April 2014
Volume 55, Issue 13
Free
ARVO Annual Meeting Abstract  |   April 2014
Recognizing glaucomatous defect patterns and detecting progression from visual field measurements using Gaussian mixture model and expectation maximization
Author Affiliations & Notes
  • Siamak Yousefi
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
  • Michael Henry Goldbaum
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
  • Felipe A Medeiros
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
  • Linda M Zangwill
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
  • Robert N Weinreb
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
  • Christopher A Girkin
    Department of Ophthalmology, School of Medicine, University of Alabama, Birmingham, AL
  • Jeffrey M Liebmann
    Department of Ophthalmology, New York University School of Medicine, New York, NY
    Einhorn Clinical Research Center, New York Eye and Ear Infirmary, New York, NY
  • Christopher Bowd
    Department of Ophthalmology, Hamilton Glaucoma Center, University of California at San Diego, La Jolla, CA
Investigative Ophthalmology & Visual Science April 2014, Vol.55, 985. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Siamak Yousefi, Michael Henry Goldbaum, Felipe A Medeiros, Linda M Zangwill, Robert N Weinreb, Christopher A Girkin, Jeffrey M Liebmann, Christopher Bowd; Recognizing glaucomatous defect patterns and detecting progression from visual field measurements using Gaussian mixture model and expectation maximization. Invest. Ophthalmol. Vis. Sci. 2014;55(13):985.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose
 

To recognize glaucomatous defect patterns and to detect glaucoma progression from longitudinal series of Standard Automated Perimetry (SAP) visual fields (VFs).

 
Methods
 

We obtained SAP thresholds (24-2 SITA) at 52 test points from 2085 eyes of 1398 participants in the Diagnostic Innovations in Glaucoma Study (DIGS) and the African Descent and Glaucoma Evaluation Study (ADAGES). 939 eyes had abnormal SAP results (PSD = 5%, GHT outside normal limits) and 1146 eyes had normal SAP results. First, we employed an unsupervised Gaussian Mixture Model using the Expectation Maximization (GEM) method to assign cross-sectional abnormal and normal VFs to clusters. We trained 600 models and chose the model with the best average combination of sensitivity and specificity. We then used principal component analysis to decompose each cluster into several axes. Next, in an independent dataset of 97 stable glaucoma eyes (from patients tested 5 times over 5 weeks), we computed the variability within each axis to determine the 95% confidence limits used to define progression. To test glaucoma progression detection, we employed a dataset of 76 progressing eyes (defined by stereophotograph assessment), projected the sequence of fields for each eye onto each axis, and assigned progression if the progression rate along any axis was greater than the 95% confidence limit (corrected for number of axes) of the stable eyes. Otherwise, non-progression was assigned.

 
Results
 

GEM clustering was 87% sensitive and 96% specific for correctly clustering VFs. Progression detection accuracy at 95% specificity using GEM axes was 29% sensitive. Sensitivities for linear regression (using the same criterion to define progression) of MD, PSD and VFI were 17%, 14% and 14%, respectively.

 
Conclusions
 

A progression detection framework was developed using GEM, that could identify glaucomatous visual field defect patterns and could detect glaucomatous progression from baseline and a sequence of follow-up SAP measurements, with higher sensitivity than regression of global SAP indices.

 
 
Average SAP at superior hemifield versus inferior hemifield (top) and MD versus PSD (bottom) for three clusters.
 
Average SAP at superior hemifield versus inferior hemifield (top) and MD versus PSD (bottom) for three clusters.
 
 
Sample eye that was identified as progressed since it hit the 95% CL line in gray (top); sample eye that was identified as non-progressed (bottom).
 
Sample eye that was identified as progressed since it hit the 95% CL line in gray (top); sample eye that was identified as non-progressed (bottom).
 
Keywords: 473 computational modeling • 758 visual fields  
×
×

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.

×