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

Improved watershed transform for medical image segmentation using prior information.

V Grau1, A U J Mewes, M Alcañiz

  • 1Surgical Planning Laboratory, Brigham and Women's Hospital and Harvard Medical School, Boston, MA 02138, USA. vgrauc@bwh.harvard.edu

IEEE Transactions on Medical Imaging
|April 16, 2004
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

Reduced preoperative serum choline esterase levels and fecal peritoneal contamination as potential predictors for the leakage of intestinal sutures after source control in secondary peritonitis.

World journal of emergency surgery : WJES·2024
Same author

Publisher Correction: Brain charts for the human lifespan.

Nature·2022
Same author

Brain charts for the human lifespan.

Nature·2022
Same author

An MRI method for parcellating the human striatum into matrix and striosome compartments in vivo.

NeuroImage·2021
Same author

Commercial α1-antitrypsin preparations markedly differ in their potential to inhibit the ATP-induced release of monocytic interleukin-1β.

Pulmonary pharmacology & therapeutics·2021
Same author

Tractography of the Cerebellar Peduncles in Second- and Third-Trimester Fetuses.

AJNR. American journal of neuroradiology·2021

This study enhances the watershed transform for medical image segmentation by incorporating prior information and atlas registration. The improved algorithm effectively addresses oversegmentation and noise issues in MRI analysis.

Area of Science:

  • Medical image analysis
  • Computer vision
  • Biomedical engineering

Background:

  • The watershed transform is a valuable image segmentation technique due to its simplicity and completeness.
  • However, its application in medical imaging is limited by oversegmentation and sensitivity to noise.
  • Detecting thin or low signal-to-noise ratio structures remains a challenge for standard watershed algorithms.

Purpose of the Study:

  • To improve the watershed transform for medical image segmentation by integrating prior information.
  • To develop a method combining watershed transform with atlas registration using markers.
  • To validate the enhanced algorithm on challenging medical imaging applications.

Main Methods:

  • Introduced prior information into the watershed transform calculation via a preceding probability map.

Related Experiment Videos

  • Developed a marker-based approach to integrate watershed transform with atlas registration.
  • Applied the novel algorithm to segment knee cartilage and gray/white matter in MR images.

    • Main Results:

    • The enhanced watershed transform effectively reduced oversegmentation and improved the detection of challenging structures.
    • The integration with atlas registration provided robust segmentation results.
    • Numerical validation confirmed the algorithm's strength in medical image segmentation tasks.

    Conclusions:

    • The proposed enhancement significantly improves the watershed transform's applicability to medical image analysis.
    • The method offers a robust solution for segmenting complex structures in MRI.
    • This approach demonstrates potential for advancing automated medical image segmentation.