June 2013
Volume 54, Issue 15
Free
ARVO Annual Meeting Abstract  |   June 2013
Automatic Drusen Quantification and Risk Assessment of Age-related Macular Degeneration on Color Fundus Images
Author Affiliations & Notes
  • Mark J J P van Grinsven
    Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Yara Lechanteur
    Ophthalmology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Johannes van de Ven
    Ophthalmology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Bram van Ginneken
    Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Carel Hoyng
    Ophthalmology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Thomas Theelen
    Ophthalmology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Clara Sanchez
    Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, Netherlands
  • Footnotes
    Commercial Relationships Mark J J P van Grinsven, None; Yara Lechanteur, None; Johannes van de Ven, None; Bram van Ginneken, None; Carel Hoyng, None; Thomas Theelen, Heidelberg Engineering (F), Heidelberg Engineering (R); Clara Sanchez, None
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2013, Vol.54, 5496. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mark J J P van Grinsven, Yara Lechanteur, Johannes van de Ven, Bram van Ginneken, Carel Hoyng, Thomas Theelen, Clara Sanchez; Automatic Drusen Quantification and Risk Assessment of Age-related Macular Degeneration on Color Fundus Images. Invest. Ophthalmol. Vis. Sci. 2013;54(15):5496.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract
 
Purpose
 

To evaluate a machine learning algorithm that allows for computer aided diagnosis (CAD) of non-advanced age-related macular degeneration (AMD) by providing an accurate detection and quantification of drusen location, area and size.

 
Methods
 

Color fundus photographs of 407 eyes without AMD or with early to moderate AMD were randomly selected from a large European multicenter database. A machine learning system was developed to automatically detect and quantify drusen on each image. Based on detected drusen, the CAD software provided a risk assessment to develop advanced AMD. Evaluation of the CAD system was performed using annotations made by two blinded human graders.

 
Results
 

Free-response Receiver Operating Characteristics (FROC) analysis showed that the proposed system approaches the performance of human observers in detecting drusen. The estimated drusen area showed excellent agreement with both observers, with mean intra-class correlation coefficients (ICC) larger than 0.85. Maximum druse diameter agreement was lower with a maximum ICC of 0.69 but comparable to the interobserver agreement (ICC=0.79). For automatic AMD risk assessment, the system achieved areas under the Receiver Operating Characteristic (ROC) curve of 0.948 and 0.954, reaching similar performance as human observers. Sensitivity/specificity pairs of 0.87/0.93 and 0.87/0.93 were reached using both human observers as reference. Human observers have a sensitivity/specificity pair of 0.84/0.96 and 0.85/0.96 when compared to each other, respectively.

 
Conclusions
 

A machine learning system, capable of separating high risk from low risk patients with non-advanced AMD by providing accurate detection and quantification of drusen, was developed. The proposed method allows for quick and reliable diagnosis of AMD, opening the way for large dataset analysis within population studies and genotype-phenotype correlation analysis.

 
 
Top: Color fundus image containing drusen. Bottom: Automatically segmented drusen.
 
Top: Color fundus image containing drusen. Bottom: Automatically segmented drusen.
 
Keywords: 412 age-related macular degeneration • 504 drusen • 550 imaging/image analysis: clinical  
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×