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

Structure localization in brain images: application to relevant image selection.

U Sinha1, R Taira, H Kangarloo

  • 1Department of Radiological Sciences, University of California at Los Angeles, USA.

Proceedings. AMIA Symposium
|February 12, 2002
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

Predictive value of bedside clinical signs and symptoms in early diagnosis of deep vein thrombosis in acutely ill medical patients with special reference to deep vein thrombosis prophylaxis.

Journal of the Indian Medical Association·2012
Same author

Selective, novel spleen tyrosine kinase (Syk) inhibitors suppress chronic lymphocytic leukemia B-cell activation and migration.

Leukemia·2012
Same author

Recent advances in breast MRI and MRS.

NMR in biomedicine·2008
Same author

Efficient multilevel brain tumor segmentation with integrated bayesian model classification.

IEEE transactions on medical imaging·2008
Same author

Quantitative assessment of parallel acquisition techniques in diffusion tensor imaging at 3.0 Tesla.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same author

Analysis of the brain-stem white-matter tracts with diffusion tensor imaging.

Neuroradiology·2005
Same journal

Progressive display of very high resolution images using wavelets.

Proceedings. AMIA Symposium·2002
Same journal

The Chronus II temporal database mediator.

Proceedings. AMIA Symposium·2002
Same journal

Gene expression levels in different stages of progression in oral squamous cell carcinoma.

Proceedings. AMIA Symposium·2002
Same journal

An assessment of the visibility of MeSH-indexed medical web catalogs through search engines.

Proceedings. AMIA Symposium·2002
Same journal

Filtering for medical news items using a machine learning approach.

Proceedings. AMIA Symposium·2002
Same journal

Enriching the structure of the UMLS semantic network.

Proceedings. AMIA Symposium·2002
See all related articles

Automated methods using natural language processing and structure localization can accurately select relevant brain MRI images. This approach enhances the effective communication of study findings by identifying key imaging slices.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Neuroimaging Analysis

Background:

  • Increasingly large datasets in medical imaging necessitate automated methods for result interpretation.
  • Efficiently conveying study findings requires the selection of the most relevant images from imaging studies.
  • Manual image selection is time-consuming and prone to variability.

Purpose of the Study:

  • To develop and evaluate an automated method for identifying relevant images in MR brain studies.
  • To combine natural language processing (NLP) with automatic structure localization for image selection.
  • To improve the efficiency and accuracy of selecting critical imaging slices.

Main Methods:

  • A novel method integrating NLP for extracting finding locations and automatic structure localization algorithms.

Related Experiment Videos

  • Two structure localization approaches were evaluated: atlas-based registration and eigenimage search.
  • A prototype system was developed and tested on MR brain studies from nine patients.

    • Main Results:

    • The atlas registration method achieved 98% agreement with expert selection for relevant structure slices.
    • The eigenimage search method successfully located lateral ventricles in all test cases.
    • The combined NLP and structure localization approach demonstrated high accuracy in identifying relevant MR brain images.

    Conclusions:

    • The proposed automated method accurately identifies relevant image slices in MR brain studies.
    • This technique enhances the effective communication of imaging study results.
    • The integration of NLP and structure localization offers a promising solution for automated medical image selection.