Researchers chart a course for AI-aided diagnosis of degenerative eye conditions

August 1, 2018 by Paulette Campbell, Johns Hopkins University
Artificial intelligence could improve how doctors identify and diagnose eye conditions such as age-related macular degeneration. Credit: Pixabay / The Light

A team of researchers from Johns Hopkins is leading the way in understanding how the advent of electronic medical records with large image databases and advances in artificial intelligence with deep learning can offer medical professionals new opportunities to dramatically improve disease diagnostics.

Researchers from the Johns Hopkins Applied Physics Laboratory and collaborators at the Johns Hopkins School of Medicine have developed image analysis and machine learning tools to detect , or AMD, a condition that causes lesions on the part of the eye called the retina. When not detected early, the vision loss caused by the lesions is often irreversible. It is the leading cause of blindness in individuals over the age of 50.

The APL team partnered with researchers at the Johns Hopkins Wilmer Eye Institute on ways to automate AMD diagnosis, discovering that machine diagnostics using can match the performance of human ophthalmologists. The findings are published in JAMA Ophthalmology.

"We've been able to show the feasibility of automated fine-grained classification of AMD severity that only highly trained ophthalmologists can achieve," said APL's Philippe Burlina, a co-principal investigator for the project. "These techniques have the potential to provide individuals with automated grading of images to identify AMD or monitor those individuals with earlier stages of AMD for the onset of the more advanced stages when prompt treatment may be indicated to reduce the risk of blindness."

Images show the progression of age-related macular degeneration: (from left) disease-free, early stage AMD, intermediate AMD, and advanced stage AMD. Credit: Applied Physics Laboratory

The team has also expanded its inquiry to characterize layers of the retina during , or OCT, a noninvasive imaging technique that provides high-resolution, cross-sectional images of the retina, retinal nerve fiber layer, and optic nerve head. Such techniques can be used to diagnose other such as diabetic retinopathy and have the potential to help characterize vascular and neurodegenerative pathologies.

"We were able to show that machines can do as well as humans for diagnosing AMD," Burlina said. "So now we have started looking at other retinal diseases and how to combine images with other sources of information—demographics, lifestyle factors such as smoking, and sunlight exposure—to automatically perform prognosis and predict the probability for five-year risk of developing the advanced form of the disease. The end goal is to help clinicians and guide treatment."

This year, the team expanded its collaboration to include scientists from the Singapore National Eye Center and tested its algorithms on groups of individuals from Malaysia, India, and China. In a review for Nature Medicine, the team examines the potential of AI applied to retinal image diagnostics and discusses requirements and future work needed to allow translation and deployment of these techniques for clinical and point-of-care scenarios.

Burlina said the researchers will also work with hospitals in Thailand, Brazil, and France to explore how algorithms trained on a database of specific ethnicities, demographics, and imaging-capture scenarios can be adapted for different ethnicities and conditions.

Explore further: New laser scanners shed light on eye disease before vision loss occurs

More information: Philippe M. Burlina et al. Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks, JAMA Ophthalmology (2017). DOI: 10.1001/jamaophthalmol.2017.3782

Related Stories

New laser scanners shed light on eye disease before vision loss occurs

December 22, 2017
SFU engineering science professor Marinko Sarunic has developed a high resolution retinal imaging scanner that will one day revolutionize eye care, helping ophthalmologists diagnose eye diseases before vision loss occurs.

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

March 13, 2018
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. ...

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 ...

Fighting diabetic blindness: Researchers develop new target to study potential treatments

April 25, 2018
Diabetic retinopathy is a retinal microvascular disease that often causes blindness in adults who have had diabetes mellitus for 10 years or more. Estimates are that 600 million people will have some sort of diabetic retinopathy ...

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.

Recommended for you

Researchers report vision-based neurotransmitter events for the first time

November 27, 2018
How does vision work, and what happens in the brain during the process? As simple as this question may sound, it has yet to be scientifically clarified. Dr. Valentin Riedl of the Technical University of Munich (TUM) and his ...

Minimally invasive retinal detachment has better outcomes, clinical trial findings

November 26, 2018
A minimally invasive treatment for retinal detachment gives patients sharper vision, less distortion and reduced side-effects, according to the findings of a randomized controlled trial performed at St. Michael's Hospital ...

Scientists combine technologies to view the retina in unprecedented detail

November 14, 2018
By combining two imaging modalities—adaptive optics and angiography—investigators at the National Eye Institute (NEI) can see live neurons, epithelial cells, and blood vessels deep in the eye's light-sensing retina. Resolving ...

Eyepatch with dissolvable needles used to treat eye disease

November 12, 2018
A team of researchers affiliated with several institutions in Singapore has developed an eyepatch with dissolvable needles for use in treating eye diseases. In their paper published in the journal Nature Communications, the ...

Calcifications in the eye increase risk for progression to advanced AMD by more than six times

November 8, 2018
Calcified nodules in the retina are associated with progression to late stages of age-related macular degeneration (AMD). Experts from Queen's University Belfast, working in partnership with the University of Alabama of Birmingham ...

Traditional glaucoma test can miss severity of disease

November 8, 2018
The most common tests for glaucoma can underestimate the severity of the condition by not detecting the presence of central vision loss, according to a new Columbia University study.

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.