Diabetic Retinopathy
From CATER
| Diabetic retinopathy is the most common diabetic eye disease and a leading cause of blindness in American adults. It is caused by changes in the blood vessels of the retina.
In some people with diabetic retinopathy, blood vessels may swell and leak fluid. In other people, abnormal new blood vessels grow on the surface of the retina. The retina is the light-sensitive tissue at the back of the eye. A healthy retina is necessary for good vision. If you have diabetic retinopathy, at first you may not notice changes to your vision. But over time, diabetic retinopathy can get worse and cause vision loss. Diabetic retinopathy usually affects both eyes. |
A prototype system is being developed to automatically identify eye images with diabetic retinopathy. The system uses convolutional neural networks to classify images. The initial system uses a limited training and testing set with minimal number of label categories. The aim of this project is to enhance this system by developing pre-processing methods to improve image quality applying different network configurations to identify best possible learning architecture applying new methods to improve performance apply tests using new training and testing data or, anything you think that might improve performance.
The protoype system is being developed using Lush programming language. Lush provides several unique advantages over classical compiled and interpreted languages and contains a very large machine learning library.
People
Koray Kavukcuoglu
Nathan Silberman
Alex Rubinsteyn
Kristy Ahlrich
Yann LeCun
Rob Fergus
Lakshminaryanan Subramanian
Publications
- Automated Detection of Nonproliferative Diabetic Retinopathy. K. Ahrlich1, L. Subramanian, K. Kavukcuoglu, A. Rubinsteyn and J. Young. ARVO 2008
