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

Drusen analysis in a human-machine synergistic framework.

R Theodore Smith1, Mahsa A Sohrab, Nicole M Pumariega

  • 1Columbia University Harkness Eye Institute, 160 Fort Washington Ave, Room 509C, New York, NY 10032, USA. rts1@columbia.edu

Archives of Ophthalmology (Chicago, Ill. : 1960)
|January 12, 2011
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

Central Airway Obstruction: From Technical Challenge to Health Care System Design.

Journal of cardiothoracic and vascular anesthesia·2026
Same author

Survival following sublobar resection after neoadjuvant therapy for T1N1-2M0 lung cancer.

PloS one·2026
Same author

Cardiovascular Disease and Age-Related Macular Degeneration.

American journal of ophthalmology·2026
Same author

Letter to the Editor: The limitations of centile curves for evaluating myopic eye growth.

Optometry and vision science : official publication of the American Academy of Optometry·2026
Same author

Efficiency Quality Index for Lobectomy - Developing a Quality Assessment Tool Scoring System.

The Journal of surgical research·2026
Same author

Elevated prevalence of age-related macular degeneration in a low-income urban primary care setting.

Discover public health·2026
Same journal

The economics of the initial preventive physical examination in medicare-reply.

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
Same journal

Modification of silicone oil retention sutures in aphakic eyes with iris loss-reply;.

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
Same journal

December 2011 archives web quiz winner.

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
Same journal

Angle involvement and glaucoma in patients with biopsy-proven iris melanoma: a response-reply.

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
Same journal

About this journal.

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
Same journal

In memoriam: goodwin m. Breinin, MD (1918-2011).

Archives of ophthalmology (Chicago, Ill. : 1960)·2013
See all related articles

Human-machine intelligence efficiently analyzes drusen in age-related macular degeneration (AMD) retinal images. This validated method offers fast, accurate quantitative analysis, improving upon traditional grading.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Age-related macular degeneration (AMD) is a leading cause of vision loss.
  • Accurate analysis of drusen, a key indicator of AMD, is crucial for diagnosis and monitoring.
  • Current manual grading methods can be time-consuming and subjective.

Purpose of the Study:

  • To integrate human-machine intelligence for efficient drusen image analysis in AMD.
  • To validate this novel method using two large, independent population-based datasets.
  • To assess the accuracy and efficiency of the user-interactive drusen detection algorithm.

Main Methods:

  • A user-interactive drusen detection algorithm was developed and applied to digitized color fundus slides.
  • A graphic user interface facilitated image preprocessing, region selection, and artifact correction.

Related Experiment Videos

  • Weighted kappa statistics were used to compare algorithm grading with human graders.
  • Validation was performed on two independent datasets: Netherlands Genetic Isolate Study and Columbia Macular Genetics Study.

    • Main Results:

    • The user-interactive system reduced image processing time by 60%.
    • After applying corrective filters, weighted kappa values for drusen detection ranged from 0.61 to 0.76, indicating fair to good agreement with human graders.
    • Concordance remained high in the second validation dataset.

    Conclusions:

    • The user-interactive human-machine intelligence approach enables fast and accurate quantitative retinal image analysis for drusen.
    • This method demonstrates fair to good agreement with human grading after accounting for common error sources.
    • The synergy between human expertise and machine computation optimizes drusen identification in AMD.