Menu
​IBM deep learning improves detection of diabetic eye disease

​IBM deep learning improves detection of diabetic eye disease

New method could potentially provide clinicians with a better view of disease progression

IBM is using its deep learning and visual analytics technology to improve the early detection of diabetic retinopathy (DR).

Results from new research published by IBM – which classify the degree of severity of the disease in an eye image – exceed currently published studies for severity classification using deep learning and pathology insights.

A new method created by the IBM team achieved an accuracy score of 86 per cent in classifying the severity of the disease across five levels recognised on the international clinical DR scale.

IBM believes the research could potentially provide doctors and clinicians with a better view of disease progression so they can determine the best treatment.

Diabetic retinopathy is the world’s leading cause of blindness and affects one in three of the 422 million people who suffer from diabetes globally. If untreated, it can lead to blindness but early detection and treatment can reduce the risk of blindness of 95 per cent.

Using more than 35,000 eye images across via EyePACS, the IBM technology was trained to identify lesions such as micro-aneurysms, hemorrhages and exudates to indicate damage of the retina’s blood vessels and assess both the presence and severity of the disease.

This method of detecting the disease combines deep learning techniques and convolutional neural networks with dictionary-based learning to incorporate DR-specific pathologies.

Over time, IBM said its research scientists will continue to advance the system to increase its understanding of the diabetic retinopathy and the pathologies manifested in the retina area from the disease.

“The alarming projections of the number of patients with diabetic retinopathy have major implications for the health system,” said Dr Peter van Wijngaarden, principal investigator at the Centre for Eye Research Australia, Department of Opthalmology at the University of Melbourne.

“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.”

Currently, diabetic retinopathy is diagnosed through regular screening of diabetes patients where a clinician examines specialised fundus photography of the retina to identify lesions. Interpreting these images requires specialist training and is often a manual, time-intensive and subjective process to rate them for disease presence and severity.

“Recent advancements in deep learning and image analytics are showing significant promise in the potential to help solve some of the greatest health challenges we face today,” said Dr Joanna Batstone, vice president and lab director of IBM Research Australia.

“Automated and highly accurate DR screening methods have the potential to help doctors screen far more patients than currently possible.”

Follow CIO Australia on Twitter and Like us on Facebook… Twitter: @CIO_Australia, Facebook: CIO Australia, or take part in the CIO conversation on LinkedIn: CIO Australia

Follow Byron Connolly on Twitter: @ByronConnolly

Join the CIO Australia group on LinkedIn. The group is open to CIOs, IT Directors, COOs, CTOs and senior IT managers.

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Tags diabetesuniversity of melbournedeep learningpathology insightsEyePACSCentre for Eye Research Australiadiabetic retinopathyblindnessDr Peter van WinjngaardenDr Joanna Batstone

More about FacebookIBMTwitterUniversity of Melbourne

Show Comments
[]