High-resolution retinal images with artificial intelligence – Articles

Applied by researchers from the National Institutes of Health artificial intelligence (AI) refers to a technology that produces high-resolution images of cells in the eye. They reported that with AI, images became 100 times faster and image contrast improved by 3.5 times. They say this advance will provide researchers with a better tool to evaluate Age-related macular degeneration (AMD) and other retinal diseases.

Vineeta Das, NEI's Department of Clinical and Translational Imaging, explains how artificial intelligence improves images of light-sensitive retinas.

“AI helps overcome the main limitation of retinal cells, which is time,” said Johnny Tam, Ph.D., who directs the Division of Clinical and Translational Imaging at the National Eye Institute of the National Institutes of Health.

TAM is developing a technology called… Adaptive optics (AO) to improve imaging devices based on CT scan Optical coherence (October). Like ultrasound, OCT is a non-invasive, rapid, painless device that is standard in most eye clinics.

“the Adaptive optics “This takes OCT-based imaging to the next level,” Tam said. “It's like going from a balcony seat to a front-row seat to viewing the retina. Using AO, we can detect 3D retinal structures with wide-field resolution. This allows us to get closer One of the early signs of the disease.

Image: Johnny Tam, PhD, NEI Division of Clinical and Translational Imaging.

While adding adaptive optics (AO) to CT scan Optical coherence (OCT) provides a much better view of the cells, and AO-OCT images take much longer to process after they are captured than OCT without AO.

Tam's most recent work focuses on… Retinal pigment epithelium (RPE), a layer of tissue located behind the light-sensitive retina that supports metabolically active retinal neurons, including photoreceptors. The retina lines the back of the eye and captures, processes, and converts light that enters the front of the eye into signals that it then transmits through the optic nerve to the brain. Scientists are interested in the RPE because many retinal diseases occur when the RPE deteriorates.

Illustration of the eye showing the location of the retina and the retinal pigment epithelium (RPE).

Top-down view of lab-grown RPE cells viewed using high-resolution microscopy. Unlike AO-OCT, which is performed on an awake person, this image is created using preserved tissue. Credit: Kapil Bharti, National Eye Institute.

Imaging RPE cells using AO-OCT brings new challenges, including a phenomenon called speckle. Mottling interferes with AO-OCT in the same way that clouds interfere with aerial photography. At any time, some parts of the image may be obscured. Managing websites is similar to managing cloud cover. Researchers obtain repeated images of cells over a long period of time. Over time, the stain changes, allowing different parts of the cells to show through. Scientists then undertake the tedious and time-consuming task of stitching together many images to create a spot-free image of RPE cells.