eye
Artificial Intelligence Getting Smarter! Innovations from the Vision Field
Posted on by Michael F. Chiang, M.D., National Eye Institute
One of many health risks premature infants face is retinopathy of prematurity (ROP), a leading cause of childhood blindness worldwide. ROP causes abnormal blood vessel growth in the light-sensing eye tissue called the retina. Left untreated, ROP can lead to lead to scarring, retinal detachment, and blindness. It’s the disease that caused singer and songwriter Stevie Wonder to lose his vision.
Now, effective treatments are available—if the disease is diagnosed early and accurately. Advancements in neonatal care have led to the survival of extremely premature infants, who are at highest risk for severe ROP. Despite major advancements in diagnosis and treatment, tragically, about 600 infants in the U.S. still go blind each year from ROP. This disease is difficult to diagnose and manage, even for the most experienced ophthalmologists. And the challenges are much worse in remote corners of the world that have limited access to ophthalmic and neonatal care.
Artificial intelligence (AI) is helping bridge these gaps. Prior to my tenure as National Eye Institute (NEI) director, I helped develop a system called i-ROP Deep Learning (i-ROP DL), which automates the identification of ROP. In essence, we trained a computer to identify subtle abnormalities in retinal blood vessels from thousands of images of premature infant retinas. Strikingly, the i-ROP DL artificial intelligence system outperformed even international ROP experts [1]. This has enormous potential to improve the quality and delivery of eye care to premature infants worldwide.
Of course, the promise of medical artificial intelligence extends far beyond ROP. In 2018, the FDA approved the first autonomous AI-based diagnostic tool in any field of medicine [2]. Called IDx-DR, the system streamlines screening for diabetic retinopathy (DR), and its results require no interpretation by a doctor. DR occurs when blood vessels in the retina grow irregularly, bleed, and potentially cause blindness. About 34 million people in the U.S. have diabetes, and each is at risk for DR.
As with ROP, early diagnosis and intervention is crucial to preventing vision loss to DR. The American Diabetes Association recommends people with diabetes see an eye care provider annually to have their retinas examined for signs of DR. Yet fewer than 50 percent of Americans with diabetes receive these annual eye exams.
The IDx-DR system was conceived by Michael Abramoff, an ophthalmologist and AI expert at the University of Iowa, Iowa City. With NEI funding, Abramoff used deep learning to design a system for use in a primary-care medical setting. A technician with minimal ophthalmology training can use the IDx-DR system to scan a patient’s retinas and get results indicating whether a patient should be sent to an eye specialist for follow-up evaluation or to return for another scan in 12 months.
Many other methodological innovations in AI have occurred in ophthalmology. That’s because imaging is so crucial to disease diagnosis and clinical outcome data are so readily available. As a result, AI-based diagnostic systems are in development for many other eye diseases, including cataract, age-related macular degeneration (AMD), and glaucoma.
Rapid advances in AI are occurring in other medical fields, such as radiology, cardiology, and dermatology. But disease diagnosis is just one of many applications for AI. Neurobiologists are using AI to answer questions about retinal and brain circuitry, disease modeling, microsurgical devices, and drug discovery.
If it sounds too good to be true, it may be. There’s a lot of work that remains to be done. Significant challenges to AI utilization in science and medicine persist. For example, researchers from the University of Washington, Seattle, last year tested seven AI-based screening algorithms that were designed to detect DR. They found under real-world conditions that only one outperformed human screeners [3]. A key problem is these AI algorithms need to be trained with more diverse images and data, including a wider range of races, ethnicities, and populations—as well as different types of cameras.
How do we address these gaps in knowledge? We’ll need larger datasets, a collaborative culture of sharing data and software libraries, broader validation studies, and algorithms to address health inequities and to avoid bias. The NIH Common Fund’s Bridge to Artificial Intelligence (Bridge2AI) project and NIH’s Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) Program project will be major steps toward addressing those gaps.
So, yes—AI is getting smarter. But harnessing its full power will rely on scientists and clinicians getting smarter, too.
References:
[1] Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. Brown JM, Campbell JP, Beers A, Chang K, Ostmo S, Chan RVP, Dy J, Erdogmus D, Ioannidis S, Kalpathy-Cramer J, Chiang MF; Imaging and Informatics in Retinopathy of Prematurity (i-ROP) Research Consortium. JAMA Ophthalmol. 2018 Jul 1;136(7):803-810.
[2] FDA permits marketing of artificial intelligence-based device to detect certain diabetes-related eye problems. Food and Drug Administration. April 11, 2018.
