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

Masseter segmentation using an improved watershed algorithm with unsupervised classification.

H P Ng1, S H Ong, K W C Foong

  • 1NUS Graduate School for Integrative Sciences and Engineering, Singapore.

Computers in Biology and Medicine
|October 24, 2007
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

Identifying eating disorders at the earliest opportunity: Testing the reliability of an online eating disorder screener (IOI-S) in primary care and youth mental health settings.

Early intervention in psychiatry·2023
Same author

Electrochemical quantification of atrazine-fulvic acid and removal through bismuth tungstate photocatalytic hybrid membranes.

Chemosphere·2022
Same author

Membrane technology for pesticide removal from aquatic environment: Status quo and way forward.

Chemosphere·2022
Same author

The state-of-the-art development of photocatalysts for the degradation of persistent herbicides in wastewater.

The Science of the total environment·2022
Same author

Nanomaterials for microplastic remediation from aquatic environment: Why nano matters?

Chemosphere·2022
Same author

Study protocol for an open labelled randomised controlled trial of perioperative oral nutrition supplement in breast and colorectal cancer patients undergoing elective surgery.

Trials·2021
Same journal

sEEGnal: an automated EEG preprocessing pipeline evaluated against expert-driven preprocessing.

Computers in biology and medicine·2026
Same journal

Corrigendum to "Integrating experimental biology, computational methods, and artificial Intelligence in anticancer drug discovery: Bridging the translational Gap" [Comput. Biol. Med. 213 (2026) 111832].

Computers in biology and medicine·2026
Same journal

Organ dose optimization for a point-of-care forearm X-ray photon-counting CT.

Computers in biology and medicine·2026
Same journal

Physics-guided transformation of breathomic feature spaces into disease-specific representations for respiratory disease classification.

Computers in biology and medicine·2026
Same journal

An AI-driven deep learning pipeline for taxonomic classification and biodiversity assessment of deep-sea environmental DNA.

Computers in biology and medicine·2026
Same journal

Rapid personalisation of cardiovascular models using invasively measured right ventricular pressure.

Computers in biology and medicine·2026
See all related articles

This study improves medical image segmentation by enhancing the watershed algorithm with automated thresholding and merging, significantly reducing over-segmentation for better anatomical representation.

Area of Science:

  • Medical image analysis
  • Computer vision
  • Biomedical engineering

Background:

  • The standard watershed algorithm often results in over-segmentation and is sensitive to false edges in medical images.
  • This leads to inaccurate anatomical representations, hindering diagnostic and analytical capabilities.

Purpose of the Study:

  • To address the limitations of the watershed algorithm in medical image segmentation.
  • To improve anatomical representation by reducing over-segmentation and enhancing accuracy.

Main Methods:

  • Introduced automated thresholding based on gradient magnitude histogram.
  • Implemented post-segmentation merging using an intensity similarity criterion.
  • Integrated K-means clustering for initial coarse segmentation of textured images.

Related Experiment Videos

  • Applied the improved algorithm to segment the masseter muscle in MRI scans.

    • Main Results:

    • The improved watershed algorithm merged over 90% of initial partitions, significantly reducing over-segmentation.
    • Achieved an average overlap index (kappa) of 90.6% for masseter segmentation.
    • Demonstrated comparable results to the gradient vector flow snake method.
    • Successfully merged 98% of initial partitions on average in MRI segmentation.

    Conclusions:

    • The enhanced watershed algorithm effectively reduces over-segmentation in medical images.
    • The proposed method provides accurate and robust anatomical segmentation.
    • This approach offers a valuable tool for medical image analysis, particularly for textured regions.