Mount Vernon Student Develops Glaucoma Detection Model

MOUNT VERNON, VA—As many students were on their summer break from school, Avyuk Dixit arrived at a rural eye camp near Pondicherry, India. This was no leisure trip—the Mount Vernon student was there to develop research on eye disease.

Dixit, now a junior at Thomas Jefferson High School for Science and Technology, spent the summer with Aravind Eye Hospital developing a machine learning model for diagnosing glaucoma. He became motivated to research the topic after learning his uncle, a teacher in New Dehli, had glaucoma. He hoped his research could replace ophthalmologists for glaucoma screening processes, making it more accessible, extensive and affordable.

"Visiting him, I saw how his declining vision hurt his ability to teach, read fine-printed textbooks, and detracted generally from his livelihood," writes Dixit about his experience. "Seeing a close family member suffer like that made me realize how privileged I was. I hope that my solution will be able to help him and others suffering with glaucoma on an international scale."

Ultimately Dixit made a model to detect glaucoma using the fundus images of the eye. His model diagnoses glaucoma with a top accuracy of 87 percent.

Dixit has a deep interest in computer science, particularly computer vision and machine learning. His other research projects have monitored glaucoma progression in patients, detected violent behavior based on human pose estimation and created a client-side application to alerts users of phishing.

His research may be confounding for someone outside the computer science field, but his sense of purpose is clear.

"Nobody is too young or too old to give back to others," writes Dixit. "As a community, we have an obligation to help those in need and allow them access to equal opportunities."

Image: Avyuk Dixit with other volunteers at an eye camp in India, courtesy photo