Automatic diagnosis of diabetic retinopathy

Automatic diagnosis of diabetic retinopathy

Diabetic retinopathy, also known as diabetic eye disease (DED), is a medical condition in which damage occurs to the retina due to diabetes mellitus. It is a leading cause of blindness in developed countries. Diabetic retinopathy affects up to 80 percent of those who have had diabetes for 20 years or more. At least 90% of new cases could be reduced with proper treatment and monitoring of the eyes. The longer a person has diabetes, the higher his or her chances of developing diabetic retinopathy. Each year in the United States, diabetic retinopathy accounts for 12% of all new cases of blindness. It is also the leading cause of blindness in people aged 20 to 64.

Eye diseases are detected from an eye fundus study. This test is very important to detect pathologies such as choroid melanoma, diabetic retinopathy, glaucoma, age-related macular degeneration, toxoplasmosis or other diseases. An image with a high visual quality is very important for ophthalmologists, because it guarantees a more precise diagnosis. However, image quality can be affected for different reasons at the time of acquisition. Some of the common problems that images often suffer at the time of acquisition are low contrast, poor detail, insufficient lighting or artifact generation. To solve these problems, digital image processing techniques are used to enhance the visual quality of the images

The main objective of the project is the development of a diabetic retinopathy diagnostic tool using a neuroevolution approach. The secondary objectives of the project are:

  1. Generate a fundus image database.
  2. Design and implement an image processing algorithm to improve the interpretability of the image.
  3. Search the optimal hyperparameter values combination using a neuroevolution approach.
  4. Build a predictive model to diagnose patients with diabetic retinopathy.

For such purpose, we created a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay