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

Segmentation of volumetric tissue images using constrained active contour models.

P S Umesh Adiga1

  • 1Bio-Imaging Group, MS 84-171, Lawrence Berkeley National laboratory, 1 Cyclotron Road, Berkeley, CA 94705, USA. upadiga@lbl.gov

Computer Methods and Programs in Biomedicine
|May 22, 2003
PubMed
Summary

This study introduces an active contour model for segmenting 3D histopathological images. The method enhances image quality and uses novel potentials for accurate nucleus segmentation in prostate tissue.

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

A binary segmentation approach for boxing ribosome particles in cryo EM micrographs.

Journal of structural biology·2004
Same author

An integrated system for feature evaluation of 3D images of a tissue specimen.

Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology·2002
Same author

Some efficient methods to correct confocal images for easy interpretation.

Micron (Oxford, England : 1993)·2000
Same author

Deformable models for segmentation of CLSM tissue images and its application in FISH signal analysis.

Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology·1999

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Histopathology

Background:

  • Accurate segmentation of 3D histopathological images is crucial for disease diagnosis.
  • Confocal laser scanning microscopy (CLSM) generates 3D image stacks of tissue specimens.
  • Existing segmentation methods struggle with noise and complex cellular structures.

Purpose of the Study:

  • To develop and apply an active contour model for segmenting 3D histopathological images.
  • To improve the accuracy and robustness of image segmentation in complex tissue samples.
  • To present results from prostate tissue section analysis.

Main Methods:

  • Acquisition of 3D images using confocal laser scanning microscopy (CLSM).
  • Application of noise reduction and feature enhancement techniques.

Related Experiment Videos

  • Utilizing a combination of distance and diffused gradient potentials for active contour model.
  • Employing region-based information to mitigate nucleus boundary influence.
  • Leveraging increased axial resolution for automatic contour propagation between slices.

    • Main Results:

    • Achieved a smooth potential surface for reliable active contour convergence.
    • Demonstrated effective reduction of neighboring nucleus interference.
    • Successfully propagated active contours across image slices by increasing axial resolution.
    • Presented validated segmentation results on prostate tissue images.

    Conclusions:

    • The proposed active contour model provides accurate segmentation of 3D histopathological images.
    • The method effectively handles noise and complex structures in tissue samples.
    • Automatic contour propagation enhances efficiency for 3D image analysis.