May 2005
Volume 46, Issue 13
Free
ARVO Annual Meeting Abstract  |   May 2005
Automated Detection of Optic Disc Margin in HRT II– Images
Author Affiliations & Notes
  • V. Derhartunian
    Department of Ophthalmology,
    University Erlangen–Nuremberg, Erlangen, Germany
  • R. Chrastek
    Chair for Pattern Recognition,
    University Erlangen–Nuremberg, Erlangen, Germany
  • A. Viestenz
    Department of Ophthalmology,
    University Erlangen–Nuremberg, Erlangen, Germany
  • C. Mardin
    Department of Ophthalmology,
    University Erlangen–Nuremberg, Erlangen, Germany
  • G. Michelson
    Department of Ophthalmology,
    University Erlangen–Nuremberg, Erlangen, Germany
  • Footnotes
    Commercial Relationships  V. Derhartunian, None; R. Chrastek, None; A. Viestenz, None; C. Mardin, None; G. Michelson, None.
  • Footnotes
    Support  SFB 539/A4
Investigative Ophthalmology & Visual Science May 2005, Vol.46, 2509. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      V. Derhartunian, R. Chrastek, A. Viestenz, C. Mardin, G. Michelson; Automated Detection of Optic Disc Margin in HRT II– Images . Invest. Ophthalmol. Vis. Sci. 2005;46(13):2509.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Abstract:
 

To evaluate HRT II– parameters calculated upon a manual and automated contour line drawing in HRT II–reflectivity images.

 

108 optic disc images were acquired with the scanning laser tomography (HRT II, Heidelberg Engineering). Four experienced HRT II specialists and an automated algorithm defined in each image the contour line of the optic disc margin. The automated algorithm was based on a pattern recognition algorithm performing morphological operations and detection of anatomical structures (Chrastek et al., Methods Inf. Med. 2004; 43: 336–42). All morphological optic disc parameters were calculated (HRT II, version 1.4.1.0). The mean of each HRT II–parameter defined by the 4 glaucoma experts served as control. Correlations between the manually and automatically found HRT II–parameters were calculated. Statistical analysis was performed by the paired T–Test (SPSS 11.0 version).

 

All major HRT II– parameters defined by glaucoma experts correlated significantly with the HRT II parameters found by the automated procedure. The table depicts the R– and p–values. The 3rd moment showed the strongest correlation.

 

 

An automated procedure to find the disc margin in HRT II– images gave similar morphological values as the mean of 4 experienced glaucoma specialists.

 

 
Keywords: imaging/image analysis: clinical • optic disc • imaging methods (CT, FA, ICG, MRI, OCT, RTA, SLO, ultrasound) 
×
×

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.

×