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

Geodesic deformable models for medical image analysis

W J Niessen1, B M ter Haar Romeny, M A Viergever

  • 1Image Sciences Institute, University Hospital Utrecht, The Netherlands. wiro@isi.uu.nl

IEEE Transactions on Medical Imaging
|December 9, 1998
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

Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI.

EClinicalMedicine·2024
Same author

Association between prenatal alcohol exposure and children's facial shape: a prospective population-based cohort study.

Human reproduction (Oxford, England)·2023
Same author

Differences Between MR Brain Region Segmentation Methods: Impact on Single-Subject Analysis.

Frontiers in big data·2021
Same author

Recurrent inference machines as inverse problem solvers for MR relaxometry.

Medical image analysis·2021
Same author

Corrigendum to "Effects of hunger state on the brain responses to food cues across the life span" [NeuroImage 171 (2018) 246-255].

NeuroImage·2021
Same author

Automatic extraction of the intracranial volume in fetal and neonatal MR scans using convolutional neural networks.

NeuroImage. Clinical·2019

This study introduces implicit deformable models for medical image segmentation and enhancement. These models adapt topology naturally and segment multiple objects simultaneously, but struggle with poor image quality.

Area of Science:

  • Medical image analysis
  • Computer vision
  • Computational anatomy

Background:

  • Implicit deformable models offer topological adaptability, unlike classical explicit models.
  • Geodesic formulations of implicit models possess energy-minimizing properties.
  • Current methods face challenges with image artifacts and data-driven limitations.

Purpose of the Study:

  • To modify geodesic deformable models for enhanced medical image segmentation and enhancement.
  • To segment multiple objects simultaneously using implicit models.
  • To compare the performance of implicit and explicit deformable models.

Main Methods:

  • A modified geodesic deformable model approach considering all image level sets as energy-minimizing contours.
  • Application to cardiac computed tomography (CT) and magnetic resonance (MR) image segmentation and enhancement.

Related Experiment Videos

  • Comparative analysis of implicit and explicit deformable models for specific medical imaging tasks.

    • Main Results:

    • Simultaneous segmentation of multiple objects in medical images.
    • Effective enhancement and segmentation of cardiac CT and MR images.
    • Demonstration of implicit models' complementary nature and limitations in low-contrast or gapped boundaries.

    Conclusions:

    • Modified implicit deformable models enable simultaneous multi-object segmentation and image enhancement.
    • Implicit models are data-driven and perform poorly with artifacts like noise or motion.
    • Implicit and explicit models have complementary strengths for medical image analysis.