EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Tool Localization for Laparoscopic Surgery Using Convolutional Neural Network

Diego Benavides iD, Ana Cisnal iD, Carlos Fontúrbel iD, Eusebio de la Fuente iD, Juan Carlos Fraile

Sensors · 27.06.2024 · 24 (13) · 4191

DOI: 10.3390/s24134191 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.06.2024. Verfasst von Diego Benavides und 4 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de las Tecnologías Avanzadas de la Producción (ITAP), Escuela de Ingenierías Industriales, Universidad de Valladolid, Paseo Prado de la Mag…. Hauptthemen laut MEDLINE: Laparoscopy, Neural Networks, Computer. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish Ministry of Science, Innovation, and Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Partially automated robotic systems, such as camera holders, represent a pivotal step towards enhancing efficiency and precision in surgical procedures. Therefore, this paper introduces an approach for real-time tool localization in laparoscopy surgery using convolutional neural networks. The proposed model, based on two Hourglass modules in series, can localize up to two surgical tools simultaneously. This study utilized three datasets: the ITAP dataset, alongside two publicly available datasets, namely Atlas Dione and EndoVis Challenge. Three variations of the Hourglass-based models were proposed, with the best model achieving high accuracy (92.86%) and frame rates (27.64 FPS), suitable for integration into robotic systems. An evaluation on an independent test set yielded slightly lower accuracy, indicating limited generalizability. The model was further analyzed using the Grad-CAM technique to gain insights into its functionality. Overall, this work presents a promising solution for automating aspects of laparoscopic surgery, potentially enhancing surgical efficiency by reducing the need for manual endoscope manipulation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LaparoscopyNeural Networks, ComputerHumansRobotic Surgical ProceduresAlgorithms

Stichwörter der Autor:innen

artificial intelligencebiomedical image processingconvolutional neural networklaparoscopy robotic surgeryreal-timesurgical tool tracking

Autor:innen und Institutionen

  • Instituto de las Tecnologías Avanzadas de la Producción (ITAP), Escuela de Ingenierías Industriales, Universidad de Valladolid, Paseo Prado de la Magdalena 3-5, 47011 Valladolid, Spain.

ORCID-Profile: Diego Benavides, Ana Cisnal, Carlos Fontúrbel, Eusebio de la Fuente

Förderung

  • Spanish Ministry of Science, Innovation, and Universities

Zitieren

APA

Benavides, D., Cisnal, A., Fontúrbel, C., de la Fuente, E., & Fraile, J. C. (2024). Real-Time Tool Localization for Laparoscopic Surgery Using Convolutional Neural Network. Sensors, 24(13), 4191. https://doi.org/10.3390/s24134191

Vancouver

Benavides D, Cisnal A, Fontúrbel C, de la Fuente E, Fraile JC. Real-Time Tool Localization for Laparoscopic Surgery Using Convolutional Neural Network. Sensors. 2024;24(13):4191. doi:10.3390/s24134191

BibTeX
@article{Benavides2024,
  author = {Benavides, Diego and Cisnal, Ana and Fontúrbel, Carlos and de la Fuente, Eusebio and Fraile, Juan Carlos},
  title = {Real-Time Tool Localization for Laparoscopic Surgery Using Convolutional Neural Network},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4191},
  doi = {10.3390/s24134191}
}
Kostenlos starten →