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

Identification of a mitochondrial biomarker signature linking neuroinflammation to neuronal dysfunction in spinal cord injury.

Scientific reports·2026
Same author

Identification of ursolic acid from Wumei as a syk-targeting anti-allergic agent using a piezoresistive cantilever biosensor.

Journal of pharmaceutical and biomedical analysis·2026
Same author

Spinal Manipulative Therapy for Moderate-to-Severe Adolescent Idiopathic Scoliosis: A Randomized Controlled Trial.

Chinese journal of integrative medicine·2025
Same author

Designing a Multi-Epitope Vaccine Against MPXV and HIV Based on an Immunoinformatic Approach.

International journal of molecular sciences·2025
Same author

Constructing Cu<sup>0</sup>/Cu<sup>+</sup> interface on copper foils to boost electrochemical CO<sub>2</sub> reduction to ethylene.

Chemical communications (Cambridge, England)·2025
Same author

Cellular Mechanical Phenotypes of Drought-Resistant and Drought-Sensitive Rice Species Distinguished by Double-Resonator Piezoelectric Cytometry Biosensors.

Biosensors·2025

Related Experiment Video

Updated: Sep 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Deep learning approach for bubble segmentation from hysteroscopic images.

Dong Wang1, Wei Dai1, Ding Tang1

  • 1State Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai, 200240, China.

Medical & Biological Engineering & Computing
|April 9, 2022
PubMed
Summary

Computer vision accurately extracts gas bubble parameters from hysteroscopy images. This technology aids in developing automatic bubble removal devices for safer hysteroscopic surgery.

Keywords:
Bubble size distributionEdge-aware networkGas embolismHysteroscopic surgeryMarker-controlled watershed

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis
05:31

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis

Published on: September 5, 2020

6.0K

Related Experiment Videos

Last Updated: Sep 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis
05:31

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis

Published on: September 5, 2020

6.0K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Surgical Technology

Background:

  • Gas embolism is a critical risk during hysteroscopic surgery.
  • Monitoring bubble parameters in real-time is essential for preventing complications.
  • Existing methods lack the precision needed for automatic bubble removal systems.

Purpose of the Study:

  • To develop a robust computer vision framework for extracting gas bubble parameters from hysteroscopy images.
  • To enhance the accuracy and reliability of bubble detection and measurement.
  • To provide a foundation for automated bubble removal devices in hysteroscopic procedures.

Main Methods:

  • A novel framework combining a deep edge-aware network for segmentation and a marker-controlled watershed algorithm for instance separation.
  • The edge-aware network utilizes an encoder-decoder architecture with a contour branch supervised by edge losses.
  • Post-processing with the watershed algorithm calculates bubble size distribution.

Main Results:

  • The proposed model demonstrated superior performance compared to traditional segmentation methods.
  • Key performance metrics include Accuracy (0.859±0.017), Sensitivity (0.868±0.019), Precision (0.955±0.005), Dice score (0.862±0.005), and mean IoU (0.758±0.007).
  • The system effectively segments and quantifies bubbles in hysteroscopic images.

Conclusions:

  • The developed computer vision framework accurately extracts critical bubble parameters from hysteroscopy images.
  • This approach offers a valuable reference for the development of automatic bubble removal devices.
  • Improved bubble monitoring can significantly enhance patient safety during hysteroscopic surgery.