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

GIST: an interactive, GPU-based level set segmentation tool for 3D medical images.

Joshua E Cates1, Aaron E Lefohn, Ross T Whitaker

  • 1Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112-9205, USA. cates@cs.utah.edu

Medical Image Analysis
|September 29, 2004
PubMed
Summary

This study introduces a novel tool for 3D medical image segmentation using graphics processing units (GPUs) to achieve interactive rates. This accelerates the segmentation process and allows for real-time parameter tuning, improving segmentation reliability.

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

Pro-inflammatory effects of inhaled Great Salt Lake dust particles.

Particle and fibre toxicology·2025
Same author

Pro-Inflammatory Effects of Inhaled Great Salt Lake Dust Particles.

Research square·2024
Same author

HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2024
Same author

Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes.

International journal of environmental research and public health·2022
Same author

Prediction of femoral head coverage from articulated statistical shape models of patients with developmental dysplasia of the hip.

Journal of orthopaedic research : official publication of the Orthopaedic Research Society·2021
Same author

A Nonparametric Approach for Estimating Three-Dimensional Fiber Orientation Distribution Functions (ODFs) in Fibrous Materials.

IEEE transactions on medical imaging·2021

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Geometry

Background:

  • Level set methods are powerful for 3D medical image segmentation but suffer from slow computation and difficult parameter tuning.
  • These limitations hinder the practical application of level sets in clinical settings.

Purpose of the Study:

  • To develop an interactive tool for 3D medical image segmentation that overcomes the speed and parameter tuning limitations of traditional level set methods.
  • To enable real-time feedback for users to control segmentation models effectively.

Main Methods:

  • Implemented a 3D level set solver on a commodity graphics processing unit (GPU) utilizing a novel GPU memory management technique.
  • Developed intensity-based speed functions for intuitive control of the deformable model's behavior.

Related Experiment Videos

  • Achieved interactive computation rates for the level-set partial differential equation (PDE) solver.

    • Main Results:

    • The GPU-accelerated solver enables interactive rates, providing immediate feedback for parameter adjustment.
    • Intensity-based speed functions allow for quick and intuitive user control over segmentation.
    • The combined interactive tools facilitate the production of reliable 3D segmentations.

    Conclusions:

    • The novel tool significantly enhances the efficiency and usability of 3D level set segmentation.
    • Interactive rates and intuitive controls lead to improved segmentation accuracy and reliability.
    • Demonstrated effectiveness through qualitative results across diverse datasets and quantitative evaluation in brain tumor segmentation.