Findings from Department of Refractive Surgery Update Understanding of Refractive Errors (Deep Transfer Learning for Ethnically Distinct Populations: Prediction of Refractive Error Using Optical Coherence Tomography).

A recent report discusses research conducted in Seoul, South Korea, on refractive errors in ethnically diverse populations. The study aimed to improve the performance of deep learning models in predicting refractive errors using optical coherence tomography (OCT) images. The researchers used a deep transfer learning model with adaptation training to reduce performance differences between ethnic groups and image domains. The study found that the adaptation models significantly outperformed those without adaptation in predicting spherical equivalent and mean keratometry values. However, the researchers noted that further studies with larger sample sizes are needed to confirm the feasibility of their algorithm. [Extracted from the article]