Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

OpenClaw and Multi-Agent AI in Plastic Surgery.

Aesthetic surgery journal·2026
Same author

Fine-Tuning, Retrieval-Augmented Generation, and Hybrid Large Language Models for Postoperative Decision Support: A Comparative Analysis.

Journal of medical Internet research·2026
Same author

Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review.

Bioengineering (Basel, Switzerland)·2026
Same author

AI-Generated Avatar Videos for Postoperative Patient Education Among Health Care Workers: Pilot Randomized Controlled Trial.

JMIR perioperative medicine·2026
Same author

Performance Modeling of Lightweight Retrieval-Augmented Large Language Models for Low-Resource Plastic Surgery Settings.

Bioengineering (Basel, Switzerland)·2026
Same author

An AI-powered RAG Conversational Agent for Enhancing Patient Recall of Surgical Consultations: A Proof-of-concept Study.

Aesthetic surgery journal·2026

Related Experiment Video

Updated: May 31, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

763

Use of Multimodal Artificial Intelligence in Surgical Instrument Recognition.

Syed Ali Haider1, Olivia A Ho1, Sahar Borna1

  • 1Division of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USA.

Bioengineering (Basel, Switzerland)
|January 24, 2025
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) can identify surgical instruments, with ChatGPT-4o showing the highest accuracy. While AI excels at category identification, precise instrument naming remains a challenge for all tested models, impacting surgical safety.

Keywords:
AIartificial intelligencecomputer visionmultimodal AIsurgical instrument

More Related Videos

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

629
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.2K

Related Experiment Videos

Last Updated: May 31, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

763
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

629
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.2K

Area of Science:

  • Medical Technology
  • Artificial Intelligence in Healthcare
  • Surgical Safety

Background:

  • Accurate surgical instrument identification is vital for operating room efficiency and patient safety, especially to prevent retained surgical items.
  • Artificial Intelligence (AI) offers potential solutions for automating surgical instrument recognition.

Purpose of the Study:

  • To evaluate the accuracy of publicly available Large Language Models (LLMs) and a commercial application in identifying surgical instruments from images.
  • To compare the performance of ChatGPT-4, ChatGPT-4o, Gemini, and Surgical-Instrument Directory (SID 2.0) in surgical instrument classification.

Main Methods:

  • A dataset of 92 high-resolution images featuring 25 types of surgical instruments (retractors, forceps, scissors, trocars) photographed from multiple angles was used.
  • Model performance was assessed using metrics including accuracy, weighted precision, recall, and F1 score.

Main Results:

  • ChatGPT-4o achieved the highest accuracy (89.1%) in categorizing instruments, outperforming SID 2.0 (77.2%), ChatGPT-4 (76.1%), and Gemini (44.6%).
  • All models demonstrated low accuracy in precise subtype identification (e.g., 'Mayo scissors'), with SID 2.0 at 39.1% and ChatGPT-4o at 33.69%.
  • ChatGPT-4 and 4o correctly identified all trocars, while Gemini identified all surgical scissors.

Conclusions:

  • Publicly available LLMs, particularly ChatGPT-4o, show promise for reliable surgical instrument categorization.
  • Precise identification of specific surgical instrument subtypes remains a significant challenge for current AI models.
  • Further AI model refinement is necessary to enhance accuracy and bolster patient safety in surgical instrument management.