May 2006
Volume 47, Issue 13
Free
ARVO Annual Meeting Abstract  |   May 2006
Classifying Scanning Laser Polarimetry Images by a Limited Number of Features
Author Affiliations & Notes
  • K.A. Vermeer
    Quantitative Imaging Group, Delft University of Technology, Delft, The Netherlands
    Glaucoma Service, Rotterdam Eye Hospital, Rotterdam, The Netherlands
  • N.J. Reus
    Glaucoma Service, Rotterdam Eye Hospital, Rotterdam, The Netherlands
  • F.M. Vos
    Quantitative Imaging Group, Delft University of Technology, Delft, The Netherlands
  • A.M. Vossepoel
    Quantitative Imaging Group, Delft University of Technology, Delft, The Netherlands
  • H.G. Lemij
    Glaucoma Service, Rotterdam Eye Hospital, Rotterdam, The Netherlands
  • Footnotes
    Commercial Relationships  K.A. Vermeer, CZM, F; N.J. Reus, CZM, F; F.M. Vos, None; A.M. Vossepoel, None; H.G. Lemij, CZM, F; CZM, C.
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science May 2006, Vol.47, 3340. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      K.A. Vermeer, N.J. Reus, F.M. Vos, A.M. Vossepoel, H.G. Lemij; Classifying Scanning Laser Polarimetry Images by a Limited Number of Features . Invest. Ophthalmol. Vis. Sci. 2006;47(13):3340.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose:
 

The built–in classifier (NFI) of the GDx VCC (Carl Zeiss Meditec, Inc., Dublin, CA) that classifies scans as healthy or glaucomatous on a scale of 1–100 is a linear support vector (SV) machine that depends on a large number (87) of features derived from the scans. A classifier based on only a few features may be more intuitive to the clinician, without adversely affecting the classification results. This study compares the cross–validated accuracy of a linear SV classifier based on many features with one based on only a few features for the classification of SLP images.

 
Methods:
 

71 healthy and 71 glaucomatous eyes were included. The optimal cut–off value and the corresponding accuracy of the built–in classifier were determined. A linear SV classifier based on all 87 features, thereby mimicking the built–in classifier, was trained and tested. A linear SV classifier based on a limited number of features (1–6) was trained and tested. All errors were estimated by cross–validation to avoid biased results.

 
Results:
 

The optimal cut–off value for the NFI was 42, resulting in an error of 9.2%. A linear SV classifier, trained on all 87 features of the available data, gave an error of 5.0% (SD 0.5%). Reducing the number of features to four hardly increased the error; the estimation of the error of this classifier was 5.9% (SD 2.5%). All results of the limited feature sets are tabulated below.

 
Conclusions:
 

Comparing the errors of the retrained SV classifier and the four–feature SV classifier shows no significant difference, although the error of the 87–feature classifier has a somewhat smaller variance. Adding more features to the four–feature classifier did not significantly reduce the estimated error of 5.9%.  

 
Keywords: image processing • nerve fiber layer 
×
×

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.

×