June 2013
Volume 54, Issue 15
Free
ARVO Annual Meeting Abstract  |   June 2013
Computational discovery of optic nerve head phenotypes
Author Affiliations & Notes
  • Mark Christopher
    Biomedical Engineering, University of Iowa, Iowa City, IA
  • Li Tang
    Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA
  • John Fingert
    Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA
  • Todd Scheetz
    Biomedical Engineering, University of Iowa, Iowa City, IA
    Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA
  • Michael Abramoff
    Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA
    Veterans Affairs, University of Iowa, Iowa City, IA
  • Footnotes
    Commercial Relationships Mark Christopher, None; Li Tang, None; John Fingert, None; Todd Scheetz, None; Michael Abramoff, IDx LLC (E), IDx LLC (I), University of Iowa (P)
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2013, Vol.54, 4819. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mark Christopher, Li Tang, John Fingert, Todd Scheetz, Michael Abramoff, Ocular Hypertension Treatment Study; Computational discovery of optic nerve head phenotypes. Invest. Ophthalmol. Vis. Sci. 2013;54(15):4819.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose
 

To apply computational methods in the discovery of 3D optic nerve head (ONH) structural phenotype features for detecting and monitoring glaucoma damage, and the discovery of new phenotype-genotype associations.

 
Methods
 

A subset of participants (n=370) from the Ocular Hypertension Treatment Study was selected on the basis of availability of simultaneous stereo fundus images. A stereo correspondence algorithm, optimized for fundus images, was applied to the set of stereo fundus pairs to produce a disparity map that quantitatively measured the ONH structure for each subject (Figure 1). Principal component analysis (PCA) was applied to the disparity maps to extract computational 3D ONH structural features. The first 25 principal components, or features, were retained and examined individually in building a predictive regression model for horizontal cup-to-disc ratio (HCDR). The relationship between the ONH features and demographic variables gender, age and ethnicity were also examined. In all cases, Bonferroni correction was used to adjust for multiple hypothesis testing.

 
Results
 

Five of the 25 computational 3D ONH features were significantly associated (corrected p<0.05) with HCDR, the association for a single ONH feature is shown in Figure 2. Combined, these features explained 65% of the variance in HCDR in the subjects. Significant associations were also found between the features and ethnicity, while suggestive associations were found with age and gender.

 
Conclusions
 

Using computational methods, we generated a set of structural features for quantifying the 3D shape of the ONH. These statistically independently features had significant association with and predictive power for HCDR, a clinically important measurement used to diagnose and monitor glaucoma. Intriguing associations of ONH phenotype features were also found with ethnicity, age and gender. Future work will explore the power of applying these features to detect and track glaucoma.

 
 
A: A stereo fundus pair cropped around the ONH. B: The disparity map of the stereo pair. C: A 3D rendering of the ONH structure based on the disparity map.
 
A: A stereo fundus pair cropped around the ONH. B: The disparity map of the stereo pair. C: A 3D rendering of the ONH structure based on the disparity map.
 
 
A: The top five computational 3D ONH structural features derived from PCA. The features are shown in decreasing order of explained variance in ONH structure, from left to right. B: The relationship between the third 3D ONH structural feature and HCDR measurements for each subject. This feature was significantly (p<1e-16) associated with HCDR.
 
A: The top five computational 3D ONH structural features derived from PCA. The features are shown in decreasing order of explained variance in ONH structure, from left to right. B: The relationship between the third 3D ONH structural feature and HCDR measurements for each subject. This feature was significantly (p<1e-16) associated with HCDR.
 
Keywords: 629 optic nerve • 549 image processing • 473 computational modeling  
×
×

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.

×