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

A 3D generalization of user-steered live-wire segmentation.

A X Falcão1, J K Udupa

  • 1Institute of Computing, State University of Campinas, SP, Brazil.

Medical Image Analysis
|January 12, 2001
PubMed
Summary

This study introduces a 3D live-wire method for faster and more repeatable image segmentation. This advanced technique significantly reduces user time for segmenting 3D/4D object boundaries in medical imaging.

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

Anatomic attention regions via optimal anatomy modeling and recognition for DL-based image segmentation.

Proceedings of SPIE--the International Society for Optical Engineering·2024
Same author

Optimal computed tomography-based biomarkers for prediction of incisional hernia formation.

Hernia : the journal of hernias and abdominal wall surgery·2023
Same author

Automated diagnosis of intestinal parasites: A new hybrid approach and its benefits.

Computers in biology and medicine·2020
Same author

Three-dimensional kinematic stress magnetic resonance image analysis shows promise for detecting altered anatomical relationships of tissues in the cervical spine associated with painful radiculopathy.

Medical hypotheses·2013
Same author

Boundary detection in multidimensions.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Relation of vision to global and regional brain MRI in multiple sclerosis.

Neurology·2007

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Anatomy

Background:

  • User-steered image segmentation requires significant human input for object definition.
  • Previous 2D live-wire and live-lane methods offered improved repeatability and speed over manual tracing.
  • Existing methods necessitate slice-by-slice segmentation for 2D/3D/4D data.

Purpose of the Study:

  • To introduce a 3D generalization of the live-wire approach for segmenting 3D/4D object boundaries.
  • To further reduce user time and improve accuracy in image segmentation tasks.
  • To enhance the efficiency and repeatability of 3D object boundary delineation.

Main Methods:

  • Developed a 3D extension of the live-wire algorithm.
  • Users define object boundaries on a few strategically chosen orthogonal slices.
  • Dijkstra's algorithm is employed to find minimum-cost paths for boundary segments.
  • Automatic tracing of boundary segments in all natural slices based on initial user input.

Main Results:

  • The 3D live-wire extension demonstrated superior repeatability (P < 0.0001) compared to 2D live-wire.
  • Achieved significant speed improvements: 2-6 times faster than 2D live-wire and 3-15 times faster than manual tracing (P < 0.01).
  • Validation studies on foot bone segmentation in MR images confirmed the method's efficacy.

Conclusions:

  • The 3D live-wire method offers a substantial advancement in 3D/4D image segmentation.
  • The approach significantly enhances efficiency and repeatability for delineating complex object boundaries.
  • This technique holds promise for accelerating medical image analysis and interpretation.

Related Experiment Videos