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: May 10, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Local/non-local regularized image segmentation using graph-cuts: application to dynamic and multispectral MRI.

Erik A Hanson1, Arvid Lundervold

  • 1Department of Mathematics, University of Bergen, Bergen, Norway, erik.hanson@math.uib.no.

International Journal of Computer Assisted Radiology and Surgery
|June 15, 2013
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

Spatial-temporal recurrence patterns of grade 4 glioma using deep learning integrated multiparametric MRI and molecular pathology.

NPJ precision oncology·2026
Same author

Patient Similarity Networks for Irritable Bowel Syndrome: Revisiting Brain Morphometry and Cognitive Features.

Diagnostics (Basel, Switzerland)·2026
Same author

DiaGuide-LLM-Using large language models for patient-specific education and health guidance in diabetes.

Frontiers in artificial intelligence·2025
Same author

Deep-learning segmentation of the substantia nigra from multiparametric MRI: Application to Parkinson's disease.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Multi-Tool Marine Metabarcoding Bioassessment for Baselining and Monitoring Species and Communities in Kelp Habitats.

Molecular ecology resources·2025
Same author

Brain Morphometry and Cognitive Features in the Prediction of Irritable Bowel Syndrome.

Diagnostics (Basel, Switzerland)·2025
Same journal

Correspondence-free local-to-global liver deformation correction via implicit neural representation and biomechanical model.

International journal of computer assisted radiology and surgery·2026
Same journal

BronchoLumen: analysis of recent YOLO-based architectures for real-time bronchial orifice detection in video bronchoscopy.

International journal of computer assisted radiology and surgery·2026
Same journal

Model-guided medicine for early diagnosis of transthyretin-associated cardiac amyloidosis using multimodal data integration and standardized interoperable models (the CRONOS-ATTR study).

International journal of computer assisted radiology and surgery·2026
Same journal

Electromagnetic navigation for femoral osteotomy using high-accuracy X-ray-to-CT registration.

International journal of computer assisted radiology and surgery·2026
Same journal

Modular instrument actuation unit for robotic-assisted systems in laparoscopic surgery.

International journal of computer assisted radiology and surgery·2026
Same journal

Pose-aware deep perceptual similarity for iterative 2D/3D registration of knee joints using contrastive learning.

International journal of computer assisted radiology and surgery·2026
See all related articles

A novel spatial regularization method enhances image segmentation by incorporating non-local information. This approach improves the accuracy of segmenting complex shapes in medical imaging, like MRI scans, with minimal user input.

Area of Science:

  • Medical Imaging Analysis
  • Computer Vision
  • Image Processing

Background:

  • Image segmentation is crucial for analyzing multispectral, multichannel, and time-series data across various applications.
  • Traditional regularization methods often rely on local image information, leading to locally smooth or piecewise constant segmentations.
  • Existing techniques can struggle with complex shapes and require significant user interaction.

Purpose of the Study:

  • To develop and evaluate a new spatial regularization method for image segmentation that incorporates non-local information.
  • To improve the segmentation of multichannel images, including color images and magnetic resonance imaging (MRI) sequences.
  • To achieve accurate segmentation of regions with both smooth and complex non-smooth shapes.

Main Methods:

More Related Videos

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Related Experiment Videos

Last Updated: May 10, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

  • A novel spatial regularization technique was developed, integrating local edge properties, region boundary minimization, and non-local similarities.
  • The method was applied to feature space classification in multichannel images.
  • Implementation utilized a discrete graph-cut framework for efficient computation.

Main Results:

  • The proposed method demonstrated successful segmentation of regions with diverse shapes, from smooth to complex non-smooth structures.
  • Testing was conducted on multidimensional MRI recordings of human kidney and brain, as well as simulated MRI volumes.
  • The approach achieved accurate segmentation with minimal user intervention.

Conclusions:

  • The developed spatial regularization method effectively segments complex regions in multichannel images.
  • Non-local information integration enhances segmentation accuracy and robustness.
  • The method offers a significant improvement over traditional local regularization techniques, requiring less user interaction.