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

Molecular mechanism of crisaborole combined with erythromycin against methicillin-resistant <i>Staphylococcus aureus in vivo</i> and <i>in vitro</i>.

Frontiers in microbiology·2025
Same author

Screening of cytokines-cytokine receptor-associated genes in childhood asthma based on bioinformatics.

Integrative biology : quantitative biosciences from nano to macro·2025
Same author

Subcritical water extraction improves the ability of Auricularia cornea var. Li. Polysaccharides to stabilize hydrogels and emulsion gels.

International journal of biological macromolecules·2025
Same author

SALT OVERLY SENSITIVE2 and AMMONIUM TRANSPORTER1;1 contribute to plant salt tolerance by maintaining ammonium uptake.

The Plant cell·2025
Same author

Transdermal microneedle-assisted ultrasound-enhanced CRISPRa system to enable sono-gene therapy for obesity.

Nature communications·2025
Same author

Homeostasis and metabolism of iron and other metal ions in neurodegenerative diseases.

Signal transduction and targeted therapy·2025

Related Experiment Video

Updated: Jul 5, 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

2.8K

A lightweight segmentation network for endoscopic surgical instruments based on edge refinement and efficient

Mengyu Zhou1,2, Xiaoxiang Han2, Zhoujin Liu1

  • 1School of Medical Instruments, Shanghai University of Medicine & Health Sciences, Shanghai, P.R.China.

Peerj. Computer Science
|January 23, 2024
PubMed
Summary

This study introduces a new lightweight model for precise surgical instrument segmentation in robotic surgery. The model achieves high accuracy with significantly fewer parameters, improving safety and decision-making for surgeons.

Keywords:
Efficient self-attentionLightweight networkSemantic segmentationSurgical instruments

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Related Experiment Videos

Last Updated: Jul 5, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Area of Science:

  • Robotics
  • Medical Imaging
  • Computer Vision

Background:

  • Surgical instrument segmentation is vital for robotic-assisted surgery.
  • Existing models struggle with precise edges and high parameter counts, limiting deployment.

Purpose of the Study:

  • To develop a lightweight semantic segmentation model for accurate surgical instrument segmentation.
  • To improve edge refinement and reduce model complexity for practical application.

Main Methods:

  • Utilized a lightweight densely connected network for efficient feature extraction.
  • Employed a decoder with a feature pyramid and criss-cross self-attention for multi-scale integration and edge accuracy.
  • Developed a private dataset and used public datasets (Kvasir-instrument, Endovis2017) for training and validation.

Main Results:

  • Achieved a mean Intersection over Union (mIoU) of 97.11% on a private dataset with only 466K parameters.
  • Obtained excellent mIoU scores of 93.24% and 95.83% on public datasets.
  • Demonstrated superior performance with lower parameters compared to state-of-the-art models.

Conclusions:

  • The proposed lightweight model significantly enhances surgical instrument segmentation accuracy and edge definition.
  • The model's efficiency and high performance offer a foundation for advanced research in surgical robotics.