Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     
News, Tech

Australian researchers achieve world-beating results

26/04/2017
Share:
IBM’s Melbourne-based research team has used cutting-edge deep learning and visual analytics technology to advance the early detection of Diabetic Retinopathy (DR).

The technology is able to classify the degree of severity of the disease in an eye image with 86% accuracy; a figure that exceeds all other currently published research efforts in the same field.

More than 35,000 images were used to train the technology to classify severity based on the five levels recognised on the international clinical DR scale – no DR, mild, moderate, severe, proliferative. It’s hoped that this ability to quickly and accurately identify both the presence and severity of diabetic eye disease will help doctors and clinicians have a better view of disease progression and determine treatment.

IBM research scientists expect to advance the system to increase its understanding of DR and the pathologies manifested in the retina from the disease.

Currently, it identifies lesions such as micro-aneurysms, haemorrhages and exudates to indicate damage of the retina’s blood vessels and assess both the presence and severity of the disease.

DR is one of the world’s leading causes of blindness – affecting one in three of the 422 million people with diabetes globally – despite the fact early detection can reduce the risk of blindness by 95%.

Principal investigator at Centre for Eye Research Australia, Dr Peter van Wijngaarden, described the projections for the number of patients with DR as “alarming” and predicted it would have major implications for the health system if left unchecked.

“The loss of vision from the condition can impose an enormous burden on the individual, including a loss of capacity to work and the need for intensive community support,” he said.

“To substantially reduce the number of people unnecessarily losing vision from diabetic eye disease, there is a real need for innovation to improve effective screening of those who are at risk to enable early sight-saving treatment.”

It’s anticipated emerging computer vision methods to identify and classify lesions in an image within 20 seconds could create new levels of efficiency. As a result, it could help clinicians screen a greater number of diabetic patients, and quickly refer those who need specialist care.

AFT Pharmaceuticals
advertisement





rectangle
advertisement
Editor's Suggestion
Hot Stories

rectangle
advertisement


OR
 

Subscribe for Insight in your Inbox

Get Insight with the latest in industry news, trends, new products, services and equipment!