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 Video

Updated: Jun 5, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Optimal threshold selection for segmentation of dense homogeneous objects in tomographic reconstructions.

Wim van Aarle1, Kees Joost Batenburg, Jan Sijbers

  • 1IBBT-Visionlab, University of Antwerp, B-2610Antwerp, Belgium. wim.vanaarle@ua.ac.be

IEEE Transactions on Medical Imaging
|January 11, 2011
PubMed
Summary

This study introduces a new method for segmenting dense objects in tomographic images. By minimizing segmentation inconsistency using projection data, it achieves more accurate results than traditional thresholding techniques.

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

Noise2Ghost: self-supervised deep convolutional reconstruction for ghost imaging.

Optics express·2026
Same author

Data-Driven Characterization of Knee Structures Using Non-Negative Matrix Factorization of 3D Multi-Echo UTE MRI.

NMR in biomedicine·2026
Same author

Combining magnetic resonance imaging and evoked potentials enhances machine learning prediction of multiple sclerosis disability worsening.

Frontiers in immunology·2026
Same author

Physiological cerebrospinal fluid interactions between brain and eye structures are altered after long-duration spaceflight.

Experimental physiology·2026
Same author

Leveraging hand-crafted radiomics on multicenter FLAIR MRI for predicting disability worsening in people with multiple sclerosis.

Frontiers in neuroscience·2025
Same author

Edge illumination X-ray phase contrast imaging with continuous mask motion.

Optics express·2025

Area of Science:

  • Medical Imaging
  • Image Processing
  • Computational Science

Background:

  • Accurate segmentation of dense, homogeneous objects in tomographic reconstructions is crucial for quantitative analysis.
  • Global thresholding is a common technique, but its effectiveness is limited by noise and artifacts in tomograms, which obscure clear peaks in image histograms.
  • Selecting an appropriate threshold value from noisy histograms remains a significant challenge in image segmentation.

Purpose of the Study:

  • To develop a novel and robust method for segmenting dense, homogeneous objects in tomographic reconstructions.
  • To improve the accuracy of object segmentation by addressing the limitations of traditional global thresholding methods.
  • To introduce a new threshold estimation approach that leverages projection data for optimal threshold determination.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jun 5, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Main Methods:

  • A new threshold estimation approach termed segmentation inconsistency minimization was developed.
  • This method utilizes the available projection data to determine the optimal global threshold for segmentation.
  • The algorithm was validated using both simulated tomographic data and experimental micro-computed tomography (μCT) data.

Main Results:

  • The proposed segmentation inconsistency minimization method demonstrated superior performance in segmenting dense objects.
  • The algorithm achieved more accurate segmentations compared to alternative threshold selection methods.
  • Testing on simulation and experimental μCT data confirmed the effectiveness of the novel approach.

Conclusions:

  • Segmentation inconsistency minimization offers a more accurate and reliable method for segmenting dense objects in tomographic reconstructions.
  • This novel approach overcomes the limitations of conventional histogram-based thresholding, particularly in the presence of noise and artifacts.
  • The method's successful application to both simulated and experimental data highlights its potential for widespread use in tomographic image analysis.