Peer-Reviewed Publication
J Robot Surg2025;19(1):131.March 31, 2025Journal Article
Optimizing intraoperative AI: evaluation of YOLOv8 for real-time recognition of robotic and laparoscopic instruments.
Sébastien Frey1,2,3,4, Federica Facente5,6,7, Wen Wei7, Ezem Sura Ekmekci6, Eric Séjor8,7, Patrick Baqué5,8, Matthieu Durand5,9,10, Hervé Delingette6, François Bremond11, Pierre Berthet-Rayne7, Nicholas Ayache6
1Université Côte d'Azur, Nice, France. freysebastien6@gmail.com.
2Department of General Surgery, Pasteur 2 Hospital, University Hospital of Nice, Nice, France. freysebastien6@gmail.com.
3Epione Team, Université Côte d'Azur, Inria, Sophia-Antipolis, Nice, France. freysebastien6@gmail.com.
4Hôpital L'Archet, University Hospital of Nice, 151, Route de Saint-Antoine, Nice, France. freysebastien6@gmail.com.
5Université Côte d'Azur, Nice, France.
6Epione Team, Université Côte d'Azur, Inria, Sophia-Antipolis, Nice, France.
7Caranx Medical, Nice, France.
8Department of General Surgery, Pasteur 2 Hospital, University Hospital of Nice, Nice, France.
9Urology, Andrology, Renal Transplant Unit, Pasteur 2 Hospital, University Hospital of Nice, Nice, France.
10INSERM U1081 - CNRS UMR 7284, Nice University Côte d'Azur, Nice, France.
11Stars Team, Université Côte d'Azur, Inria, Sophia-Antipolis, Nice, France.
Abstract
The accurate recognition of surgical instruments is essential for the advancement of intraoperative artificial intelligence (AI) systems. In this study, we assessed the YOLOv8 model's efficacy in identifying robotic and laparoscopic instruments in robot-assisted abdominal surgeries. Specifically, we evaluated its ability to detect, classify, and segment seven different types of surgical instrument…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans