The quality of retinal images is compromised by aberrations that remain uncorrected even in confocal adaptive optics imaging. This study demonstrates phase diversity (PD), a computational imaging technique,...

This past week, the New England Journal of Medicine released one of its excellent instructional videos, detailing how to do direct ophthalmoscopy to examine the retina. That’s the use of one of those ...

Eye, Published online: 20 January 2025; doi:10.1038/s41433-025-03607-6Features of intermediate and late dry age-related macular degeneration on adaptive optics ophthalmoscopy: Pinnacle Study Report 8

The ocular fundus can reveal a wealth of pathophysiological findings. Direct ophthalmoscopy is challenging in emergency settings, but non-mydriatic fundus photography can improve early and accurate…

Background: The availability of dedicated image analysis scripts for adaptive optics (AO)–flood illumination ophthalmoscopy (FIO) is limited, especially for large-scale measurements and analyses of nonhealthy images. This limitation highlights the need for alternative approaches to facilitate automated and scalable analysis. Large language models may help develop such scripts. Objective: This study aimed to generate an analysis script for AO-FIO images in the R programming language using a widely available generative AI (GenAI; specifically, GPT-4) as a proof of principle for generating a functional but nonvalidated script. Methods: GPT-4 was used to generate an R script for the analysis of AO-FIO images. The code generated by GPT-4 was fine-tuned iteratively based on trial and error, testing the script for image preprocessing and analysis using images from 4 participants, including 1 healthy individual and 3 patients with Stargardt disease. The script code was subsequently checked for errors by another researcher who was naive to previous coding, using a different test set of AO-FIO images from 4 other participants (n=1 healthy individual and n=3 patients with Stargardt disease). The cone counts from 5 AO image snippets were compared with the counts independently recorded by 2 human graders and those generated by pre-existing AO analysis software that was trained on healthy participants. Results: After 54 iterations of instructions, a functional R script for the analysis of AO-FIO images was generated. The script identified and quantified blobs. Conclusions: We developed a preliminary nonvalidated script for cone detection in retinal AO images with support from GPT-4. Before such a script can be used in clinical research, it should undergo more fine-tuning and extensive testing. Future work should enhance the image analysis capabilities of the script and validate its results to assess the potential of AO-based cone counts as biomarkers in clinical trials.

UCL Discovery is UCL's open access repository, showcasing and providing access to UCL research outputs from all UCL disciplines.