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

Complex Deep Neural Networks for Denoising Ultra-Fast Submillimeter T2*-weighted Imaging and Quantitative Susceptibility Mapping.

European journal of radiology artificial intelligence·2026
Same author

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding.

Advances in neural information processing systems·2026
Same author

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection.

Proceedings. IEEE International Conference on Computer Vision·2026
Same author

Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data.

Machine intelligence research (Beijing)·2026
Same author

Application of the 2024 McDonald Criteria in Individuals With Nonspecific Symptoms or Incidental Imaging Findings in a Multicenter Study.

Neurology·2026
Same author

Scaling 3D Compositional Models for Robust Classification and Pose Estimation.

Proceedings. IEEE International Conference on Computer Vision·2026

Related Experiment Video

Updated: Jul 9, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Detection and segmentation of pathological structures by the extended graph-shifts algorithm.

Jason J Corso1, Alan Yuille, Nancy L Sicotte

  • 1Center for Computational Biology, Laboratory of Neuro Imaging, University of California, Los Angeles, USA. jcorso@ucla.edu

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|December 7, 2007
PubMed
Summary

We developed an extended graph-shifts algorithm for efficient medical image segmentation. This method accurately detects brain tumors and multiple sclerosis lesions with high precision and recall.

More Related Videos

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Jul 9, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Biology

Background:

  • Image segmentation and labeling are crucial for analyzing medical images.
  • Accurate detection of pathological brain structures aids in diagnosis and treatment planning.
  • Existing algorithms may lack efficiency or accuracy in complex medical imaging tasks.

Purpose of the Study:

  • To introduce an extended graph-shifts algorithm for enhanced image segmentation and labeling.
  • To apply the algorithm to the specific tasks of brain tumor segmentation and multiple sclerosis lesion detection.
  • To evaluate the algorithm's accuracy, efficiency, and generalizability in medical imaging.

Main Methods:

  • Developed an extended graph-shifts algorithm utilizing a dynamic hierarchical image representation.
  • Implemented energy minimization through automatic selection of moves at different hierarchy levels.
  • Trained energy terms using statistical learning algorithms on medical imaging datasets.
  • Applied the algorithm to segment brain tumors and detect multiple sclerosis lesions in 3D volumes.

Main Results:

  • Achieved high accuracy in segmenting pathological brain structures, with precision and recall around 93%.
  • Demonstrated the algorithm's computational efficiency, capable of segmenting a full 3D volume in approximately one minute.
  • Validated the algorithm's effectiveness for both brain tumor segmentation and multiple sclerosis lesion detection.

Conclusions:

  • The extended graph-shifts algorithm offers an accurate and efficient solution for medical image segmentation.
  • This method shows significant potential for clinical applications in neuroimaging, particularly for detecting brain pathologies.
  • The algorithm's performance highlights the benefits of dynamic hierarchical representations and automated energy minimization for complex segmentation tasks.