Saving sight: Using AI to diagnose diabetic eye disease

January 08, 2019

Researchers have used artificial intelligence to support the instant diagnosis of one of the top causes of blindness, diabetes-related eye disease, in its earliest stages.

Diabetic retinopathy is the leading cause of vision loss in adults* and its impact is growing worldwide, with 191 million people set to be affected by 2030**.

There are no early-stage symptoms and the disease may already be advanced by the time people start losing their sight. Early diagnosis and treatment can make a dramatic difference to how much vision a patient retains.

Now a team of Australian-Brazilian researchers led by RMIT University have developed an image-processing algorithm that can automatically detect one of the key signs of the disease, fluid on the retina, with an accuracy rate of 98%.

Lead investigator Professor Dinesh Kant Kumar, RMIT, said the method was instantaneous and cost-effective.

"We know that only half of those with diabetes have regular eye exams and one-third have never been checked," Kumar said.

"But the gold standard methods of diagnosing diabetic retinopathy are invasive or expensive, and often unavailable in remote or developing parts of the world.

"Our AI-driven approach delivers results that are just as accurate as clinical scans but relies on retinal images that can be generated with ordinary optometry equipment.

"Making it quicker and cheaper to detect this incurable disease could be life changing for the millions of people who are currently undiagnosed and risk losing their sight."

Fluorescein angiography and optical coherence tomography scans are currently the most accurate clinical methods for diagnosing diabetic retinopathy.

An alternative and cheaper method is analysing images of the retina that can be taken with relatively inexpensive equipment called fundus cameras, but the process is manual, time-consuming and less reliable.

To automate the analysis of fundus images, researchers in the Biosignals Laboratory in the School of Engineering at RMIT, together with collaborators in Brazil, used deep learning and artificial intelligence techniques.

The algorithm they developed can accurately and reliably spot the presence of fluid from damaged blood vessels, or exudate, inside the retina.

The researchers hope their method could eventually be used for widespread screening of at-risk populations.

"Undiagnosed diabetes is a massive health problem here and around the globe," Kumar said.

"For every single person in Australia who knows they have diabetes, another is living with diabetes but isn't diagnosed. In developing countries, the ratio is one diagnosed to four undiagnosed.

"This results in millions of people developing preventable and treatable complications from diabetes-related diseases.

"With further development, our technology has the potential to reduce that burden."

The researchers are in discussions with manufacturers of fundus cameras about potential collaborations to advance the technology.
-end-
The research - with lead author Parham Khojasteh and collaborators from Federal University of Sao Carlos, Federal Institute of Sao Paolo, University of Campinas and Sao Paolo State University - is published in Computers in Biology and Medicine (January 2019, Volume 104).

* Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss (DOI:10.1186/s40662-015-0026-2)

** Psychophysical Exams as Early Indicators of Diabetic Retinopathy (DOI:10.17925/EE.2014.10.01.61)

RMIT University

Related Diabetes Articles from Brightsurf:

New diabetes medication reduced heart event risk in those with diabetes and kidney disease
Sotagliflozin - a type of medication known as an SGLT2 inhibitor primarily prescribed for Type 2 diabetes - reduces the risk of adverse cardiovascular events for patients with diabetes and kidney disease.

Diabetes drug boosts survival in patients with type 2 diabetes and COVID-19 pneumonia
Sitagliptin, a drug to lower blood sugar in type 2 diabetes, also improves survival in diabetic patients hospitalized with COVID-19, suggests a multicenter observational study in Italy.

Making sense of diabetes
Throughout her 38-year nursing career, Laurel Despins has progressed from a bedside nurse to a clinical nurse specialist and has worked in medical, surgical and cardiac intensive care units.

Helping teens with type 1 diabetes improve diabetes control with MyDiaText
Adolescence is a difficult period of development, made more complex for those with Type 1 diabetes mellitus (T1DM).

Diabetes-in-a-dish model uncovers new insights into the cause of type 2 diabetes
Researchers have developed a novel 'disease-in-a-dish' model to study the basic molecular factors that lead to the development of type 2 diabetes, uncovering the potential existence of major signaling defects both inside and outside of the classical insulin signaling cascade, and providing new perspectives on the mechanisms behind insulin resistance in type 2 diabetes and possibly opportunities for the development of novel therapeutics for the disease.

Tele-diabetes to manage new-onset diabetes during COVID-19 pandemic
Two new case studies highlight the use of tele-diabetes to manage new-onset type 1 diabetes in an adult and an infant during the COVID-19 pandemic.

Genetic profile may predict type 2 diabetes risk among women with gestational diabetes
Women who go on to develop type 2 diabetes after having gestational, or pregnancy-related, diabetes are more likely to have particular genetic profiles, suggests an analysis by researchers at the National Institutes of Health and other institutions.

Maternal gestational diabetes linked to diabetes in children
Children and youth of mothers who had gestational diabetes during pregnancy are at increased risk of diabetes themselves, according to new research published in CMAJ (Canadian Medical Association Journal).

Two diabetes medications don't slow progression of type 2 diabetes in youth
In youth with impaired glucose tolerance or recent-onset type 2 diabetes, neither initial treatment with long-acting insulin followed by the drug metformin, nor metformin alone preserved the body's ability to make insulin, according to results published online June 25 in Diabetes Care.

People with diabetes visit the dentist less frequently despite link between diabetes, oral health
Adults with diabetes are less likely to visit the dentist than people with prediabetes or without diabetes, finds a new study led by researchers at NYU Rory Meyers College of Nursing and East Carolina University's Brody School of Medicine.

Read More: Diabetes News and Diabetes Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.