Skip to main content

ophthalmology

Artificial Intelligence Getting Smarter! Innovations from the Vision Field

Posted on by

AI. Photograph of retina

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.

Caption: Image of a neonatal retina prior to AI processing. Left: Image of a premature infant retina showing signs of severe ROP with large, twisted blood vessels; Right: Normal neonatal retina by comparison. Credit: Casey Eye Institute, Oregon Health and Science University, Portland, and National Eye Institute, NIH

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.

Caption: The IDx-DR is the first FDA-approved system for diagnostic screening of diabetic retinopathy. It’s designed to be used in a primary care setting. Results determine whether a patient needs immediate follow-up. Credit: Digital Diagnostics, Coralville, IA.

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)

NEI Research News

Michael Abramoff (University of Iowa, Iowa City)

Bridge to Artificial Intelligence (Common Fund/NIH)

Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) Program (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.]


Moving Closer to a Stem Cell-Based Treatment for AMD

Posted on by

In recent years, researchers have figured out how to take a person’s skin or blood cells and turn them into induced pluripotent stem cells (iPSCs) that offer tremendous potential for regenerative medicine. Still, it’s been a challenge to devise safe and effective ways to move this discovery from the lab into the clinic. That’s why I’m pleased to highlight progress toward using iPSC technology to treat a major cause of vision loss: age-related macular degeneration (AMD).

In the new work, researchers from NIH’s National Eye Institute developed iPSCs from blood-forming stem cells isolated from blood donated by people with advanced AMD [1]. Next, these iPSCs were exposed to a variety of growth factors and placed on supportive scaffold that encouraged them to develop into healthy retinal pigment epithelium (RPE) tissue, which nurtures the light-sensing cells in the eye’s retina. The researchers went on to show that their lab-grown RPE patch could be transplanted safely into animal models of AMD, preventing blindness in the animals.

This preclinical work will now serve as the foundation for a safety trial of iPSC-derived RPE transplants in 12 human volunteers who have already suffered vision loss due to the more common “dry” form of AMD, for which there is currently no approved treatment. If all goes well, the NIH-led trial may begin enrolling patients as soon as this year.

Risk factors for AMD include a combination of genetic and environmental factors, including age and smoking. Currently, more than 2 million Americans have vision-threatening AMD, with millions more having early signs of the disease [2].

AMD involves progressive damage to the macula, an area of the retina about the size of a pinhead, made up of millions of light-sensing cells that generate our sharp, central vision. Though the exact causes of AMD are unknown, RPE cells early on become inflamed and lose their ability to clear away debris from the retina. This leads to more inflammation and progressive cell death.

As RPE cells are lost during the “dry” phase of the disease, light-sensing cells in the macula also start to die and reduce central vision. In some people, abnormal, leaky blood vessels will form near the macula, called “wet” AMD, spilling fluid and blood under the retina and causing significant vision loss. “Wet” AMD has approved treatments. “Dry” AMD does not.

But, advances in iPSC technology have brought hope that it might one day be possible to shore up degenerating RPE in those with dry AMD, halting the death of light-sensing cells and vision loss. In fact, preliminary studies conducted in Japan explored ways to deliver replacement RPE to the retina [3]. Though progress was made, those studies highlighted the need for more reliable ways to produce replacement RPE from a patient’s own cells. The Japanese program also raised concerns that iPSCs derived from people with AMD might be prone to cancer-causing genomic changes.

With these challenges in mind, the NEI team led by Kapil Bharti and Ruchi Sharma have designed a more robust process to produce RPE tissue suitable for testing in people. As described in Science Translational Medicine, they’ve come up with a three-step process.

Rather than using fibroblast cells from skin as others had done, Bharti and Sharma’s team started with blood-forming stem cells from three AMD patients. They reprogrammed those cells into “banks” of iPSCs containing multiple different clones, carefully screening them to ensure that they were free of potentially cancer-causing changes.

Next, those iPSCs were exposed to a special blend of growth factors to transform them into RPE tissue. That recipe has been pursued by other groups for a while, but needed to be particularly precise for this human application. In order for the tissue to function properly in the retina, the cells must assemble into a uniform sheet, just one-cell thick, and align facing in the same direction.

So, the researchers developed a specially designed scaffold made of biodegradable polymer nanofibers. That scaffold helps to ensure that the cells orient themselves correctly, while also lending strength for surgical transplantation. By spreading a single layer of iPSC-derived RPE progenitors onto their scaffolds and treating it with just the right growth factors, the researchers showed they could produce an RPE patch ready for the clinic in about 10 weeks.

To test the viability of the RPE patch, the researchers first transplanted a tiny version (containing about 2,500 RPE cells) into the eyes of a rat with a compromised immune system, which enables human cells to survive. By 10 weeks after surgery, the human replacement tissue had integrated into the animals’ retinas with no signs of toxicity.

Next, the researchers tested a larger RPE patch (containing 70,000 cells) in pigs with an AMD-like condition. This patch is the same size the researchers ultimately would expect to use in people. Ten weeks after surgery, the RPE patch had integrated into the animals’ eyes, where it protected the light-sensing cells that are so critical for vision, preventing blindness.

These results provide encouraging evidence that the iPSC approach to treating dry AMD should be both safe and effective. But only a well-designed human clinical trial, with all the appropriate prior oversights to be sure the benefits justify the risks, will prove whether or not this bold approach might be the solution to blindness faced by millions of people in the future.

As the U.S. population ages, the number of people with advanced AMD is expected to rise. With continued progress in treatment and prevention, including iPSC technology and many other promising approaches, the hope is that more people with AMD will retain healthy vision for a lifetime.

References:

[1] Clinical-grade stem cell-derived retinal pigment epithelium patch rescues retinal degeneration in rodents and pigs. Sharma R, Khristov V, Rising A, Jha BS, Dejene R, Hotaling N, Li Y, Stoddard J, Stankewicz C, Wan Q, Zhang C, Campos MM, Miyagishima KJ, McGaughey D, Villasmil R, Mattapallil M, Stanzel B, Qian H, Wong W, Chase L, Charles S, McGill T, Miller S, Maminishkis A, Amaral J, Bharti K. Sci Transl Med. 2019 Jan 16;11(475).

[2] Age-Related Macular Degeneration, National Eye Institute.

[3] Autologous Induced Stem-Cell-Derived Retinal Cells for Macular Degeneration. Mandai M, Watanabe A, Kurimoto Y, Hirami Y, Takasu N, Ogawa S, Yamanaka S, Takahashi M, et al. N Engl J Med. 2017 Mar 16;376(11):1038-1046.

Links:

Facts About Age-Related Macular Degeneration (National Eye Institute/NIH)

Stem Cell-Based Treatment Used to Prevent Blindness in Animal Models of Retinal Degeneration (National Eye Institute/NIH)

Kapil Bharti (NEI)

NIH Support: National Eye Institute; Common Fund