AI Decision Support Technology of Fundus Image in Diabetes Mellitus

This technology is a collaboration of the minds of the human brain and artificial intelligence through the expertise of doctors and AI analysis. It enhances the efficiency of helping non-ophthalmologist physicians conduct the detection of subtle lesions in fundus images, and eliminates the inconvenience of referrals to ophthalmologists. The technology therefore increases the early detection rate for potential patients and reduces the cost of healthcare and social care.

● Labeling the lesion locations of Diabetic Retinopathy

This is currently the only AI detection technology in the world that can detect the main four lesions (Microaneurysms, Hemorrhages, Soft Exudates, Hard Exudates), clearly label the corresponding locations, and effectively assist doctors to interpret more effectively in accordance to the severity of condition.

● In accordance with the needs of the severity scales of Taiwan’s Diabetes Shared Care Network

This technology provides a classification model for the five severity scales of diabetic retinopathy (No DR, Mild NPDR, Moderate NPDR, Severe NPDR, PDR), and ensures suitable healthcare for patients with different severity levels. It also produces a binary classification model regarding the decision for referrals to ophthalmologists.

 Look for: 

Agents, medical device manufacturer, and healthcare information system service provider are welcome to have further discussion on cooperation.

InnoZone Booth No. A007