Data Set:

Corneal Nerve Images


Automatic Nerve Tracing

3D Reconstruction of the Cornea

Automatic Endothelial Cell Count

Identification of Endothelial Cells

Automatic Tracing of the Corneal Nerves

F. Scarpa, E. Grisan, A. Ruggeri. Automatic recognition of corneal nerve structures in images from confocal microscopy. Invest Ophthalmol Vis Sci 49(11): 4801-7, Nov 2008.

The recognition of nerve structures in the cornea appears to be an important clinical issue, e.g. to investigate about damages from surgical interventions (LASIK/PRK) or severity of diabetic neuropathy. We addressed the problem of recognizing and tracing corneal nerves in confocal microscopy images. We implemented a prototype of the algorithm in the Matlab language: the purpose is the completely automatic tracing of the nerves. Image luminosity and contrast are normalized and the nerve tracking procedure is run. After nerve segments are recognized, a post-processing procedure removes false recognitions and links sparse segments.
An evaluation was performed on a data set containing 90 images. The percent of tracked nerves (with respect to manual tracing) was on average 80%; the rate of false positive recognitions (with respect to total tracing) was on average 8%.

In the following figures you can see an image of the nerve structures in the cornea and the nerves traced by our algorithm (green segments).


return to top