Is AI the Answer? With healthcare systems lagging, applications of AI in ophthalmic imaging shows significant promise

Renowned ophthalmologist and expert in imaging and machine learning Dr. Suber Huang talked to us about how artificial intelligence is set to transform the field of ophthalmic imaging like never before. 

Over the past few years, artificial intelligence (AI) has been a force that is permeating all aspects of our lives, brought on by the digital era and accelerated by the COVID-19 pandemic.1 

In ophthalmology, deep learning has been widely used in imaging, such as fundus photographs, optical coherence tomography (OCT), and visual fields — achieving robust classification performance in the detection of diseases like diabetic retinopathy and retinopathy of prematurity, glaucoma-like disc, macular edema, and age-related macular degeneration.2

AI in Ophthalmology: An unstoppable revolution

“Imaging in ophthalmology is undergoing a revolution in all facets,” started Dr. Suber Huang, founder and CEO of Future Vision Foundation (Ohio, USA). 

“While there used to be just fundus photographs, clinical exams, and fluorescence angiography, there are now many kinds of imaging modalities, such as OCT and its different kinds, including intraoperative OCT, as well as multimodal imaging,” he shared. 

He added that combining these imaging modalities with AI and machine learning would allow us not only to look into the structure (of the eye) but also potentially its function. “Also, federated machine learning is a very important concept in AI, where we can use lots and lots of data and have findings and insights that we would never have before. By aggregating lots of data potentially from all over the world, such as the natural history of a million patients, we can have a better view of things that we can never do before,” he continued. 

“On a sophisticated level, AI can do repeated tasks quickly and repetitively with a kind of certainty that’s difficult (for humans) to do. And at the highest level is the fact that it can learn from its algorithm, either from a dataset that we already know, or potentially educate itself as we go on,” he explained.  

The importance of data sharing

While Dr. Huang has many notable achievements under his belt, the most historic one is the Retina Image Bank, a vast open-access library of more than 25,000 unique and downloadable retina images.

“A work which I am most proud of is the Retina Image Bank platform. It is a program of the America Society of Retina Specialists, which I started approximately 10 years ago,” he shared. “Initially, it works as a repository of educational material, fundus photographs, and all kinds of things related to the retina. Today, it is growing very well, not surprisingly. It took about three years to get to a million page views. And this summer, we passed 3 million page views. It’s been used in over 181 of 183 identified countries in the world, and we have 40 thousand hits per month. The important thing is, it is the world’s largest, most comprehensive open-access site,” he said proudly. 

He also stressed the importance of data sharing between AI platforms, which could facilitate more accurate models and results. “Market forces allow companies to address an unmet need to thrive, but the bigger picture is, for instance, to share data that otherwise is generated but lost. For example, if a clinical trial succeeds, that data is published. But if a study is extremely well done but doesn’t meet its endpoint, that data is sequestered and lost,” he noted. 

“To have a robust AI system, you would really like to have a million images that reflect the whole world. And it is important to devise systems that can link and share data across platforms all over the world,” he emphasized. 

AI in the Asia-Pacific 

Is AI the Answer? With healthcare systems lagging, applications of AI in ophthalmic imaging shows significant promise

Dr. Huang described the Asia-Pacific region as a growing and very important region in the world, as it houses the majority of the population worldwide. “However, the healthcare systems in the region are lagging behind, and every healthcare system is under financial constraint. In short, there are too few doctors for too many patients. So we are looking for ways to increase the efficiency of medical care here,” he said. 

And AI may just be the answer. By using AI to do repetitive tasks such as screening, physicians will not be put out of jobs, but every patient they see will potentially be presented at the right time required to save their vision, noted Dr. Huang. 

“I think there are opportunities all around for innovation, which will make things better and easier — just as each version of our cell phone gets a little bit better and a little bit easier to use. But the real major innovation is unpredictable, and we don’t know when that will come,” he mused.


  1. Benet D, Pellicer-Valero OJ. Artificial intelligence: the unstoppable revolution in ophthalmology. Surv Ophthalmol. 2022;67(1):252-270. 
  2. Ting DSW, Pasquale LR, Peng L, et al. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019;103(2):167-175.

Suber Huang

Dr. Suber Huang

is the CEO of the Retina Center of Ohio and a voluntary assistant clinical professor of ophthalmology at Bascom Palmer Eye Institute, University of Miami, Florida, USA. He is also the CEO of the Future Vision Foundation, whose mission celebrates breakthrough vision research through powerful documentaries of discovery, impact, and hope. He created the Future Vision Forum to bring visionary leaders in basic, translational, and clinical research together to seek new directions that accelerate discovery and innovation. Dr. Huang has over 25 years of experience as a retina specialist and has held various leadership positions, such as being the president of the American Society of Retina Specialists. Also, he has received numerous awards, including the “Top Doctors” and “Best Doctors in America” awards each year since 2003. [Email:]

Notify of
Inline Feedbacks
View all comments