Friedrich-Alexander-Universität Erlangen
Lehrstuhl für Mustererkennung
Martensstraße 3
91058 Erlangen

Automated Glaucoma Classification using OCT Images

Automated Glaucoma Classification Using OCT Images

The glaucoma disease is the loss of supporting tissue and nerve fibers in the papilla area. OCT is capable to image this region in depth, and thus give an in-vivo impression of the retinal nerve fiber layer thickness. Using thickness profiles generated out of our Automated Retinal Layer Segmentation we try to automatically discriminate between normals and glaucoma patients. The goal is to develop an OCT-based glaucoma indicator comparable to the GPS included in the HRT imaging device and the Glaucoma Risk Index (GRI) for color fundus photographs invented at our lab.

</br>Example NFL thickness profile on a 3.4mm circular scan around the papilla of a glaucoma patient. The red lines are manual corrections to the automated segmentations.



Preliminary work on this project is published in the following form:

     

  • Markus A. Mayer, Joachim Hornegger, Christian Y. Mardin, Friedrich E. Kruse, Ralf. P. Tornow: "Automated Glaucoma Classification Using Nerve Fiber Layer Segmentations On Circular Spectral Domain OCT B-Scans", The Association for Research in Vision and Ophthalmology, Inc. (ARVO) (Annual Meeting) in Fort Lauderdale, Florida, USA, 2009. Poster Download

  •