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

A systematic approach to standardizing the visual appearance of endometriotic lesions for artificial intelligence recognition.

Acta obstetricia et gynecologica Scandinavica·2026
Same author

The Association Between Endometriosis and an Increased Risk of Epithelial Ovarian Cancer and Cardiovascular Disease: Perspective on a Patient-Centered Approach to Endometriosis, a Heterogeneous Disease.

Reproductive medicine and biology·2026
Same author

Prognostic impact of time to first recurrence in low-grade serous ovarian carcinoma: A multicentric retrospective study from the French TMRG network.

Gynecologic oncology·2026
Same author

Ovarian vascularisation assessment using indocyanine green after laparoscopic treatment of ovarian cysts - A feasibility study.

European journal of obstetrics, gynecology, and reproductive biology·2026
Same author

Does size matter? Expectations and limitations in imaging diagnosis of deep endometriosis?

Fertility and sterility·2026
Same author

Camera augmentation: enabling uncalibrated stereo matching of minimally invasive surgery images by training from the wealth of public synthetic image datasets.

International journal of computer assisted radiology and surgery·2026

Related Experiment Video

Updated: Jul 4, 2025

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

696

Automatic Smoke Analysis in Minimally Invasive Surgery by Image-Based Machine Learning.

Rasoul Sharifian1, Henrique M Abrão2, Sabrina Madad-Zadeh3

  • 1EnCoV, Institut Pascal, UMR 6602, CNRS/UCA, Clermont-Ferrand, France; SURGAR, Surgical Augmented Reality, Clermont-Ferrand, France; Department of Clinical Research and Innovation, Clermont-Ferrand University Hospital, Clermont-Ferrand, France.

The Journal of Surgical Research
|February 2, 2024
PubMed
Summary

This study introduces machine learning for analyzing surgical smoke. The system accurately quantifies smoke, assesses evacuation confidence, and recommends evacuation, matching or exceeding expert performance.

Keywords:
Image analysisMini-invasive surgeryNeural networkSmoke

More Related Videos

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.1K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Related Experiment Videos

Last Updated: Jul 4, 2025

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

696
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.1K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Area of Science:

  • Medical Imaging
  • Surgical Technology
  • Artificial Intelligence in Medicine

Background:

  • Minimally invasive surgery (MIS) generates electrosurgical smoke, reducing visibility and posing health risks to staff.
  • Current image analysis for surgical smoke is limited to basic classification.
  • Automatic analysis can enhance surgical safety and efficiency.

Purpose of the Study:

  • To develop and evaluate a machine learning approach for surgical smoke analysis.
  • To quantify smoke levels, estimate evacuation confidence, and recommend smoke evacuation.
  • To compare the performance of the developed system against human experts.

Main Methods:

  • Utilized deep neural networks for end-to-end training on three surgical smoke analysis tasks.
  • Developed datasets with expert annotations for smoke quantification, evacuation confidence, and evacuation recommendation.
  • Created indirect predictors combining tasks for improved performance on confidence and recommendation.

Main Results:

  • The neural network achieved comparable accuracy to experts in smoke quantification.
  • Indirect predictors outperformed experts in estimating smoke evacuation confidence (23.60% vs. 27.35% error).
  • The system demonstrated higher accuracy than experts in smoke evacuation recommendation (81.30% vs. 76.78%).

Conclusions:

  • Automatic surgical image analysis using machine learning is effective for smoke quantification, confidence estimation, and recommendation.
  • The developed system shows potential to match or surpass expert performance in managing surgical smoke.
  • This technology can improve surgical site visibility and staff safety during MIS.