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 Experiment Video

Updated: Jul 5, 2026

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

ESD-VesNet: uncertainty-aware vessel segmentation network for endoscopic submucosal dissection with hard negative

Mengya Xu1,2, Ming Chen3, Zhen Li4

  • 1Department of Computer Science and Engineering, CUHK, Hong Kong, China. mengyaxu@cuhk.edu.hk.

International Journal of Computer Assisted Radiology and Surgery
|July 3, 2026
PubMed
Summary

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

Confined Internal Standard Core-Gap-Shell Nanoprobes for Ratiometric SERS Sensing of Urine pH.

Sensors (Basel, Switzerland)·2026
Same author

Oncogenic Viruses and Inhaled Microplastics: A Double Hit Hypothesis for Asthma Progression and Lung Cancer Development.

Reviews in medical virology·2026
Same author

BmFOXP1 and BmSGF1 divergently cooperate with BmGATAβ4 to regulate vitellogenin expression during vitellogenesis of the silkworm, Bombyx mori.

Insect biochemistry and molecular biology·2026
Same author

Accurate 3D recording: Integrating ground-based LiDAR data and 3D segmentation network to extract 3D traits and analyze genetics in wheat populations.

Plant phenomics (Washington, D.C.)·2026
Same author

Condition-Associated Pattern Extraction and Recovery From Multi-Condition Single-Cell RNA-seq Data With CAPER.

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

Framework Response-Activated SERS Sensing: A Guest-Induced "Gate-Opening" Strategy for Ultrasensitive Sub-Ppt Formaldehyde Detection.

ACS sensors·2026

This study introduces ESD-VesNet, an AI tool for endoscopic submucosal dissection (ESD) that accurately identifies blood vessels and their uncertainty, significantly reducing bleeding risks during procedures.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Endoscopy
  • Surgical Safety

Background:

  • Intraoperative bleeding during endoscopic submucosal dissection (ESD) is a significant risk.
  • Accurate identification and pre-coagulation of submucosal vessels are crucial for preventing bleeding.
  • Current methods may lack precision in vessel detection, leading to potential complications.

Purpose of the Study:

  • To develop an AI-driven system for precise submucosal vessel segmentation in ESD.
  • To enhance surgical safety by reducing the risk of intraoperative bleeding.
  • To provide uncertainty awareness in vessel detection to minimize unnecessary interventions.

Main Methods:

  • Introduction of ESD-VesNet, a framework based on SAM3 with an evidential head for probability and uncertainty output.
Keywords:
Endoscopic submucosal dissectionEvidential deep learningSAM3Uncertainty estimationVessel segmentation

More Related Videos

The Pocket-Creation Procedure of Endoscopic Submucosal Dissection for Large Rectal Laterally Spreading Tumors
04:09

The Pocket-Creation Procedure of Endoscopic Submucosal Dissection for Large Rectal Laterally Spreading Tumors

Published on: February 13, 2026

Related Experiment Videos

Last Updated: Jul 5, 2026

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

The Pocket-Creation Procedure of Endoscopic Submucosal Dissection for Large Rectal Laterally Spreading Tumors
04:09

The Pocket-Creation Procedure of Endoscopic Submucosal Dissection for Large Rectal Laterally Spreading Tumors

Published on: February 13, 2026

  • Training on a custom ESD-Vessel dataset with positive and hard negative samples.
  • Implementation of false-positive-aware training and uncertainty-guided hard negative mining.

    • Main Results:

    • ESD-VesNet achieved a Vessel Detection Rate of 96.81% with a low Background False Positive Rate of 0.61%.
    • High structural quality metrics (E-measure 0.7275, S-measure 0.7223) were reported.
    • The model demonstrated robustness in challenging conditions like bubbles, debris, and blood seepage.

    Conclusions:

    • The integration of SAM3, evidential uncertainty, and hard negative mining creates a clinically valuable vessel segmentation system.
    • ESD-VesNet offers high detection sensitivity and low false positives, contributing to safer ESD procedures.
    • This approach supports clinicians by providing reliable vessel identification, minimizing risks.