EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing bowel sound recognition with self-attention and self-supervised pre-training

Yansuo Yu iD, Mingwu Zhang, Zhennian Xie, Qiang Liu iD

PLOS ONE · 31.12.2024 · 19 (12) · e0311503

DOI: 10.1371/journal.pone.0311503 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 31.12.2024. Verfasst von Yansuo Yu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Education Commission, Chinese Academy of Traditional Chinese Medicine, Beijing Institute of Petrochemical Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bowel sounds, a reflection of the gastrointestinal tract’s peristalsis, are essential for diagnosing and monitoring gastrointestinal conditions. However, the absence of an effective, non-invasive method for assessing digestion through auscultation has resulted in a reliance on time-consuming and laborious manual analysis by clinicians. This study introduces an innovative deep learning-based method designed to automate and enhance the recognition of bowel sounds. Our approach integrates the Branchformer architecture, which leverages the power of self-attention and convolutional gating for robust feature extraction, with a self-supervised pre-training strategy. Specifically, the Branchformer model employs parallel processing of self-attention and convolutional gated Multi-layer Perceptron branches to capture both global and local dependencies in audio signals, thereby enabling effective characterization of complex bowel sound patterns. Furthermore, a self-supervised pre-training strategy is employed, leveraging a large corpus of unlabeled audio data to learn general sound wave representations, followed by fine-tuning on a limited set of bowel sound data to optimize the model’s recognition performance for specific tasks. Experimental results on public bowel sound datasets demonstrate the superior recognition performance of the proposed method compared to existing baseline models, particularly under data-limited conditions, thereby confirming the effectiveness of the self-supervised pre-training strategy. This work provides an efficient and automated solution for clinical bowel sound monitoring, facilitating early diagnosis and treatment of gastrointestinal disorders.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansSoundNeural Networks, ComputerAuscultationSignal Processing, Computer-AssistedMaleAdult

Autor:innen und Institutionen

  • Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing, China.
  • Xiyuan Hospital, Chinese Academy of Traditional Chinese Medicine, Beijing, China.

ORCID-Profile: Yansuo Yu, Qiang Liu

Förderung

  • Beijing Municipal Education Commission
  • Chinese Academy of Traditional Chinese Medicine
  • Beijing Institute of Petrochemical Technology

Zitieren

APA

Yu, Y., Zhang, M., Xie, Z., & Liu, Q. (2024). Enhancing bowel sound recognition with self-attention and self-supervised pre-training. PLOS ONE, 19(12), e0311503. https://doi.org/10.1371/journal.pone.0311503

Vancouver

Yu Y, Zhang M, Xie Z, Liu Q. Enhancing bowel sound recognition with self-attention and self-supervised pre-training. PLOS ONE. 2024;19(12):e0311503. doi:10.1371/journal.pone.0311503

BibTeX
@article{Yu2024,
  author = {Yu, Yansuo and Zhang, Mingwu and Xie, Zhennian and Liu, Qiang},
  title = {Enhancing bowel sound recognition with self-attention and self-supervised pre-training},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {12},
  pages = {e0311503},
  doi = {10.1371/journal.pone.0311503}
}
Kostenlos starten →