.png){kind=icon}
.png){kind=icon}
Return
Plain language summary of disease activity and therapeutic response to pegcetacoplan for geographic atrophy identified by deep learning-based analysis of OCT
.png){kind=icon}
OA
AI
U
J
G
S
W
A
A
E
L
H
DOI：10.1080/1750743X.2025.2569302.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
What is this summary about?
This is a summary of a study that used artificial intelligence (AI) to read images of eyes of people with geographic atrophy, or GA. These images were taken using optical coherence tomography, or OCT. AI was used to monitor how GA affected these eyes over 2 years.
GA damages the area at the back of the eye called the retina. GA mainly affects two layers of cells in theretina: theellipsoid zone (EZ), a layer that includes cells calledphotoreceptorswhich react to light, and theretinal pigment epithelium (RPE), a layer of cells found underneath the EZ that helps keep the photoreceptors and the retina healthy. Over time, GA destroys both the EZ and RPE layers, which leads to formation ofGA lesionsand vision loss.
In this study, OCT images of eyes taken during two earlierphase 3 clinical studiescalled OAKS and DERBY were examined in detail, but this time with AI methods. In the OAKS and DERBY studies, a medicine called pegcetacoplan was tested for the treatment of GA. When these images were looked at again with AI, researchers measured:
How much of the EZ layer and RPE layer were destroyed by the disease over 2 years; and
How much GA lesions grew over 2 years.
After this, they compared these measurements in people who were given pegcetacoplan and people who were not treated during the study.
Why was AI used?
AI can look at thousands of OCT images of eyes without getting tired, unlike a human examiner, while providing exact measurements of cell damage and GA lesion growth faster thanophthalmologists. When AI looks at these images, it can detect damage to the EZ and RPE layers that cannot be seen with standard methods. This helps researchers and ophthalmologists better understand the impact of GA and treatment with pegcetacoplan.
What were the results?
This study found that treatment with pegcetacoplan slowed the destruction of EZ and RPE layers compared with no treatment. It also found that using AI to read 3-dimensional OCT images was better for learning how GA affected EZ and RPE layers in the retina when compared with 2-dimensionalfundus autofluorescence (FAF)images that were originally used in the OAKS and DERBY studies.
What do these results mean?
Ophthalmologists might be able to use AI to read OCT images to help them manage GA better by finding out who will respond best to treatment. Using AI to read the OCT images showed that pegcetacoplan slowed the destruction of the EZ and RPE layers in the retinas of people with GA.
This is an abstract of the Plain Language Summary of Publication article.
View the full Plain Language Summary PDFof this article to read the full-text
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
J
IF:
2.9
Papers:
2.1K
Citations:
3.2K
Organization
Cited Papers