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

No-reference image quality metrics for structural MRI.

Jeffrey P Woodard1, Monica P Carley-Spencer

  • 1The MITRE Corporation, M/S H407 7515 Colshire Dr. McLean,VA 22102-7508, USA. jwoodard@mitre.org

Neuroinformatics
|September 1, 2006
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 journal

Metabolically Faithful 3D PET Restoration via Volumetric Swin Transformers.

Neuroinformatics·2026
Same journal

CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training.

Neuroinformatics·2026
Same journal

Increasing the Reliability of Functional Connectivity by Predicting Long-Scan Functional Connectivity based on Short-Scan Functional Connectivity: Model Exploration, Explanation, Validation, and Application.

Neuroinformatics·2026
Same journal

HESREN: A Derivative-Informed Reservoir Framework for Detecting Transient Neural Events and Windowless Estimation of Dynamic Functional Connectivity.

Neuroinformatics·2026
Same journal

Computational Morphometry of Peripheral Nerves: A Pipeline Perspective on Reproducibility and Generalization.

Neuroinformatics·2026
Same journal

Multimodal Branched Transport Infers Anatomically Aligned Brain Reaction Maps.

Neuroinformatics·2026
See all related articles

Objective image quality measures are needed for screening magnetic resonance images (MRIs). This study found that no-reference image quality measures, particularly those based on Natural Scene Statistics, can effectively detect distortions in MRIs.

Area of Science:

  • Medical Imaging
  • Image Processing
  • Neuroscience

Background:

  • Manual inspection of neuroimaging data for distortions is time-consuming and subjective.
  • Automated quality assessment is crucial due to the increasing volume of neuroimaging data.
  • Objective, no-reference image quality measures are needed to screen for distortions.

Purpose of the Study:

  • To evaluate the effectiveness of no-reference image quality measures for detecting distortions in magnetic resonance images (MRIs).
  • To identify which image quality measures are most reliable for automated screening of MRI data.

Main Methods:

  • Assessed 239 no-reference image quality measures from seven families using 1001 MRIs from 143 subjects.
  • Artificially distorted MRIs with Gaussian noise and intensity nonuniformity.

Related Experiment Videos

  • Used Analysis of Variance to identify effective quality measure families.

    • Main Results:

    • Two families of quality measures, Natural Scene Statistics and image compression-derived measures, were most effective.
    • These measures reliably discriminated between undistorted, noisy, and intensity-nonuniform MRIs.
    • The best measures were sensitive to distortion type and level, unaffected by other factors.

    Conclusions:

    • No-reference image quality measures show promise for automating MRI quality control.
    • Measures based on Natural Scene Statistics are particularly effective for detecting common MRI distortions.
    • Several promising quality measures are being integrated into operational MRI workflows.