Nav: Home

Google's AI program: Building better algorithms for detecting eye disease

March 13, 2018

SAN FRANCISCO - March 13, 2017 - The ability of artificial intelligence (AI) to help screen patients for a common diabetic eye disease gains momentum with a new study published online today in Ophthalmology, the journal of the American Academy of Ophthalmology. Lily Peng, M.D., Ph.D., and her colleagues at Google AI research group, show that they could improve their disease detecting software by using a small subset of images adjudicated by ophthalmologists who specialize in retinal diseases. The specialists' input was then used to improve their computer's performance so that it was roughly equal to that of individual retinal specialists.

More than 29 million Americans have diabetes, and are at risk for diabetic retinopathy, a potentially blinding eye disease. People often don't notice changes in their vision in the disease's early stages. But as it progresses, diabetic retinopathy usually causes vision loss that in many cases cannot be reversed. That's why it's so important that people with diabetes have yearly screenings.

In earlier research, Dr. Peng and her team used neural networks--complex mathematical systems for identifying patterns in data--to recognize diabetic retinopathy. They fed thousands of retinal scans into these neural networks to teach them to "see" tiny hemorrhages and other lesions that are early warning signs of retinopathy. Dr. Peng showed the software worked roughly as well as human experts.

But Dr. Peng is interested in developing a system that would be good enough for her grandmother. So, to improve the accuracy of the software, she included the input of retina specialists, ophthalmologists who specialize in diseases of the retina.

"For my grandma, I would love to have a panel of subspecialists who actually treat the disease, to sit and debate her case, giving their opinion," Dr. Peng said. "But that is really expensive and it's hard to do. So how do you build an algorithm that gets close to this?"

To tease out how this could be done, Dr. Peng compared the performance of the original algorithm with manual image grading by either a majority decision of three general ophthalmologists, or a consensus grading by three retinal specialists.

The grading of diabetic retinopathy can be a complex process that requires the identification and quantification of fine features such as small aneurysms and hemorrhages. As a result, there can be a fair amount of variability among physicians examining images, looking for disease.

The retina specialists graded the images separately, then worked together to resolve any disagreements. Their review and subsequent consensus diagnosis offered considerable insight into the grading process, helping to correct errors such as artifacts caused by dust spots, distinguishing between different types of hemorrhages, and creating more precise definitions for "gray areas" that make it difficult to make a definitive diagnosis. At the end of the process, the retina specialists indicated that the precision used in the decision process was above that typically used in everyday clinical practice.

Using these specialist-graded images, Dr. Peng could then fine-tune the software, which improved their model's performance and improved detection of disease.

"We believe this work provides a basis for further research and raises the bar for reference standards in the field of applying machine learning to medicine," Dr. Peng said.
-end-
About the American Academy of Ophthalmology

The American Academy of Ophthalmology is the world's largest association of eye physicians and surgeons. A global community of 32,000 medical doctors, we protect sight and empower lives by setting the standards for ophthalmic education and advocating for our patients and the public. We innovate to advance our profession and to ensure the delivery of the highest-quality eye care. Our EyeSmart® program provides the public with the most trusted information about eye health. For more information, visit aao.org.

About Ophthalmology

Ophthalmology, the official journal of the American Academy of Ophthalmology, publishes original, peer-reviewed, clinically-applicable research. Topics include the results of clinical trials, new diagnostic and surgical techniques, treatment methods, technology assessments, translational science reviews and editorials. For more information, visit http://www.aaojournal.org.

