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 Videos

An automated method for accurate vessel segmentation.

Xin Yang1, Chaoyue Liu1, Hung Le Minh1

  • 1Huazhong University of Science and Technology, Wuhan, 430074, People's Republic of China.

Physics in Medicine and Biology
|April 7, 2017
PubMed
Summary
This summary is machine-generated.

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

Concordant ETV6::RUNX1-positive acute lymphoblastic leukemia in monozygotic twins: a case report and review of the literature.

Frontiers in medicine·2026
Same author

Response to Letter to editor Regarding "Low incidence of acute actionable imaging findings in emergency department patients imaged for vertigo".

Emergency radiology·2026
Same author

Longitudinal Analysis of Location- and Growth-Associated Hemodynamics in Matched Paraclinoid Aneurysms.

AJNR. American journal of neuroradiology·2026
Same author

Enhancing WSI image classification with graph convolutional neural networks and model uncertainty modeling.

BMC medical imaging·2026
Same author

Multi-Omics Integration Identifies the Cholesterol Metabolic Enzyme <i>DHCR24</i> as a Key Driver in Breast Cancer.

Biology·2026
Same author

Low incidence of acute actionable imaging findings in emergency department patients imaged for vertigo: Retrospective analysis and proposed guidelines.

Emergency radiology·2025

This study introduces an automated system for accurate medical vessel segmentation, even in low signal-to-noise ratio (SNR) and noisy boundary regions. The system enhances image contrast and refines boundaries for improved diagnostic and surgical applications.

Area of Science:

  • Medical Image Analysis
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Accurate vessel segmentation is crucial for diagnosing conditions like diabetic retinopathy and guiding neurosurgery.
  • Existing segmentation methods struggle with low signal-to-noise ratio (SNR) and complex vessel boundaries.
  • Clinical applications require robust automated systems for reliable vessel analysis.

Purpose of the Study:

  • To develop an automated system for highly accurate 2D and 3D vessel segmentation.
  • To address challenges posed by low SNR and disturbed vessel boundaries in medical imaging.
  • To improve accuracy in clinical applications such as cerebral aneurysm analysis.

Main Methods:

  • Progressive contrast enhancement to improve visibility of challenging pixels.

Related Experiment Videos

  • Boundary refinement using Canny edge detection for improved segmentation accuracy.
  • Content-aware region-of-interest (ROI) adjustment for automatic identification of ambiguous areas.

    • Main Results:

    • Superior performance compared to state-of-the-art methods on public 2D retinal (DRIVE) and clinical 2D cerebral datasets.
    • Achieved 94% average accuracy on 3D CTA cerebral datasets, outperforming baseline methods by 23-33%.
    • Clinical application for cerebral aneurysm analysis showed consistent automatic diagnosis outcomes with manual measurements.

    Conclusions:

    • The proposed automated system achieves highly accurate vessel segmentation in challenging clinical scenarios.
    • The system demonstrates significant improvements over existing methods for both 2D and 3D medical images.
    • The validated clinical application highlights the system's utility in analyzing cerebral aneurysm development.