EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real‐Time Tool Detection in Laparoscopic Datasets for Surgical Training in Low‐Resource Settings

Omar Choudhry, Sharib Ali iD, Chandra Shekhar Biyani, Dominic Jones iD

Healthcare Technology Letters · 2025-01 · 12 (1)

DOI: 10.1049/htl2.70045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 10.12.2025. Verfasst von Omar Choudhry und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science University of Leeds Leeds UK. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation, Engineering and Physical Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In low‐resource settings, there is a critical need for skilled surgeons. Alternative training processes that include computer‐assisted surgical skill evaluation are essential to address this gap. Using tool detection, surgical videos can be leveraged to derive insights into surgical skill assessment. However, state‐of‐the‐art laparoscopic tool detection methods usually have more complex architectures tailored for in vivo data, which suffer from challenges such as smoke, occlusion, bleeding, etc., which are absent from in vitro training contexts. Thus, this paper tests multiple anchor‐based and anchor‐free, convolution‐ and transformer‐based, traditional (non‐surgical domain‐specific) computer vision deep learning state‐of‐the‐art models. With various hardware configurations on a newly curated in‐house laparoscopic box‐trainer dataset, we emphasise real‐time performance on low‐cost embedded devices. Overall, the anchor‐free YOLOv8‐X model was the most accurate, achieving of 99.5% and of 96.6% with an inference time of 23.5 ms/42.6 FPS on an NVIDIA Jetson Orin Nano 8GB (comparable low‐cost hardware which could be expected to run real‐time skill assessment methods for surgical training boot camps in a resource‐constrained environment). The most efficient model was YOLOv11‐N, providing 3.1 ms/322.6 FPS with a performance difference of +0% and –2.1% . The results highlight the models' potential for effective real‐time detection of surgical tools and are suitable for further downstream assessment of surgical skills, even in resource‐constrained environments.

Schlagwörter

Stichwörter der Autor:innen

computer visiondata acquisitionimage processinglearning (artificial intelligence)surgery

Autor:innen und Institutionen

  • School of Computer Science University of Leeds Leeds UK.
  • St Jamess University Hospital Leeds Teaching Hospitals NHS Trust Leeds UK.
  • School of Electronic and Electrical Engineering University of Leeds Leeds UK.

ORCID-Profile: Sharib Ali, Dominic Jones

Förderung

  • UK Research and Innovation
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Choudhry, O., Ali, S., Biyani, C. S., & Jones, D. (2025). Real‐Time Tool Detection in Laparoscopic Datasets for Surgical Training in Low‐Resource Settings. Healthcare Technology Letters, 12(1). https://doi.org/10.1049/htl2.70045

Vancouver

Choudhry O, Ali S, Biyani CS, Jones D. Real‐Time Tool Detection in Laparoscopic Datasets for Surgical Training in Low‐Resource Settings. Healthcare Technology Letters. 2025;12(1). doi:10.1049/htl2.70045

BibTeX
@article{Choudhry2025,
  author = {Choudhry, Omar and Ali, Sharib and Biyani, Chandra Shekhar and Jones, Dominic},
  title = {Real‐Time Tool Detection in Laparoscopic Datasets for Surgical Training in Low‐Resource Settings},
  journal = {Healthcare Technology Letters},
  year = {2025},
  volume = {12},
  number = {1},
  doi = {10.1049/htl2.70045}
}
Kostenlos starten →