DRISTI

Diabetic Retinopathy (DR) is the damage caused to retina by complications of diabetes which can eventually lead to blindness. Proper and systematic screening for DR have been shown to be effective in prevention and management of DR.

However, in developing countries like India there is an enormous disparity in ratio between trained ophthalmologists to patients which makes screening programs less effective. Computer Aided Detection can play a pivotal role in addressing prevention of avoidable blindness by increasing screening efficiency of DR.

DRISTI, using quantitative image analysis algorithms, analyses retinal fundus images for DR lesions and directs DR suspicious cases for detailed ophthalmologist's review. Most of the DR negative cases are screened out without an ophthalmologist's intervention.

Use Cases

• Population Screening Scenarios
• Ophthalmologic/Diabetic Clinics
• Telemedicine and other Remote Diagnostic Scenarios.
• Quality Check in Tertiary/ Specialty Hospitals.
• Training for Optometrists.

Salient Features

• Automatically classifies retina as either Non-DR or suspicious of DR.
• Only cases having suspicion of DR need an ophthalmologist's review.
• Patient prioritization based on automated severity scoring.
• Increase screening efficiency by up to 78%.
• Real-time image quality notification for re-imaging.
• Detects retinal pathologies like micro-aneurisms, haemorrhages, exudates and cotton-wool-spots.
• Intuitive GUI for automated analysis of image level, patient level and patient batch.
• Systematic storage of patient details and analysis results.