American Academy of Ophthalmology

Related Retinopathy Articles:

Loss of pericytes deteriorates retinal environment
This new study revealed how the loss of pericytes aggravates the retinal environment and function in a mouse experimental model.
Implementing large-scale teleretinal diabetic retinopathy screening program
Can a large-scale, primary care-based teleretinal diabetic retinopathy screening (TDRS) program reduce wait times for screening and improve the timeliness of care in the Los Angeles County Department of Health Services, the largest publicly operated county safety net health care system in the United States?
Many youths with diabetes not being screened as recommended for diabetic retinopathy
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.
Scientists find therapeutic target for diabetes-related blindness
Specific cells in the retina trigger inflammation and vision impairment associated with diabetes, according to new research out of Case Western Reserve University School of Medicine.
Is preeclampsia a risk or a protective factor in retinopathy of prematurity?
Mary Elizabeth Hartnett, M.D., and colleagues at the John A.
Dual-drug combination shows promise against diabetic eye disease in animal model
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.
Retinopathy of prematurity: New developments are cause for hope
A mini-symposium published in the Journal of the American Association for Pediatric Ophthalmology and Strabismus (AAPOS) provides important insights into new techniques and treatments that show promise for eliminating retinopathy of prematurity (ROP) throughout the world.
Powerful anti-inflammatory molecule may block vision loss in diabetic retinopathy
A more powerful version of an anti-inflammatory molecule already circulating in our blood may help protect our vision in the face of diabetes.
Study examines use of deep machine learning for detection of diabetic retinopathy
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 online by JAMA.
Retinopathy: Senescence-associated secretory phenotype contributes to pathological angiogenesis
A study sheds new understanding on the mechanisms of the diabetic retinopathy -- which is the most prominent complication of diabetes and the leading cause of blindness in working age individuals -- as it uncovered a program of accelerated aging of the neurons, blood vessels and immune cells of the retina in areas where blood vessels had been damaged.

Related Retinopathy Reading:

Focus on Music 2: Exploring the Musicality of Children and Young People with Retinopathy of Prematurity (Issues in Practice)
by Adam Ockelford (Author), Christina Matawa (Author)

Diabetic Retinopathy: From Diagnosis to Treatment
by David S. Boyer MD (Author), Homayoun Tabandeh MD (Author)

Retinopathy of Prematurity: Current Diagnosis and Management
by Andrés Kychenthal B. (Editor), Paola Dorta S. (Editor)

Current Management of Diabetic Retinopathy
by Caroline R. Baumal MD (Author), Jay S. Duker MD (Author)

Diabetic Eye Disease - Don't Go Blind From Diabetes: An easy to understand guide to keeping your vision for people with diabetes
by David Khorram MD (Author)

A Practical Manual of Diabetic Retinopathy Management (Practical Manual of Series)
by Peter H. Scanlon (Editor), Ahmed Sallam (Editor), Peter van Wijngaarden (Editor)

Diabetic Retinopathy
by Bruno, M.D. Lumbroso (Author), Marco, M.D. Rispoli (Author), Maria Cristina, M.D., Ph.D. Savastano (Author)

Bilberry & Lutein: The Vision Enhancers! Protect Against Cataracts, MacUlar Degeneration, Glaucoma, Retinopathy & Other Health Problems (Health lear (Health Learning Handbook)
by Beth M. Ley (Author)

Goodbye Floaters: How to Beat Floaters and Diabetic Retinopathy Naturally

Diabetic Retinopathy for the Comprehensive Ophthalmologist, Second Edition
by Jonathan Walker, Robert B. Chambers Raj K. Maturi (Author)

Best Science Podcasts 2018

We have hand picked the best science podcasts for 2018. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Dying Well
Is there a way to talk about death candidly, without fear ... and even with humor? How can we best prepare for it with those we love? This hour, TED speakers explore the beauty of life ... and death. Guests include lawyer Jason Rosenthal, humorist Emily Levine, banker and travel blogger Michelle Knox, mortician Caitlin Doughty, and entrepreneur Lux Narayan.
Now Playing: Science for the People

#492 Flint Water Crisis
This week we dig into the Flint water crisis: what happened, how it got so bad, what turned the tide, what's still left to do, and the mix of science, politics, and activism that are still needed to finish pulling Flint out of the crisis. We spend the hour with Dr Mona Hanna-Attisha, a physician, scientist, activist, the founder and director of the Pediatric Public Health Initiative, and author of the book "What the Eyes Don't See: A Story of Crisis, Resistance, and Hope in an American City".