Glaucoma is one of the most common causes of blindness with a mean prevalence of 2.4% for all ages and of 4.7% for ages above 75 years (Klein et al. 1992). The disease is characterized by the progressive degeneration of optic nerve fibers and astrocytes showing a distinct pathogenetic pattern of the optic nerve head.

The main goal of my research is the development of techniques to statistically model the optic nerve head appearance that can be used for an automated glaucoma detection.

Current projects:

• Automated glaucoma risk index (GRI):
  This novel automated glaucoma detection system operates on digital color fundus images and transfers the idea of Eigenfaces to the domain of ophthalmology.
  After a disease specific preprocessing and appearance-based feature reduction, a two-stage classification system provides the novel Glaucoma Risk Index (GRI).
  The system shows a competitive area under ROC curve of 88 % compared to established glaucoma indices without utilizing geometeric parameters of the ONH.

• Statistical deformation model of the optic nerve head
  Quantitative glaucoma indices commonly rely on geometric parameters of the optic nerve head (ONH) such as disk area or cup volume. However, the ONH is too complex structure to be accurately analyzed such a sparse sampling of ONH.
  We provide dense descriptions of the ONH variability extracting the main modes of glaucomatous variations