Scientists from the National Eye Institute (NEI) discovered five subpopulations of retinal pigment epithelium (RPE). Using artificial intelligence (AI), the researchers were able to analyze images of RPE at single-cell resolution to create a reference map that locates each subpopulation within the eye.
Their findings are published in the journal Proceedings of the National Academy of Sciences, in a paper titled, “Single-cell–resolution map of human retinal pigment epithelium helps discover subpopulations with differential disease sensitivity.”
“These results provide a first-of-its-kind framework for understanding different RPE cell subpopulations and their vulnerability to retinal diseases, and for developing targeted therapies to treat them,” said Michael F. Chiang, MD, director of the NEI, part of the National Institutes of Health.
“The findings will help us develop more precise cell and gene therapies for specific degenerative eye diseases,” said the study’s lead investigator, Kapil Bharti, PhD, who directs the NEI Ocular and Stem Cell Translational Research Section.
The team used AI to analyze RPE cell morphometry, the external shape, and dimensions of each cell. They trained a computer using fluorescently-labeled images of RPE to analyze the entire human RPE monolayer from nine cadaver donors with no history of significant eye disease.
Unexpectedly, they discovered that the peripheral retina contains a ring of RPE cells (P4) with a cell area very similar to RPE in and around the macula.
“The presence of the P4 subpopulation highlights the diversity within retinal periphery, suggesting that there could be functional differences among RPE that we are currently unaware of,” said the study’s first author, Davide Ortolan, PhD, a research fellow in the NEI Ocular and Stem Cell Translational Research Section. “Future studies are needed to help us understand the role of this subpopulation.”
To further test the hypothesis that different retinal degenerations affect specific RPE subpopulations, they analyzed ultrawide-field fundus autofluorescence images from patients affected by choroideremia, L-ORD, or a retinal degeneration with no identified molecular cause.
“Overall, the results suggest that AI can detect changes of RPE cell morphometry prior to the development of visibly apparent degeneration,” said Ortolan.