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

Computer-assisted, interactive fundus image processing for macular drusen quantitation.

D S Shin1, N B Javornik, J W Berger

  • 1Computer Vision Laboratory, Scheie Eye Institute, University of Pennsylvania School of Medicine, Philadelphia 19104, USA.

Ophthalmology
|June 12, 1999
PubMed
Summary

This study developed automated software to accurately measure drusen in eye images, improving clinical trials for age-related macular degeneration (AMD). The software provides efficient and robust quantitation, enhancing diagnostic capabilities.

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

Common femoral arterial access and arteriography in infants: Principles, pearls, and pitfalls.

Clinical imaging·2023
Same author

Semi-automatic segmentation and surface reconstruction of computed tomography images by using rotoscoping and warping techniques.

Folia morphologica·2019
Same author

Sectioned images and surface models of a cadaver head with reference to botulinum neurotoxin injection.

Folia morphologica·2018
Same author

Sectioned images and surface models of a cadaver for understanding the free vascularised anterior rib flap.

Folia morphologica·2016
Same author

Accessible and informative sectioned images and surface models of the maxillofacial area for orthognathic surgery.

Folia morphologica·2015
Same author

Segmentation and surface reconstruction of a cadaver heart on Mimics software.

Folia morphologica·2015

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computational Biology

Background:

  • Age-related macular degeneration (AMD) is a leading cause of vision loss.
  • Accurate quantification of drusen is crucial for AMD clinical trials.
  • Current manual grading of drusen is time-consuming and subjective.

Purpose of the Study:

  • To design and validate a software package for quantifying drusen area in color fundus photographs.
  • To enable efficient and accurate clinical trials for AMD.

Main Methods:

  • Developed an algorithm and software for automated drusen quantification.
  • Utilized digitized color fundus photographs from patient records and a clinical trial.
  • Employed image preprocessing, local thresholding, and region-growing algorithms with supervised levels.

Related Experiment Videos

  • Validated against manual grading using intraclass correlation coefficients.

    • Main Results:

    • Automated supervised image analysis demonstrated high robustness and accuracy.
    • Processing times were significantly reduced, averaging 5 seconds per image with minimal supervision.
    • High concordance with manual grading was achieved (intraclass correlation coefficients of 0.92 and 0.93).

    Conclusions:

    • Automated supervised fundus image analysis is an efficient, robust, and valid method for drusen quantitation.
    • This technique can significantly aid in conducting efficient and accurate clinical trials for AMD.