EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Network for Free Fluid Detection in Focused Assessment with Sonography in Trauma (FAST) Examination

Mingyi Yang iD, Nianzeng Yuan, Shipeng Han, Tianjiao Guo, Wen Luo, Hao Lv

Bioengineering · 13.05.2026 · 13 (5) · 550

DOI: 10.3390/bioengineering13050550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 13.05.2026. Verfasst von Mingyi Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Air Force Medical University, Xi'an 710032, China. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Focused Assessment with Sonography in Trauma (FAST) enables rapid point-of-care screening for internal hemorrhage by detecting free fluid, but its accuracy is highly operator-dependent and prone to missed diagnoses in emergency settings. While deep learning–based AI assistance can address these limitations, most existing models rely on computationally intensive networks, restricting deployment on resource-limited bedside devices. Thus, developing a lightweight architecture for free fluid detection is essential for clinical translation. We propose a lightweight model based on YOLOX, incorporating a dual-stream fusion (DSF) backbone to preserve spatial details while reducing computation, and a global fusion feedback (GFF) neck to enhance efficient multi-scale feature fusion. We also built a dedicated dataset using ultrasound images from rabbits with active liver hemorrhage to better mimic in vivo sonographic features of free fluid. Compared with mainstream detectors, our method achieves the lowest FLOPs and parameter count while maintaining superior precision, recall, and F1-score. Ablation studies validate that DSF improves accuracy and reduces complexity, and GFF further lowers computational costs with minimal performance tradeoff. The proposed approach enables fast, accurate free fluid detection on constrained bedside devices, advancing intelligent point-of-care trauma assessment.

Schlagwörter

Stichwörter der Autor:innen

Focused Assessment with Sonography in Trauma (FAST)free fluid detectionlightweight network

Autor:innen und Institutionen

  • School of Biomedical Engineering, Air Force Medical University, Xi'an 710032, China.
  • Department of Ultrasound, Xijing Hospital of Air Force Medical University, Xi'an 710032, China.

ORCID-Profile: Mingyi Yang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yang, M., Yuan, N., Han, S., Guo, T., Luo, W., & Lv, H. (2026). A Lightweight Network for Free Fluid Detection in Focused Assessment with Sonography in Trauma (FAST) Examination. Bioengineering, 13(5), 550. https://doi.org/10.3390/bioengineering13050550

Vancouver

Yang M, Yuan N, Han S, Guo T, Luo W, Lv H. A Lightweight Network for Free Fluid Detection in Focused Assessment with Sonography in Trauma (FAST) Examination. Bioengineering. 2026;13(5):550. doi:10.3390/bioengineering13050550

BibTeX
@article{Yang2026,
  author = {Yang, Mingyi and Yuan, Nianzeng and Han, Shipeng and Guo, Tianjiao and Luo, Wen and Lv, Hao},
  title = {A Lightweight Network for Free Fluid Detection in Focused Assessment with Sonography in Trauma (FAST) Examination},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {5},
  pages = {550},
  doi = {10.3390/bioengineering13050550}
}
Kostenlos starten →