[3] Multicenter, head-to-head, real-world validation study of seven automated artificial intelligence diabetic retinopathy screening systems. Lee AY, Yanagihara RT, Lee CS, Blazes M, Jung HC, Chee YE, Gencarella MD, Gee H, Maa AY, Cockerham GC, Lynch M, Boyko EJ. Diabetes Care. 2021 May;44(5):1168-1175.
Links:
Retinopathy of Prematurity (National Eye Institute/NIH)
Diabetic Eye Disease (NEI)
Michael Abramoff (University of Iowa, Iowa City)
Bridge to Artificial Intelligence (Common Fund/NIH)
[Note: Acting NIH Director Lawrence Tabak has asked the heads of NIH’s institutes and centers to contribute occasional guest posts to the blog as a way to highlight some of the cool science that they support and conduct. This is the second in the series of NIH institute and center guest posts that will run until a new permanent NIH director is in place.]
Finding Better Ways to Image the Retina
Posted on by Dr. Francis Collins
Every day, all around the world, eye care professionals are busy performing dilated eye exams. By looking through a patient’s widened pupil, they can view the retina—the postage stamp-sized tissue lining the back of the inner eye—and look for irregularities that may signal the development of vision loss.
The great news is that, thanks to research, retinal imaging just keeps getting better and better. The images above, which show the same cells viewed with two different microscopic techniques, provide good examples of how tweaking existing approaches can significantly improve our ability to visualize the retina’s two types of light-sensitive neurons: rod and cone cells.
Specifically, these images show an area of the outer retina, which is the part of the tissue that’s observed during a dilated eye exam. Thanks to colorization and other techniques, a viewer can readily distinguish between the light-sensing, color-detecting cone cells (orange) and the much smaller, lowlight-sensing rod cells (blue).
These high-res images come from Johnny Tam, a researcher with NIH’s National Eye Institute. Working with Alfredo Dubra, Stanford University, Palo Alto, CA, Tam and his team figured out how to limit light distortion of the rod cells. The key was illuminating the eye using less light, provided as a halo instead of the usual solid, circular beam.
But the researchers’ solution hit a temporary snag when the halo reflected from the rods and cones created another undesirable ring of light. To block it out, Tam’s team introduced a tiny pinhole, called a sub-Airy disk. Along with use of adaptive optics technology [1] to correct for other distortions of light, the scientists were excited to see such a clear view of individual rods and cones. They published their findings recently in the journal Optica [2]
The resolution produced using these techniques is so much improved (33 percent better than with current methods) that it’s even possible to visualize the tiny inner segments of both rods and cones. In the cones, for example, these inner segments help direct light coming into the eye to other, photosensitive parts that absorb single photons of light. The light is then converted into electrical signals that stream to the brain’s visual centers in the occipital cortex, which makes it possible for us to experience vision.
Tam and team are currently working with physician-scientists in the NIH Clinical Center to image the retinas of people with a variety of retinal diseases, including age-related macular degeneration (AMD), a leading cause of vision loss in older adults. These research studies are ongoing, but offer hopeful possibilities for safe and non-intrusive monitoring of individual rods and cones over time, as well as across disease types. That’s obviously good news for patients. Plus it will help scientists understand how a rod or cone cell stops working, as well as more precisely test the effects of gene therapy and other experimental treatments aimed at restoring vision.
References:
[1] Noninvasive imaging of the human rod photoreceptor mosaic using a confocal adaptive optics scanning ophthalmoscope. Dubra A, Sulai Y, Norris JL, Cooper RF, Dubis AM, Williams DR, Carroll J. Biomed Opt Express. 2011 Jul 1;2(7):1864-76.
[1] In-vivo sub-diffraction adaptive optics imaging of photoreceptors in the human eye with annular pupil illumination and sub-Airy detection. Rongwen L, Aguilera N, Liu T, Liu J, Giannini JP, Li J, Bower AJ, Dubra A, Tam J. Optica 2021 8, 333-343. https://doi.org/10.1364/OPTICA.414206
Links:
Get a Dilated Eye Exam (National Eye Institute/NIH)
How the Eyes Work (NEI)
Eye Health Data and Statistics (NEI)
Tam Lab (NEI)
Dubra Lab (Stanford University, Palo Alto, CA)
NIH Support: National Eye Institute
New Director for NEI
Posted on by Dr. Francis Collins
Singing A Fun Farewell Song
Posted on by Dr. Francis Collins
Best Wishes to Paul Sieving
Posted on by Dr. Francis Collins
Next Page
