How AI could protect millions of people from vision loss 

Myopia, commonly known as nearsightedness, is increasingly prevalent, especially among children. Experts predict that by 2050, approximately 50% of the world’s population will be affected by myopia, which potentially leads to vision loss. 

Researchers attribute this surge partly to an increase in “near work,” which involves focusing on close objects like smartphones and computer screens.

Myopia increases the risk of vision loss

While many people manage myopia with glasses or contact lenses, some develop a more severe condition called myopic maculopathy. 

This condition occurs when the macula – the part of the eye responsible for sharp, central vision – is stretched and damaged due to the elongation of the eyeball into a more football-like shape. The distortion leads to impaired vision and can result in severe vision loss or blindness.

In 2015, myopic maculopathy caused visual impairment in 10 million people. If current trends continue, more than 55 million people are expected to experience vision loss due to this condition by 2050, and approximately 18 million people worldwide could become blind from it.

Improving early detection with technology

Because myopic maculopathy is irreversible, early detection is crucial. Catching the condition in its initial stages can improve health outcomes, especially for children. Ophthalmologists can prescribe special contact lenses or eye drops that slow the disease’s progression.

A team of researchers at Arizona State University’s School of Computing and Augmented Intelligence is developing new diagnostic tools that leverage artificial intelligence (AI) to more effectively screen for myopic maculopathy. 

Yalin Wang, a professor of computer science and engineering at the university, emphasizes the potential of technology to provide important solutions.

“AI is ushering in a revolution that leverages global knowledge to improve diagnosis accuracy, especially in its earliest stage of the disease,” he said. “These advancements will reduce medical costs and improve the quality of life for entire societies.”

Award-winning AI algorithms

In response to this need, the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society issued a challenge in 2023 to improve computer-aided screening systems for retinal images. 

Currently, myopic maculopathy is diagnosed using optical coherence tomography scans that create detailed images of the retina using reflected light. These scans are often manually inspected by ophthalmologists, which is time-consuming and requires specialized expertise.

Professor Wang and his team, including doctoral student Wenhui Zhu and neurologist and adjunct faculty member Dr. Oana Dumitrascu, participated in the MICCAI challenge and were among the winners. 

For the first part of their work, they classified myopic maculopathy into five categories according to its severity. Accurate classification helps ophthalmologists provide more tailored and effective treatments.

The researchers developed new AI algorithms called NN-MobileNet, designed to help software more effectively analyze retinal images and predict the correct classification of myopic maculopathy. Their research was published in the journal Myopic Maculopathy Analysis.

Crucial insights with deep neural networks

Next, the team focused on efforts in the scientific community to use deep neural networks – a type of AI – to predict the spherical equivalent in retinal scans. The spherical equivalent is an estimate of the eye’s refractive error, crucial for prescribing corrective lenses. 

By developing new AI algorithms that emphasized data quality and relevance, they achieved exceptional results while minimizing computing power requirements. This research was also published in Myopic Maculopathy Analysis.

Additionally, Professor Wang collaborated with other winning teams from the MICCAI challenge on a third research paper, published in JAMA Ophthalmology in September. 

The researchers made their findings available to stimulate further advancements in the early and effective diagnosis of myopic maculopathy, aiming to improve health care outcomes globally.

Addressing health disparities

Professor Wang explained that one of the driving forces behind his work is addressing health disparities. “People living in rural areas find it difficult to access sophisticated imaging devices and see physicians,” he said. 

“Once AI-powered technology becomes available, it will significantly improve the quality of life in worldwide populations, including those who live in developing countries.”

Solutions to prevent vision loss

Ross Maciejewski, director of the School of Computing and Augmented Intelligence, praised Wang’s project as an important example of innovative work in the medical field. 

“With both myopia and myopic maculopathy increasing, solutions are needed to prevent vision loss and help health care professionals provide the best treatment options for their patients,” said Maciejewski.

“Yalin Wang’s innovative research is a principled use of artificial intelligence to address this dire medical issue.”

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–