Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world.There is a need for comprehensive and automated method of diabetic retinopathy screening.Time is lost between patients getting their eyes scanned (shown below), having their images analyzed by doctors, and scheduling a follow-up appointment. By processing images in real-time, EyeNet would allow people to seek & schedule treatment the same day. A neural network models is developed fot this task. The training data is comprised of 35,126 images, which are augmented during preprocessing.Techniques like resizing, rotations and mirroring were used during data preprocessing. With photos of eyes as input, the goal of this model is to identify retinopathy, ideally resulting in realistic clinical potential.The EyeNet classifier model has shown accuracy of 80% in training and testing process.
Input variables : Images of Eyes
Output Variables : Retinopathy Classification
Visit Model : github.com
Additional links : pubmed.ncbi.nlm.nih.gov
| Model Category | : | Public |
| Date Published | : | November, 2017 |
| Healthcare Domain | : |
Medical Technology
Provider |
| Code | : | github.com |
| Health Risk Management |
| Disease Detection |