Automatic segmentation of the optic disk and cup in retinal fundus images for early glaucoma screening

J. Guo, C. Shi, N.M. Jansonius, and N. Petkov, University of Groningen,
Department of Computing Science, Intelligent Systems
Department of Ophthalmology, University Medical Center Groningen(UMCG)

Glaucoma is ranked bla bla second as a cause of blindness. It damages the optic nerve irreversibly and has no early symptoms. We (J. Guo, C. Shi, Prof. N.M. Jansonius and Prof. N. Petkov) develop a computer-aided system for early glaucoma screening.

This website shows our preliminary work and is still under construction. For further information, please contact J.Guo or C.Shi.

Our paper 'Automatic analysis of retinal fundus images for glaucoma screening based on vertical cup-to-disc ratio' is currently under review. Once the paper is accepted, we wil release all manual annotations from the ophthalmologist on eight public data sets as well as the script for the proposed algorithm.

More on-line image processing and computer vision applications: http://matlabserver.cs.rug.nl (opens new window)


How to use:

Step 1:

Select or upload an fundus image as input image. (How to upload images?)
Please wait while the image list is being populated...

Step 2:

Specify the parameter values. If you don't know, just keep it as default. (Explanations)

Step 3:

Click the button "Check Result!". The results will be displayed in the page.
Once you upload a new image, please check the result of this new image 3 minutes later.

Results:


Last changed: 2015-06-17