for wheezing in children using real-world data
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-022-25953-1
– volume: 36
  start-page: 121
  issue: Suppl 2
  year: 2006
  ident: 10.1016/j.bspc.2025.107693_b0015
  article-title: Cancer risks following diagnostic and therapeutic radiation exposure in children
  publication-title: Pediatr. Radiol.
  doi: 10.1007/s00247-006-0191-5
– volume: 16
  issue: 7
  year: 2021
  ident: 10.1016/j.bspc.2025.107693_b0035
  article-title: Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0254134
– ident: 10.1016/j.bspc.2025.107693_b0005
– volume: 40
  issue: 3
  year: 2019
  ident: 10.1016/j.bspc.2025.107693_b0030
  article-title: An open access database for the evaluation of respiratory sound classification algorithms
  publication-title: Physiol. Meas.
  doi: 10.1088/1361-6579/ab03ea
– year: 2016
  ident: 10.1016/j.bspc.2025.107693_b0045
  article-title: You only look once: Unified, real-time object detection
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– year: 2023
  ident: 10.1016/j.bspc.2025.107693_b0105
– volume: 14
  start-page: 156
  issue: 3
  year: 2007
  ident: 10.1016/j.bspc.2025.107693_b0080
  article-title: Dynamic visualization of breath sound distribution in suspected foreign body aspiration: a pediatric case series
  publication-title: J. Bronchol. Interv. Pulmonol.
– volume: 91
  start-page: 151
  issue: 3
  year: 1997
  ident: 10.1016/j.bspc.2025.107693_b0085
  article-title: Lung auscultation in airway challenge testing
  publication-title: Respir. Med.
  doi: 10.1016/S0954-6111(97)90051-2
– volume: 162
  start-page: 905
  issue: 3
  year: 2000
  ident: 10.1016/j.bspc.2025.107693_b0090
  article-title: The relationship between normal lung sounds, age, and gender
  publication-title: Am. J. Respir. Crit. Care Med.
  doi: 10.1164/ajrccm.162.3.9905104
SSID ssj0048714
Score 2.3910682
Snippet •YOLOv1-based model for pediatric breath cycle detection via transfer learning.•Fine-tuned model achieves an F1 score of 0.824 on pediatric lung sounds...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 107693
SubjectTerms Auscultation
Breath cycle detection
Object detection
Pediatric lung sounds
Transfer learning
Title Detection of breath cycles in pediatric lung sounds via an object detection-based transfer learning method
URI https://dx.doi.org/10.1016/j.bspc.2025.107693
Volume 105
WOSCitedRecordID wos001428337700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 1746-8094
  databaseCode: AIEXJ
  dateStart: 20060101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0048714
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9wwEBZt0kN7KOmLpG2CDr0Zl_VDtnwMaUoaQihsWrYnI8lS6iXYy3oTkn-fGUuy000JbaEXs4iVvKv5PPpmPA9CPnBdKKEEPN8mzcBA4WnIuYrCzMRc5Vjxqq-z_f0kPz3ls1nx1XmVur6dQN40_Pq6WPxXUcMYCBtTZ_9C3MOiMACfQehwBbHD9Y8E_0mvtPI8UCIn_BmoGwx-sxHjrjVHcHGJngTsqtQFV31qVtBK9MoElV8hxDOuwjYSQG710reYOHd9p395Idyn8dscy_ocKe7CpiD4JEgXEz--srIx2lMR_mjHUAA_fFwH07Zdjxaqu3tjRzeudYt3XcRsCHN1_jSfUzMGMKEKzlMskWxbHw86us_Nvq_vreth_lF2C6xHGTMYwu6O4-k2xBxOcWFcF0gfZgRnj8lmnLMCtPnm_pfD2bE_wMGE60vCDz_E5VrZsMD1O_2ez9zhKGdb5LkzLui-BcUL8kg3L8mzOyUnX5H5AA_aGmrhQS08aN3QAR4U4UEtPCjAgwqY0MODrsGDenhQDw9q4fGafPt8eHZwFLp-G6FKJpNVCKq6kEoyaeBPF0JN8jg1pgCbvDKxqkwOlphOcxlFRoskM6nMZCQ4N5yZREdJ8oZsNG2jtwlVVQVEXjIwXoHyypRnzJgomwjDBZwabIdEftdK5YrRY0-Ui9JHHc5L3OkSd7q0O71DgmHOwpZiefDbzAujdGTSksQSsPPAvLf_OO8deTpC_D3ZWC0v9S55oq5WdbfccxC7BT7SnDg
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Detection+of+breath+cycles+in+pediatric+lung+sounds+via+an+object+detection-based+transfer+learning+method&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Park%2C+Sa-Yoon&rft.au=Park%2C+Ji+Soo&rft.au=Lee%2C+Jisoo&rft.au=Lee%2C+Hyesu&rft.date=2025-07-01&rft.pub=Elsevier+Ltd&rft.issn=1746-8094&rft.volume=105&rft_id=info:doi/10.1016%2Fj.bspc.2025.107693&rft.externalDocID=S1746809425002046
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon