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

Binocular Non-Cycloplegic Ocular Parameters for Modeling Cycloplegic SER in Children.

Translational vision science & technology·2026
Same author

Si-Miao-Yong-An Decoction ameliorates deep vein thrombosis by suppressing NAT10-mediated ac4C modification of HMOX1 mRNA.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Retraction notice to 'Chemical identification of the Viola phillipina extracts and their anti-acne activity: A comparison with isotretinoin and salicylic acid' [Fitoterapia 191 (2026) 107238].

Fitoterapia·2026
Same author

Synthesis, Biological Evaluation and Structure-Activity Relationship of Juglone Derived Naphthoquinones as Potential Antipsoriatic Agents.

Biomolecules·2026
Same author

Self-Healing Bilayer Hydrogel Solid-State Electrochemical Platform: Time-Resolved In Situ Dynamic Monitoring of <i>Escherichia coli</i> Activity.

Gels (Basel, Switzerland)·2026
Same author

Harnessing MDM2-Mediated Targeted Degradation of Transcriptional and Epigenetic Machinery to Disrupt Oncogenic Addictions in Pediatric Sarcoma.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Related Experiment Video

Updated: Jan 6, 2026

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

3.3K

A Holistically-Nested U-Net: Surgical Instrument Segmentation Based on Convolutional Neural Network.

Lingtao Yu1, Pengcheng Wang2, Xiaoyan Yu1

  • 1College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, Heilongjiang Province, China.

Journal of Digital Imaging
|October 10, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a novel U-Net based model for surgical instrument segmentation, enhancing surgeon awareness during operations. The improved model demonstrates strong performance in segmenting instruments from laparoscopic surgical images.

Keywords:
Convolutional neural networkDeep learningSurgical instrument segmentation

More Related Videos

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

3.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

715

Related Experiment Videos

Last Updated: Jan 6, 2026

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

3.3K
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

3.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

715

Area of Science:

  • Medical Imaging
  • Computer-Assisted Surgery
  • Artificial Intelligence in Medicine

Background:

  • Surgical instrument segmentation is crucial for computer-assisted surgery.
  • Enhanced context-awareness for surgeons during operations is a critical need.
  • Existing segmentation models require improvement for complex surgical environments.

Purpose of the Study:

  • To propose a novel U-Net based model for improved surgical instrument segmentation.
  • To enhance the context-awareness of surgeons through accurate instrument identification.
  • To validate the model's performance against established architectures using real surgical data.

Main Methods:

  • A modified U-Net architecture incorporating multi-scale feature aggregation and cascaded dilated convolutions.
  • Utilized dense upsampling convolution for efficient feature reconstruction.
  • Implemented a comprehensive side loss function supervising all layers for robust training.
  • Compared the proposed model against the standard U-Net architecture on a diverse laparoscopy image dataset.

Main Results:

  • The proposed model achieved superior performance in surgical instrument segmentation compared to the baseline U-Net.
  • The aggregation of multi-scale features and cascaded dilated convolutions improved segmentation accuracy.
  • The novel upsampling and loss function strategies contributed to effective model training and performance.

Conclusions:

  • The developed U-Net based model offers a significant advancement for surgical instrument segmentation.
  • This technology has the potential to improve surgeon's situational awareness and aid in computer-assisted surgical systems.
  • Further research can explore integration into real-time surgical guidance systems.