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

A soft-segmentation visualization scheme for magnetic resonance images.

Shashi Bhushan Mehta1, Santanu Chaudhury, Asok Bhattacharyya

  • 1Institute of Nuclear Medicine and Allied Sciences, Timar pur, Delhi 110054, India. sbmehta@vsnl.com

Magnetic Resonance Imaging
|October 11, 2005
PubMed
Summary

This study introduces a novel soft-segmentation visualization scheme for magnetic resonance (MR) images. This method enhances tissue characterization by improving the visibility of overlapping regions in brain MRIs.

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

Representation learning approach for understanding structured documents.

Scientific reports·2025
Same author

Silicodata: An Annotated Benchmark CXR Dataset for Silicosis Detection.

Scientific data·2025
Same author

MRI detection and grading of knee osteoarthritis - a pilot study using an AI technique with a novel imaging-based scoring system.

Biomaterials science·2025
Same author

A decentralized privacy-preserving XR system for 3D medical data visualization using hybrid biometric cryptosystem.

Scientific reports·2025
Same author

Differential Pattern of Brain Metabolism in Drug-naive versus Refractory OCD using [18F]-FDG PET/MRI Brain.

Indian journal of nuclear medicine : IJNM : the official journal of the Society of Nuclear Medicine, India·2025
Same author

K<sup>trans</sup> Calculation Using Reference Method Corrected Native T<sub>10</sub> for Breast Cancer Diagnosis.

Journal of medical physics·2023

Area of Science:

  • Medical Imaging
  • Image Processing
  • Computational Neuroscience

Background:

  • Traditional window width/window level methods struggle with MR images' wide dynamic range.
  • Accurate identification of tissue boundaries is challenging due to intensity variations.
  • Existing visualization tools have limitations in enhancing diagnostic value for MR images.

Purpose of the Study:

  • To develop an advanced visualization scheme for magnetic resonance (MR) images.
  • To improve the characterization of distinct tissue types in MR imaging.
  • To overcome limitations of current gray-value distribution visualization techniques.

Main Methods:

  • A soft-segmentation visualization scheme was developed using a connectionist approach.
  • Pixel partitions were generated from MR image histograms.

Related Experiment Videos

  • Selective visual depictions utilized pseudo-color based on fuzzy membership functions.

    • Main Results:

    • The proposed scheme successfully generated pixel partitions and selective visual depictions.
    • Additional overlapping regions between distinct tissue types were identified in clinical examples.
    • Improved visualization of healthy and diseased brain areas was demonstrated.

    Conclusions:

    • The soft-segmentation visualization scheme enhances tissue characterization in MR images.
    • This method aids in identifying subtle overlapping regions crucial for diagnosis.
    • The technique offers improved diagnostic value for MR image interpretation.