EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TI-YOLO: A Lightweight and Efficient Anatomical Structure Detection Model for Tracheal Intubation

Yu Tian, Congliang Yang, Lingfeng Sang iD, Cicao Ping, Lili Feng, Weixiong Chen, Hongbo Wang, Wenxian Li iD, Yuan Han iD

Bioengineering · 13.04.2026 · 13 (4) · 451

DOI: 10.3390/bioengineering13040451 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 13.04.2026. Verfasst von Yu Tian und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, Eye & ENT Hospital of Fudan University, No. 83 Fenyang Road, Xuhui District, Shanghai 200031, China. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Opening Project of Ningbo Key Laboratory of Aging Health Equipment and Service Technology, Fudan University Medical-Engineering Integration Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and rapid detection of anatomical structures, such as the glottis, is critical during tracheal intubation (TI) to ensure patient safety and procedural success. However, it remains a challenge due to the limited field of view and computational resources of video laryngoscopy, especially for difficult airway situations. Existing deep learning (DL) models struggle to balance high accuracy and real-time clinical deployment. To address these issues, we propose TI-YOLO (TI-You Only Look Once), a lightweight and efficient object detection model built upon the YOLOv11 architecture. TI-YOLO introduces the Bidirectional Feature Pyramid Network (BiFPN) module for multi-scale feature fusion, effectively enhancing the ability to detect anatomical structures of different sizes. TI-YOLO integrates the Deformable Attention Transformer (DAT) module to enhance the perception of crucial regions, improving detection accuracy and robustness. To further reduce the consumption of computational resources while maintaining efficiency, TI-YOLO is optimized by reconstructing the backbone based on MobileNetV4. Furthermore, TI-YOLO employs the Slide Weight Function (SWF) as a loss function during model training to mitigate the class imbalance within the dataset. One self-built dataset is used to validate the effectiveness of TI-YOLO. Compared to the original YOLOv11, TI-YOLO achieves mean Average Precision at IoU 0.50 (mAP50) scores of 0.902, with improvements of 3.8%. Meanwhile, TI-YOLO balances detection accuracy and computational efficiency with a 10.5% reduction in floating-point operations (FLOPs) and a 28.9% reduction in parameters, and the model weight is only 4.6 MB. Additionally, to evaluate TI-YOLO real-time inference capability, we quantize and deploy it on a low-cost embedded OrangePi 5 platform. The inference speed reaches over 50 frames per second (FPS), meeting real-time clinical requirements.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismfeature fusionlightweighttracheal intubation

Autor:innen und Institutionen

  • Department of Anesthesiology, Eye & ENT Hospital of Fudan University, No. 83 Fenyang Road, Xuhui District, Shanghai 200031, China.
  • Ningbo Key Laboratory of Aging Health Equipment and Service Technology, Ningbo Polytechnic, Ningbo 315800, China.
  • School of Health Science and Engineering, University of Shanghai for Science and Technology, No. 516 Jungong Road, Yangpu District, Shanghai 200093, China.
  • College of Intelligent Robotics and Advanced Manufacturing, Fudan University, No. 220 Handan Road, Yangpu District, Shanghai 200433, China.

ORCID-Profile: Lingfeng Sang, Wenxian Li, Yuan Han

Förderung

  • China Postdoctoral Science Foundation
  • Opening Project of Ningbo Key Laboratory of Aging Health Equipment and Service Technology
  • Fudan University Medical-Engineering Integration Project
  • Fudan-Yunfeng Healthcare Fund
  • 2023 Shanghai leading talent project, Fudan University Shanghai Medical College-Young Clinical Distinguished Physicians Training Program

Zitieren

APA

Tian, Y., Yang, C., Sang, L., Ping, C., Feng, L., Chen, W., Wang, H., Li, W., & Han, Y. (2026). TI-YOLO: A Lightweight and Efficient Anatomical Structure Detection Model for Tracheal Intubation. Bioengineering, 13(4), 451. https://doi.org/10.3390/bioengineering13040451

Vancouver

Tian Y, Yang C, Sang L, Ping C, Feng L, Chen W, et al. TI-YOLO: A Lightweight and Efficient Anatomical Structure Detection Model for Tracheal Intubation. Bioengineering. 2026;13(4):451. doi:10.3390/bioengineering13040451

BibTeX
@article{Tian2026,
  author = {Tian, Yu and Yang, Congliang and Sang, Lingfeng and Ping, Cicao and Feng, Lili and Chen, Weixiong and Wang, Hongbo and Li, Wenxian and Han, Yuan},
  title = {TI-YOLO: A Lightweight and Efficient Anatomical Structure Detection Model for Tracheal Intubation},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {451},
  doi = {10.3390/bioengineering13040451}
}
Kostenlos starten →