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

Coexistence of Multiple Myeloma, Mast Cell Hyperplasia, and Low-Level Myeloid Blastocytosis: A Report of a Rare Case.

The American journal of case reports·2026
Same author

Development of optimized fluorogenic DNA aptamers for a portable one-pot CRISPR-Cas12a platform for rapid and sensitive detection of monkeypox virus and chikungunya virus.

Journal of advanced research·2026
Same author

Beta-Glucan modulates monocyte plasticity and differentiation capacity to mitigate DSS-induced colitis.

eLife·2026
Same author

Integrative analysis reveals intra-tumoral microbial enterotypes shape host transcriptomes in colorectal cancer.

Cell reports·2026
Same author

Cold-induced Cpt1 repression uncouples lipid mobilization from oxidation and drives lipotoxicity during honeybee metamorphosis.

Insect biochemistry and molecular biology·2026
Same author

Electrothermal decoupling for investigating tumor treating fields of glioblastoma.

Physics in medicine and biology·2026

Related Experiment Video

Updated: Oct 14, 2025

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

151

Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network.

Jiacheng Wang1, Yueming Jin2, Shuntian Cai3

  • 1Department of Computer Science at School of Informatics, Xiamen University, Xiamen 361005, China.

Medical Image Analysis
|November 9, 2021
PubMed
Summary

We developed a novel shape-aware network for precise, real-time landmark detection in endoscopic submucosal dissection (ESD) surgery. This method improves accuracy and speed, outperforming existing techniques for complex surgical environments.

Keywords:
Endoscopic submucosal dissectionLandmark detectionReal-time detectionShape-aware relation network

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

682
Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor
06:39

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

174

Related Experiment Videos

Last Updated: Oct 14, 2025

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

151
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

682
Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor
06:39

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

174

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Surgical Technology

Background:

  • Landmark detection in endoscopic submucosal dissection (ESD) surgery is critical but challenging due to factors like bleeding and motion blur.
  • Existing methods often fail to adequately capture geometric relationships between landmarks or use overly complex aggregation.
  • Accurate and real-time landmark detection is essential for improving surgical outcomes in ESD procedures.

Purpose of the Study:

  • To propose a novel shape-aware relation network for accurate and real-time landmark detection in ESD surgery.
  • To address the limitations of existing methods by effectively utilizing spatial relationships among landmarks.
  • To develop a system that maintains high accuracy while operating in real-time within challenging surgical conditions.

Main Methods:

  • A shape-aware relation network was designed, leveraging spatial relationships among landmarks for improved detection.
  • An algorithm was developed to automatically generate relation keypoint heatmaps, encoding prior spatial knowledge without manual annotation.
  • Two complementary regularization schemes (pixel-level multi-task learning and global-level grouped consistency evaluation) were employed during training.

Main Results:

  • The proposed network achieved satisfactory accuracy and real-time performance, outperforming state-of-the-art methods.
  • Experimental results demonstrated superior accuracy and efficiency in landmark detection compared to existing approaches.
  • The method showed promising results in downstream applications, indicating its clinical potential in ESD.

Conclusions:

  • The novel shape-aware relation network offers a significant advancement for landmark detection in ESD surgery.
  • The method effectively integrates spatial landmark relationships, leading to enhanced accuracy and real-time capabilities.
  • The developed approach holds great potential for practical clinical application in ESD procedures.