Researchers use deep learning to create an algorithm to detect a common diabetic eye disease

April 28, 2017, American Academy of Ophthalmology

Researchers from the Byers Eye Institute at Stanford University have found a way to use artificial intelligence to fight a complication of diabetes that affects the eyes. This advance has the potential to reduce the worldwide rate of vision loss due to diabetes.

In a study published online in Ophthalmology, the journal of the American Academy of Ophthalmology, the researchers describe how they used deep-learning methods to create an automated algorithm to detect . Diabetic retinopathy (DR) is a condition that damages the blood vessels at the back of the eye, potentially causing blindness.

"What we showed is that an -based grading algorithm can be used to identify, with high reliability, which patients should be referred to an ophthalmologist for further evaluation and treatment," said Theodore Leng, M.D., lead author. "If properly implemented on a worldwide basis, this algorithm has the potential to reduce the workload on doctors and increase the efficiency of limited healthcare resources. We hope that this technology will have the greatest impact in parts of the world where ophthalmologists are in short supply."

Another advantage is that the algorithm does not require any specialized, inaccessible, or costly computer equipment to grade images. It can be run on a common personal computer or smartphone with average processors.

Deep learning is on the rise in computer science and medicine because it can teach computers to do what our brains do naturally. What Dr. Leng and his colleagues did was to create an algorithm based on more than 75,000 images from a wide range of patients representing several ethnicities, and then used it to teach a to identify between healthy patients and those with any stage of disease, from mild to severe.

Dr. Leng's algorithm could identify all disease stages, from mild to severe, with an accuracy rate of 94 percent. It would be these patients that should see an ophthalmologist for further examination. An ophthalmologist is a physician who specializes in the medical and surgical treatment of eye diseases and conditions.

Diabetes affects more than 415 million people worldwide or 1 in every 11 adults.1 About 45 percent of are likely to have diabetic retinopathy at some point in their life; however, fewer than half of patients are aware of their condition. Early detection and treatment are integral to combating this worldwide epidemic of preventable .

Ophthalmologists typically diagnose the presence and severity of diabetic retinopathy by direct examination of the back of the eye and by evaluation of color photographs of the fundus, the interior lining of the eye. Given the large number of globally, this process is expensive and time-consuming. Also, previous studies have shown that detection is somewhat subjective, even among trained specialists. This is why an effective, automated algorithm could potentially reduce the rate of worldwide blindness.

Approval from the U.S. Food and Drug Administration is required before the can be used in on a broad basis. Dr. Leng and his team expect to conduct pilot trials in the near future.

Explore further: Study examines use of deep machine learning for detection of diabetic retinopathy

More information: Rishab Gargeya et al. Automated Identification of Diabetic Retinopathy Using Deep Learning, Ophthalmology (2017). DOI: 10.1016/j.ophtha.2017.02.008

Related Stories

Study examines use of deep machine learning for detection of diabetic retinopathy

November 29, 2016
In an evaluation of retinal photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy, according to a study published ...

Dual-drug combination shows promise against diabetic eye disease in animal model

February 15, 2017
A two-drug cocktail provided better protection against diabetes-related vision loss than a single drug during testing in rat models, a team of University of Florida Health and Dutch researchers has found.

Many youths with diabetes not being screened as recommended for diabetic retinopathy

March 23, 2017
Many youths with type 1 and 2 diabetes are not receiving eye examinations as recommended to monitor for diabetic retinopathy, according to a study published online by JAMA Ophthalmology.

Researchers identify new target for abnormal blood vessel growth in the eyes

April 11, 2017
A team led by Massachusetts Eye and Ear researchers has identified a novel therapeutic target for retinal neovascularization, or abnormal blood vessel growth in the retina, a hallmark of advanced diabetic eye disease (proliferative ...

Nearly six in ten diabetics skip eye exams, study finds

November 10, 2016
(HealthDay)—Almost two-thirds of people with diabetes don't get annual eye exams, despite having an increased risk for serious eye disease and vision loss, researchers say.

Diabetic retinopathy screening for children with type 1 diabetes should start later

September 1, 2015
A new study has found that the occurrence of advanced forms of a diabetic eye disease remains low among children living with diabetes, regardless of how long they have had the disease or their ability to keep blood sugar ...

Recommended for you

Satellite imaging techniques may help reduce preventable vision loss

May 11, 2018
By adapting pattern recognition techniques used to assess satellite images, scientists have devised a novel way to diagnose blinding eye diseases, such as age-related macular degeneration.

Ophthalmologists link immunotherapy with a serious eye condition

May 7, 2018
New immunotherapy treatments offer a remarkable chance for survival for patients with advanced melanoma and hard-to-treat cancers of the bladder, kidney and lung.

Burnout, depression can affect ophthalmology residents, study finds

May 4, 2018
A new study led by Brown University researchers finds that ophthalmology residents across the U.S. face a substantial burden of burnout and depression, which may affect not only the residents themselves but also the quality ...

AI better than most human experts at detecting cause of preemie blindness

May 3, 2018
An algorithm that uses artificial intelligence can automatically and more accurately diagnose a potentially devastating cause of childhood blindness than most expert physicians, a paper published in JAMA Ophthalmology suggests.

New diagnostic technique picks up the S in vision

May 1, 2018
A new technique that could help improve diagnosis of vision disorders has been successfully tested at the University of Bradford, UK.

A bit of dark chocolate might sweeten your vision

April 26, 2018
It may not replace prescription glasses, but a few bites of dark chocolate might offer a slight and temporary bump up in vision quality, new research suggests.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.