Researchers in the United States have developed an artificial intelligence (AI) technology that speeds up optical coherence tomography (OCT) imaging 100-fold, while improving contrast 3.5-fold.

The advance, they said, would provide researchers with a better tool to evaluate agerelated macular degeneration (AMD) and other retinal diseases.

“Adaptive optics (AO) takes OCT-based imaging to the next level,” said Dr Johnny Tam, who leads the Clinical and Translational Imaging Section at the United States National Institute of Health’s National Eye Institute.

“It’s like moving from a balcony seat to a front row seat to image the retina. With AO, we can reveal 3D retinal structures at cellular-scale resolution, enabling us to zoom in on very early signs of disease.”

While adding AO to OCT provides a much better view of retinal pigment epithelium (RPE) cells, processing AO-OCT images after they’ve been captured takes much longer than OCT without AO.

Imaging the RPE with AO-OCT also produces a phenomenon called speckle. At any given moment, parts of the image may be obscured by speckle. As time passes, speckle shifts, which allows different parts of the cells to become visible. To manage speckle, researchers repeatedly image cells over a long period of time. The scientists then undertake the timeconsuming task of piecing together many images to create an image of the RPE cells that is speckle-free.

DEVELOPING A DEEP LEARNING ALGORITHM

To overcome speckle, Dr Tam and his team developed a novel AI-based method called parallel discriminator generative adversarial network (P-GAN) – a deep learning algorithm.

By feeding the P-GAN network nearly 6,000 manually analysed AO-OCT-acquired images of human RPE, each paired with its corresponding speckled original, the team trained the network to identify and recover speckle-obscured cellular features.

The team estimates that P-GAN reduced imaging acquisition and processing time by about 100-fold. P-GAN also yielded greater contrast, about 3.5 times greater than before.

When tested on new images, P-GAN successfully de-speckled the RPE images, recovering cellular details. With one image capture, it generated results comparable to the manual method, which required the acquisition and averaging of 120 images. The algorithm also outperformed other AI techniques on performance metrics that assess things like cell shape and structure.

“Our results suggest that AI can fundamentally change how images are captured,” Dr Tam said in a media release.1

“Our P-GAN artificial intelligence 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,” he said.

The team’s study was published in Communications Medicine.2

References
1. National Eye Institute, AI makes retinal imaging 100 times faster, compared to manual method (media release, 10 April 2024), available at: nei.nih.gov/about/news-and-events/news/ai-makes-retinal-imaging-100-times-faster-compared-manualmethod [accessed April 2024].
2. Das, V., Zhang, F., Bower, A.J. et al., Revealing speckle obscured living human retinal cells with artificial intelligence assisted adaptive optics optical coherence tomography. Commun Med 4, 68 (2024). DOI: 10.1038/s43856-024-00483-1.