Skip to main content

Artificial Intelligence Getting Smarter! Innovations from the Vision Field

Posted on by Michael F. Chiang, M.D., National Eye Institute

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.


[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.


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.]


  • Vicente Sanchez Crespo says:

    excellence. Doctors helping patients. it is our life work.

  • Ruby says:

    Are there uses of AI to determine if there are covid related issues at the cellular level? Usually symptoms are evident long after some manifestation at the cellular level that is not easily detected. Especially true when it comes to the brain. Sometimes behavioral changes are observed much earlier than anything is detected in MRIs. Something to keep in mind as the virus evolves to evade our interventions.

    • Mrs. Woods says:

      I disagree that artificial intelligence is getting smarter. However, perceived belief that AI is getting smarter, is the first step towards failure and misunderstanding. …

  • S. Rajapakse says:

    Artificial Intelligence by far is the most dangerous thing, why? Because all these things one either see, hear, feel or know end up ultimately illustrating the consciousness as Name & Form-Perceptions (Nama & Rupa-Sanna). As I see these artificial intelligence things will illustrate the consciousness negatively.THe Nama & Form_perceptions are the forerunners to mind and thus will lead to negative minds. Future is going to be really dangerous for Human Beings!

  • Zuccheri Gianni says:

    It had just finished snowing, at the end of the morning the last patient enters: he comes from a distant mountain town, at about one hundred miles.
    90 years old, suffering from diabetes II, he comes for his annual fundus screening.
    “Everything is ok, you can go satisfied, see you next year.
    You have to wait before driving, because your pupils are dilated ”
    I admired this person who faced these problems with his age.
    I promised myself to organize fundus screening in telemedicine, with a retinograph that remotely sends images of the eye: how many avoidable inconveniences for the sick and their relatives.
    Then, another patient over 90 years old comes to mind: periodic checkups for severe maculopathy, his handshake still has a youthful vigor.

    We await new technologies that increase the autonomy of the blind person.
    These technological means employing AI have multiple values: better efficiency, better precision and greater access to treatment, for diseases that are increasingly widespread in the population.

  • Zuccheri Gianni says:

    AI is already very useful, but is it enough alone?

    A new patient came to perform an exam OCT to monitor a retinal hemorrhagic picture , classified as originating from of a branch retinal vein occlusion, arose a few days ago.He had worsened since the first OCT, his blood tests worried me: he was performing heparin therapy, despite immediately presenting a low number of platelets (due to previous liver problems). There was a risk of life-threatening systemic bleeding. Then, I tried to find clarifying OCT images, which revealed a maculopathy with new hidden bleeding vessels.

    With this ocular clinical case report, I would like to emphasize that when there are controversial aspects of the clinical picture, the physicians should always doubt the diagnosis that the technologies provide in the first place.

  • Zuccheri Gianni says:

    What kind of experience among the factors that can affect the programming of the algorithms used in Artificial Intelligence?

    A few years ago, a man in his 30s came for a visit, reporting sudden visual loss in his right eye.
    So, I find in his retina a vast and worrying hemorrhage, inexplicable: without trauma and without reported diseases.
    OCT examination of the retina revealed the details of the bleeding.
    I urgently sent the patient for general hospital evaluation: lymphoma was discovered!
    Thanks to the treatments he was saved, today after about six years, he is in excellent health.

    This is, fortunately, a case of rare frequency but still possible: the help of technology alone is not enough to find the solution

  • Zuccheri Gianni says:

    In the 1980s I analyzed photographs of the corneal endothelium by counting the cells one by one; then the graphic tablet of the computer arrived, I traced the contours of the cells to obtain their dimensions: long and expensive work!
    Today, the instrument tells me the result immediately, through the automatic analysis of the corneal endothelial cell layer.
    This is an application of Artificial Intelligence that has turned the dream of the past into reality.

  • Fahmida Pathan says:

    With artificial intelligence people should also get more smarter.

Leave a Comment