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

Phantom-based performance evaluation: application to brain segmentation from magnetic resonance images.

B Moretti1, L M Fadili, S Ruan

  • 1GREYC-ISMRA UPRESA 6072, Caen, France. bmoretti@greyc.ismra.fr

Medical Image Analysis
|January 12, 2001
PubMed
Summary

This study introduces a novel distance-based method for evaluating brain segmentation accuracy using digital phantoms. This technique quantitatively assesses segmentation algorithms, improving upon subjective visual inspection for magnetic resonance imaging analysis.

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

Anterior knee laxity and ACL magnetic resonance signals in healthy and ACL-reconstructed knees following exercise.

European review for medical and pharmacological sciences·2025
Same author

Suitability of renewable organic materials for the synthesis of organo-mineral fertilizers: Driving factors and replacement of peat.

Heliyon·2025
Same author

Euthyroid Sick Syndrome (ESS) in proximal femoral fractures: a proof-of-concept evaluation of postoperative outcomes in elderly patients.

European review for medical and pharmacological sciences·2025
Same author

The gender role in the publishing of Authorships in high-impact orthopedic journals.

Musculoskeletal surgery·2024
Same author

Single-row versus transosseous technique in the arthroscopic treatment of rotator cuff tears: a meta-analysis.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2023
Same author

Optimisation of perioperative procedural factors to reduce the risk of surgical site infection in patients undergoing surgery: a systematic review.

Discover health systems·2023

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Neuroimaging

Background:

  • Accurate segmentation of brain tissues in magnetic resonance images (MRIs) is crucial for diagnosis and research.
  • Existing methods for evaluating segmentation accuracy often rely on subjective visual inspection, which can be biased.
  • Quantitative and objective evaluation metrics are needed to assess the performance of brain segmentation and editing algorithms.

Purpose of the Study:

  • To present a novel, distance-based technique for assessing the accuracy of segmentation algorithms.
  • To evaluate the performance of brain editing and brain tissue segmentation algorithms for MRIs.
  • To establish quantitative performance evaluation criteria using a realistic digital brain phantom.

Main Methods:

  • Utilized the Brainweb digital brain phantom as a 'ground truth' for performance evaluation.

Related Experiment Videos

  • Developed distance-based discrepancy features to measure differences between segmented tissues and the reference phantom model.
  • Employed a brain editing method combining mathematical morphology, region growing, and active contour models.
  • Applied a Markov random field model for brain tissue segmentation.

    • Main Results:

    • Demonstrated the ability to spatially determine and quantify segmentation errors relative to the reference phantom.
    • Showcased segmentation results on the Brainweb phantom and real MRIs.
    • Validated the effectiveness of active contours in refining segmentation accuracy.
    • The proposed distance-based technique provides objective performance evaluation.

    Conclusions:

    • The developed distance-based criteria can replace biased visual inspection for evaluating segmentation algorithms.
    • This method allows for quantitative assessment of algorithm sensitivity to parameters, noise, and artifacts.
    • The technique offers a robust framework for validating and comparing brain segmentation and editing algorithms in neuroimaging.