Overview / Usage

Diabetic retinopathy is a common cause of blindness, and screening can identify the disease at an earlier, more treatable stage. However, rural individuals with diabetes may have limited access to needed eye care.

Currently, detecting DR is a time-consuming and manual process that requires a trained clinician to examine and evaluate digital color fundus photographs of the retina for the presence of lesions associated with the vascular abnormalities caused by the disease. While this approach is effective, its resource demands are high. By the time human readers submit their reviews, often a day or two later, the delayed results lead to lost follow up, miscommunication, and delayed treatment, especially in rural areas.

In remote areas, a retinal specialist is required to diagnose Diabetic Retinopathy which is usually not available. Eagle Eye demonstrates the feasibility of eye screening using a fundus camera and predicting diabetic retinopathy stage even in rural and remote areas where there is no or limited internet bandwidth and non-availability of a retinal specialist.

Methodology / Approach

Eagle Eye solves the need for a comprehensive and automated method of DR screening using image classification, pattern recognition, and machine learning.

With color fundus photography as input, the automated detection system results in models with realistic clinical potential, which is capable of rating the presence of diabetic retinopathy in each eye on a scale of 0 to 4, according to the following scale:

0 - No DR,
1 - Mild,
2 - Moderate,
3 - Severe,
4 - Proliferative DR

Technologies Used

Framework: TensorFlow
Tools: OpenVINO and Movidius NCS SDK
Libraries: Intel Optimized Python
Hardware: Movidius NCS