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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Capturing Finer-grained Long-range Dependency for Dense Prediction in Medical Images: An Empirical Investigation of MLPs.

IEEE journal of biomedical and health informatics·2026
Same author

<i>Letter:</i> Acupuncture Clinical Trials in the Chinese Clinical Registry: Growth, Regional Disparities, and Standardization Challenges.

Medical acupuncture·2026
Same author

B cell-derived exosomal tRNA-Pro-TGG served as a non-invasive biomarker and mediator of inflammation in progressive IgA nephropathy.

Frontiers in immunology·2025
Same author

Domain Anchored Features for Classification of OCT Images.

IEEE journal of biomedical and health informatics·2025
Same author

TiDE-Net: A time-guided dual-encoder ResUNet for Positron Emission Tomography (PET) image denoising.

Computer methods and programs in biomedicine·2025
Same author

A case report of retroperitoneal leiomyosarcoma originating from the right ovarian vein and invading the right renal vein and inferior vena cava.

The Journal of international medical research·2025

Related Experiment Video

Updated: May 11, 2026

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Robust model for segmenting images with/without intensity inhomogeneities.

Changyang Li1, Xiuying Wang, Stefan Eberl

  • 1Biomedical and Multimedia Information Technology research group, School of Information Technologies, The University of Sydney, Sydney 2006, Australia. chli7560@it.usyd.edu.au

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|May 23, 2013
PubMed
Summary
This summary is machine-generated.

This study introduces a new image segmentation model that uses global and local statistics to overcome noise and intensity variations. The method accurately segments images, outperforming existing techniques in challenging scenarios.

More Related Videos

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

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: May 11, 2026

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

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

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

  • Medical image analysis
  • Computer vision
  • Image processing

Background:

  • Image segmentation is crucial for medical image analysis.
  • Intensity inhomogeneities and image noise hinder accurate segmentation with region-based level set models.
  • Existing methods struggle with complex image artifacts.

Purpose of the Study:

  • To develop a novel image segmentation model.
  • To address challenges posed by intensity inhomogeneities and image noise.
  • To improve the accuracy and robustness of segmentation for medical imaging.

Main Methods:

  • A new region-based level set model incorporating global and local image statistics.
  • Global energy term utilizes a Gaussian model for intensity distribution estimation.
  • Local energy term leverages neighboring pixel influences to mitigate noise and inhomogeneities.

Main Results:

  • The proposed model demonstrates robustness in segmenting synthetic and real medical images with varying noise types and intensity inhomogeneities.
  • Achieved superior accuracy compared to local binary fitting and its systematic model for images with intensity inhomogeneities.
  • Outperformed Chan–Vese and graph-based algorithms (graph-cuts, random walker) in specific segmentation tasks involving noise and inhomogeneities.

Conclusions:

  • The novel segmentation model effectively handles intensity inhomogeneities and image noise.
  • Offers a more general and robust solution for accurate image segmentation across different modalities.
  • Represents a significant advancement over existing region-based and graph-based segmentation techniques.