EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

RespAnno: A graphical software tool for manual and machine-assisted annotation of continuous respiratory sounds

Chaoyue Pan, Xingshan Liu, Shuoqun Li, Xinpei Wang, Liping Li, Guohui Wei, Guodong Zang

SoftwareX · 2026-12 · 36 · 103011

DOI: 10.1016/j.softx.2026.103011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SoftwareX, 2026-12. Verfasst von Chaoyue Pan und 6 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RespAnno is a graphical software tool for time-aligned manual and machine-assisted annotation of respiratory sounds. It integrates synchronized waveform and spectrogram visualization, editable machine-generated candidates, model-specific review progression, and iterative use of reviewed annotations for subsequent model updating and candidate generation. The machine-assisted workflow was quantitatively evaluated for Inspiration candidate generation on 2506 respiratory-sound recordings. The final configuration achieved a precision of 0.8274, recall of 0.8089, Event F1 of 0.8181, and strict-perfect rate of 59.7%.

Zitieren

APA

Pan, C., Liu, X., Li, S., Wang, X., Li, L., Wei, G., & Zang, G. (2026). RespAnno: A graphical software tool for manual and machine-assisted annotation of continuous respiratory sounds. SoftwareX, 36, 103011. https://doi.org/10.1016/j.softx.2026.103011

Vancouver

Pan C, Liu X, Li S, Wang X, Li L, Wei G, et al. RespAnno: A graphical software tool for manual and machine-assisted annotation of continuous respiratory sounds. SoftwareX. 2026;36:103011. doi:10.1016/j.softx.2026.103011

BibTeX
@article{Pan2026,
  author = {Pan, Chaoyue and Liu, Xingshan and Li, Shuoqun and Wang, Xinpei and Li, Liping and Wei, Guohui and Zang, Guodong},
  title = {RespAnno: A graphical software tool for manual and machine-assisted annotation of continuous respiratory sounds},
  journal = {SoftwareX},
  year = {2026},
  volume = {36},
  pages = {103011},
  doi = {10.1016/j.softx.2026.103011}
}
Kostenlos starten →