AI Makes Retinal Imaging 100x Faster: NIH

The NIH is developing an adaptive optics (AO) technology to enhance imaging devices utilizing optical coherence tomography (OCT).
AI Makes Retinal Imaging 100x Faster: NIH
Representative image by freepik.

Scientists at the National Institutes of Health (NIH) have integrated artificial intelligence (AI) into a cell imaging technique focused on the eye. Their findings indicate a remarkable acceleration in imaging speed by 100 times and a notable 3.5-fold enhancement in image contrast.

This advancement promises to furnish researchers with a superior tool for assessing age-related macular degeneration (AMD) and various other retinal ailments.

“AI helps overcome a key limitation of imaging cells in the retina, which is time,” said Johnny Tam, Ph.D., who leads the Clinical and Translational Imaging Section at NIH's National Eye Institute said.

Tam is pioneering the development of adaptive optics (AO) technology to enhance imaging devices utilizing optical coherence tomography (OCT). Similar to ultrasound, OCT offers a noninvasive, rapid, painless imaging method and is now standard equipment in the majority of eye clinics.

“Our results suggest that AI can fundamentally change how images are captured. Our P-GAN AI will make AO imaging more accessible for routine clinical applications and for studies aimed at understanding the structure, function, and pathophysiology of blinding retinal diseases. Thinking about AI as a part of the overall imaging system, as opposed to a tool that is only applied after images have been captured, is a paradigm shift for the field of AI,” Tam added.

Also Read
Why CDOs Need AI-Powered Data Management to Accelerate AI Readiness in 2024
AI Makes Retinal Imaging 100x Faster: NIH

The NIH also revealed that its scientists have modified an AI algorithm to detect indicators of childbirth-related post-traumatic stress disorder (CB-PTSD) by analyzing brief narrative descriptions provided by postpartum patients.

The AI program effectively recognized a significant portion of participants likely to experience the disorder. With additional enhancements, such as incorporating information from medical records and birth experiences of diverse demographics, the model holds the potential to identify a substantial proportion of individuals at risk.

Earlier this year, the National Institutes of Health (NIH) teamed up with the National Science Foundation (NSF) and the Department of Energy (DOE) to inaugurate the National Artificial Intelligence Research Resource (NAIRR) steering committee.

NAIRR aims to furnish researchers in areas such as healthcare, climate science, and energy with datasets and AI capabilities for advancing artificial intelligence research.

Related Stories

No stories found.
CDO Magazine